| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 268, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0037313432835820895, | |
| "grad_norm": 267.42432987632304, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 2.0376, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018656716417910446, | |
| "grad_norm": 497.8829601573007, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 5.6478, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03731343283582089, | |
| "grad_norm": 454.2837874993471, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 9.0654, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.055970149253731345, | |
| "grad_norm": 172.70761646653747, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 11.6263, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 431.0320152584827, | |
| "learning_rate": 0.00014814814814814815, | |
| "loss": 12.0175, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09328358208955224, | |
| "grad_norm": 57.24075920715652, | |
| "learning_rate": 0.0001851851851851852, | |
| "loss": 10.5566, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11194029850746269, | |
| "grad_norm": 207.16475278732815, | |
| "learning_rate": 0.00019992354201925428, | |
| "loss": 22.4578, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13059701492537312, | |
| "grad_norm": 39.84010000225324, | |
| "learning_rate": 0.0001994567221375987, | |
| "loss": 13.0098, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 421.8360841321533, | |
| "learning_rate": 0.00019856753906964686, | |
| "loss": 17.1304, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16791044776119404, | |
| "grad_norm": 32.18021173317482, | |
| "learning_rate": 0.00019725976891203376, | |
| "loss": 9.8365, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1865671641791045, | |
| "grad_norm": 17.663716447972774, | |
| "learning_rate": 0.00019553896537655318, | |
| "loss": 7.5461, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20522388059701493, | |
| "grad_norm": 15.828267774314414, | |
| "learning_rate": 0.0001934124362051919, | |
| "loss": 6.9658, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 307.89143980814515, | |
| "learning_rate": 0.000190889212136318, | |
| "loss": 7.6309, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24253731343283583, | |
| "grad_norm": 17.3100107773664, | |
| "learning_rate": 0.0001879800085538147, | |
| "loss": 6.9331, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.26119402985074625, | |
| "grad_norm": 42.588666065454795, | |
| "learning_rate": 0.00018469717998202462, | |
| "loss": 6.9227, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2798507462686567, | |
| "grad_norm": 10.804006051624885, | |
| "learning_rate": 0.00018105466761975109, | |
| "loss": 6.5832, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 43.74337828897061, | |
| "learning_rate": 0.00017706794013612364, | |
| "loss": 6.8176, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31716417910447764, | |
| "grad_norm": 64.2085843780536, | |
| "learning_rate": 0.00017275392797975032, | |
| "loss": 6.7523, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3358208955223881, | |
| "grad_norm": 16.593450775671112, | |
| "learning_rate": 0.0001681309514801265, | |
| "loss": 6.5873, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35447761194029853, | |
| "grad_norm": 44.277670283010906, | |
| "learning_rate": 0.00016321864304663173, | |
| "loss": 6.5937, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 10.997588847093564, | |
| "learning_rate": 0.0001580378637955128, | |
| "loss": 6.4452, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3917910447761194, | |
| "grad_norm": 12.654122748772814, | |
| "learning_rate": 0.00015261061495891345, | |
| "loss": 6.3491, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.41044776119402987, | |
| "grad_norm": 26.609938261473722, | |
| "learning_rate": 0.00014695994445216985, | |
| "loss": 6.4977, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4291044776119403, | |
| "grad_norm": 29.405974371105227, | |
| "learning_rate": 0.00014110984899615367, | |
| "loss": 6.3102, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 14.382835497900352, | |
| "learning_rate": 0.000135085172210319, | |
| "loss": 6.2751, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4664179104477612, | |
| "grad_norm": 27.156229733294634, | |
| "learning_rate": 0.00012891149910922267, | |
| "loss": 6.148, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.48507462686567165, | |
| "grad_norm": 14.830451492836382, | |
| "learning_rate": 0.00012261504745055964, | |
| "loss": 5.9625, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.503731343283582, | |
| "grad_norm": 16.181539488534295, | |
| "learning_rate": 0.00011622255639612554, | |
| "loss": 5.8024, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 7.100118045807948, | |
| "learning_rate": 0.00010976117295853154, | |
| "loss": 5.7823, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5410447761194029, | |
| "grad_norm": 6.078519973242612, | |
| "learning_rate": 0.00010325833671589687, | |
| "loss": 5.6857, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5597014925373134, | |
| "grad_norm": 10.507318938395432, | |
| "learning_rate": 9.674166328410318e-05, | |
| "loss": 5.5985, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5783582089552238, | |
| "grad_norm": 7.511601189522553, | |
| "learning_rate": 9.023882704146848e-05, | |
| "loss": 5.5306, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 9.098000461581764, | |
| "learning_rate": 8.377744360387447e-05, | |
| "loss": 5.4113, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6156716417910447, | |
| "grad_norm": 11.04848131475541, | |
| "learning_rate": 7.738495254944042e-05, | |
| "loss": 5.3399, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6343283582089553, | |
| "grad_norm": 4.899181488882252, | |
| "learning_rate": 7.108850089077735e-05, | |
| "loss": 5.2061, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6529850746268657, | |
| "grad_norm": 8.571361713934442, | |
| "learning_rate": 6.491482778968104e-05, | |
| "loss": 5.1067, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 6.366810352482946, | |
| "learning_rate": 5.889015100384636e-05, | |
| "loss": 4.9611, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6902985074626866, | |
| "grad_norm": 7.987975314659695, | |
| "learning_rate": 5.304005554783015e-05, | |
| "loss": 4.9129, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7089552238805971, | |
| "grad_norm": 4.106981286779299, | |
| "learning_rate": 4.738938504108659e-05, | |
| "loss": 4.8382, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7276119402985075, | |
| "grad_norm": 3.7918439805690527, | |
| "learning_rate": 4.196213620448723e-05, | |
| "loss": 4.7711, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 3.6468350915483128, | |
| "learning_rate": 3.6781356953368284e-05, | |
| "loss": 4.6595, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7649253731343284, | |
| "grad_norm": 2.974947620754676, | |
| "learning_rate": 3.186904851987351e-05, | |
| "loss": 4.638, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7835820895522388, | |
| "grad_norm": 2.355137193482797, | |
| "learning_rate": 2.724607202024969e-05, | |
| "loss": 4.5794, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8022388059701493, | |
| "grad_norm": 3.096708977884932, | |
| "learning_rate": 2.2932059863876365e-05, | |
| "loss": 4.5585, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8208955223880597, | |
| "grad_norm": 2.8473392855240984, | |
| "learning_rate": 1.8945332380248913e-05, | |
| "loss": 4.4602, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8395522388059702, | |
| "grad_norm": 2.7970718450568692, | |
| "learning_rate": 1.5302820017975394e-05, | |
| "loss": 4.419, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8582089552238806, | |
| "grad_norm": 3.5908637322056407, | |
| "learning_rate": 1.2019991446185309e-05, | |
| "loss": 4.394, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8768656716417911, | |
| "grad_norm": 2.327431302717702, | |
| "learning_rate": 9.110787863682002e-06, | |
| "loss": 4.3572, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 3.3167882122894534, | |
| "learning_rate": 6.587563794808127e-06, | |
| "loss": 4.3148, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.914179104477612, | |
| "grad_norm": 3.128747890951307, | |
| "learning_rate": 4.461034623446847e-06, | |
| "loss": 4.3543, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.9328358208955224, | |
| "grad_norm": 2.4600560952322423, | |
| "learning_rate": 2.7402310879662497e-06, | |
| "loss": 4.301, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9514925373134329, | |
| "grad_norm": 2.0585484791225954, | |
| "learning_rate": 1.43246093035313e-06, | |
| "loss": 4.2912, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9701492537313433, | |
| "grad_norm": 1.864333596517171, | |
| "learning_rate": 5.432778624013257e-07, | |
| "loss": 4.281, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9888059701492538, | |
| "grad_norm": 1.6036658756559803, | |
| "learning_rate": 7.645798074572552e-08, | |
| "loss": 4.2827, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 5.337969779968262, | |
| "eval_runtime": 2.3919, | |
| "eval_samples_per_second": 0.836, | |
| "eval_steps_per_second": 0.418, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 268, | |
| "total_flos": 14002264473600.0, | |
| "train_loss": 6.666975224196022, | |
| "train_runtime": 4378.2382, | |
| "train_samples_per_second": 1.956, | |
| "train_steps_per_second": 0.061 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 268, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 14002264473600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |