diff --git "a/checkpoints/checkpoint-5380/trainer_state.json" "b/checkpoints/checkpoint-5380/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoints/checkpoint-5380/trainer_state.json"
@@ -0,0 +1,4079 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.96385542168675,
+  "eval_steps": 150,
+  "global_step": 5380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03707136237256719,
+      "grad_norm": 53.36411666870117,
+      "learning_rate": 1.1152416356877324e-06,
+      "loss": 10.8165,
+      "step": 10
+    },
+    {
+      "epoch": 0.07414272474513438,
+      "grad_norm": 61.33858871459961,
+      "learning_rate": 2.2304832713754648e-06,
+      "loss": 10.8463,
+      "step": 20
+    },
+    {
+      "epoch": 0.11121408711770157,
+      "grad_norm": 67.16305541992188,
+      "learning_rate": 3.345724907063197e-06,
+      "loss": 10.821,
+      "step": 30
+    },
+    {
+      "epoch": 0.14828544949026876,
+      "grad_norm": 62.08958053588867,
+      "learning_rate": 4.4609665427509296e-06,
+      "loss": 10.4704,
+      "step": 40
+    },
+    {
+      "epoch": 0.18535681186283595,
+      "grad_norm": 53.839927673339844,
+      "learning_rate": 5.576208178438661e-06,
+      "loss": 10.8568,
+      "step": 50
+    },
+    {
+      "epoch": 0.22242817423540315,
+      "grad_norm": 57.02272033691406,
+      "learning_rate": 6.691449814126394e-06,
+      "loss": 10.3005,
+      "step": 60
+    },
+    {
+      "epoch": 0.2594995366079703,
+      "grad_norm": 88.16449737548828,
+      "learning_rate": 7.806691449814127e-06,
+      "loss": 9.6009,
+      "step": 70
+    },
+    {
+      "epoch": 0.2965708989805375,
+      "grad_norm": 84.35252380371094,
+      "learning_rate": 8.921933085501859e-06,
+      "loss": 9.7448,
+      "step": 80
+    },
+    {
+      "epoch": 0.3336422613531047,
+      "grad_norm": 77.93982696533203,
+      "learning_rate": 1.0037174721189593e-05,
+      "loss": 9.5922,
+      "step": 90
+    },
+    {
+      "epoch": 0.3707136237256719,
+      "grad_norm": 56.669166564941406,
+      "learning_rate": 1.1152416356877323e-05,
+      "loss": 10.0919,
+      "step": 100
+    },
+    {
+      "epoch": 0.4077849860982391,
+      "grad_norm": 56.652488708496094,
+      "learning_rate": 1.2267657992565056e-05,
+      "loss": 10.2733,
+      "step": 110
+    },
+    {
+      "epoch": 0.4448563484708063,
+      "grad_norm": 63.472042083740234,
+      "learning_rate": 1.3382899628252788e-05,
+      "loss": 9.4547,
+      "step": 120
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 78.0159912109375,
+      "learning_rate": 1.4498141263940521e-05,
+      "loss": 9.1738,
+      "step": 130
+    },
+    {
+      "epoch": 0.5189990732159406,
+      "grad_norm": 68.1931381225586,
+      "learning_rate": 1.5613382899628255e-05,
+      "loss": 10.0876,
+      "step": 140
+    },
+    {
+      "epoch": 0.5560704355885079,
+      "grad_norm": 49.315216064453125,
+      "learning_rate": 1.6728624535315986e-05,
+      "loss": 10.3721,
+      "step": 150
+    },
+    {
+      "epoch": 0.5560704355885079,
+      "eval_loss": 2.559400796890259,
+      "eval_runtime": 34.304,
+      "eval_samples_per_second": 47.166,
+      "eval_steps_per_second": 6.763,
+      "step": 150
+    },
+    {
+      "epoch": 0.593141797961075,
+      "grad_norm": 34.1899528503418,
+      "learning_rate": 1.7843866171003718e-05,
+      "loss": 10.4711,
+      "step": 160
+    },
+    {
+      "epoch": 0.6302131603336423,
+      "grad_norm": 37.074134826660156,
+      "learning_rate": 1.895910780669145e-05,
+      "loss": 9.9383,
+      "step": 170
+    },
+    {
+      "epoch": 0.6672845227062094,
+      "grad_norm": 49.323158264160156,
+      "learning_rate": 2.0074349442379185e-05,
+      "loss": 10.0448,
+      "step": 180
+    },
+    {
+      "epoch": 0.7043558850787767,
+      "grad_norm": 53.07639694213867,
+      "learning_rate": 2.1189591078066917e-05,
+      "loss": 9.8467,
+      "step": 190
+    },
+    {
+      "epoch": 0.7414272474513438,
+      "grad_norm": 38.345916748046875,
+      "learning_rate": 2.2304832713754645e-05,
+      "loss": 9.9434,
+      "step": 200
+    },
+    {
+      "epoch": 0.7784986098239111,
+      "grad_norm": 47.55274963378906,
+      "learning_rate": 2.3420074349442377e-05,
+      "loss": 9.7912,
+      "step": 210
+    },
+    {
+      "epoch": 0.8155699721964782,
+      "grad_norm": 59.17176055908203,
+      "learning_rate": 2.4535315985130112e-05,
+      "loss": 9.7905,
+      "step": 220
+    },
+    {
+      "epoch": 0.8526413345690455,
+      "grad_norm": 52.57457733154297,
+      "learning_rate": 2.5650557620817844e-05,
+      "loss": 9.9412,
+      "step": 230
+    },
+    {
+      "epoch": 0.8897126969416126,
+      "grad_norm": 42.251304626464844,
+      "learning_rate": 2.6765799256505576e-05,
+      "loss": 10.0084,
+      "step": 240
+    },
+    {
+      "epoch": 0.9267840593141798,
+      "grad_norm": 46.63966369628906,
+      "learning_rate": 2.788104089219331e-05,
+      "loss": 10.0139,
+      "step": 250
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 27.772289276123047,
+      "learning_rate": 2.8996282527881043e-05,
+      "loss": 9.3794,
+      "step": 260
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 46.3179931640625,
+      "learning_rate": 2.9987608426270136e-05,
+      "loss": 9.5747,
+      "step": 270
+    },
+    {
+      "epoch": 1.0370713623725671,
+      "grad_norm": 45.746551513671875,
+      "learning_rate": 2.98636926889715e-05,
+      "loss": 9.6763,
+      "step": 280
+    },
+    {
+      "epoch": 1.0741427247451343,
+      "grad_norm": 49.50416564941406,
+      "learning_rate": 2.9739776951672864e-05,
+      "loss": 10.4789,
+      "step": 290
+    },
+    {
+      "epoch": 1.1112140871177016,
+      "grad_norm": 43.72733688354492,
+      "learning_rate": 2.9615861214374226e-05,
+      "loss": 9.7244,
+      "step": 300
+    },
+    {
+      "epoch": 1.1112140871177016,
+      "eval_loss": 2.6879734992980957,
+      "eval_runtime": 34.2522,
+      "eval_samples_per_second": 47.238,
+      "eval_steps_per_second": 6.773,
+      "step": 300
+    },
+    {
+      "epoch": 1.1482854494902688,
+      "grad_norm": 48.68376541137695,
+      "learning_rate": 2.9491945477075588e-05,
+      "loss": 9.9421,
+      "step": 310
+    },
+    {
+      "epoch": 1.185356811862836,
+      "grad_norm": 44.014747619628906,
+      "learning_rate": 2.9368029739776953e-05,
+      "loss": 9.5022,
+      "step": 320
+    },
+    {
+      "epoch": 1.222428174235403,
+      "grad_norm": 49.858642578125,
+      "learning_rate": 2.9244114002478315e-05,
+      "loss": 9.6801,
+      "step": 330
+    },
+    {
+      "epoch": 1.2594995366079704,
+      "grad_norm": 49.97459411621094,
+      "learning_rate": 2.9120198265179677e-05,
+      "loss": 9.25,
+      "step": 340
+    },
+    {
+      "epoch": 1.2965708989805376,
+      "grad_norm": 40.38698196411133,
+      "learning_rate": 2.8996282527881043e-05,
+      "loss": 10.2879,
+      "step": 350
+    },
+    {
+      "epoch": 1.3336422613531047,
+      "grad_norm": 29.797264099121094,
+      "learning_rate": 2.8872366790582405e-05,
+      "loss": 9.97,
+      "step": 360
+    },
+    {
+      "epoch": 1.3707136237256718,
+      "grad_norm": 43.83412551879883,
+      "learning_rate": 2.874845105328377e-05,
+      "loss": 9.3751,
+      "step": 370
+    },
+    {
+      "epoch": 1.407784986098239,
+      "grad_norm": 42.754154205322266,
+      "learning_rate": 2.8624535315985132e-05,
+      "loss": 9.8947,
+      "step": 380
+    },
+    {
+      "epoch": 1.4448563484708064,
+      "grad_norm": 50.08184051513672,
+      "learning_rate": 2.8500619578686494e-05,
+      "loss": 9.4987,
+      "step": 390
+    },
+    {
+      "epoch": 1.4819277108433735,
+      "grad_norm": 41.81029510498047,
+      "learning_rate": 2.8376703841387856e-05,
+      "loss": 10.1515,
+      "step": 400
+    },
+    {
+      "epoch": 1.5189990732159406,
+      "grad_norm": 44.03816223144531,
+      "learning_rate": 2.8252788104089218e-05,
+      "loss": 10.0098,
+      "step": 410
+    },
+    {
+      "epoch": 1.556070435588508,
+      "grad_norm": 42.871856689453125,
+      "learning_rate": 2.8128872366790583e-05,
+      "loss": 9.5566,
+      "step": 420
+    },
+    {
+      "epoch": 1.5931417979610751,
+      "grad_norm": 44.18041229248047,
+      "learning_rate": 2.8004956629491945e-05,
+      "loss": 10.1925,
+      "step": 430
+    },
+    {
+      "epoch": 1.6302131603336423,
+      "grad_norm": 30.012725830078125,
+      "learning_rate": 2.788104089219331e-05,
+      "loss": 9.7408,
+      "step": 440
+    },
+    {
+      "epoch": 1.6672845227062094,
+      "grad_norm": 38.104827880859375,
+      "learning_rate": 2.7757125154894673e-05,
+      "loss": 9.6873,
+      "step": 450
+    },
+    {
+      "epoch": 1.6672845227062094,
+      "eval_loss": 2.5061004161834717,
+      "eval_runtime": 34.2772,
+      "eval_samples_per_second": 47.203,
+      "eval_steps_per_second": 6.768,
+      "step": 450
+    },
+    {
+      "epoch": 1.7043558850787766,
+      "grad_norm": 42.93535232543945,
+      "learning_rate": 2.7633209417596035e-05,
+      "loss": 9.1932,
+      "step": 460
+    },
+    {
+      "epoch": 1.7414272474513437,
+      "grad_norm": 63.935279846191406,
+      "learning_rate": 2.75092936802974e-05,
+      "loss": 9.9204,
+      "step": 470
+    },
+    {
+      "epoch": 1.778498609823911,
+      "grad_norm": 30.906002044677734,
+      "learning_rate": 2.7385377942998762e-05,
+      "loss": 9.5151,
+      "step": 480
+    },
+    {
+      "epoch": 1.8155699721964782,
+      "grad_norm": 48.05679702758789,
+      "learning_rate": 2.7261462205700128e-05,
+      "loss": 9.8418,
+      "step": 490
+    },
+    {
+      "epoch": 1.8526413345690456,
+      "grad_norm": 56.36283874511719,
+      "learning_rate": 2.7137546468401486e-05,
+      "loss": 9.6943,
+      "step": 500
+    },
+    {
+      "epoch": 1.8897126969416127,
+      "grad_norm": 47.22933578491211,
+      "learning_rate": 2.7013630731102848e-05,
+      "loss": 9.6948,
+      "step": 510
+    },
+    {
+      "epoch": 1.9267840593141798,
+      "grad_norm": 36.110008239746094,
+      "learning_rate": 2.6889714993804214e-05,
+      "loss": 9.2274,
+      "step": 520
+    },
+    {
+      "epoch": 1.963855421686747,
+      "grad_norm": 37.13912582397461,
+      "learning_rate": 2.6765799256505576e-05,
+      "loss": 10.138,
+      "step": 530
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 51.37559509277344,
+      "learning_rate": 2.664188351920694e-05,
+      "loss": 8.7934,
+      "step": 540
+    },
+    {
+      "epoch": 2.037071362372567,
+      "grad_norm": 42.32170104980469,
+      "learning_rate": 2.6517967781908303e-05,
+      "loss": 8.8304,
+      "step": 550
+    },
+    {
+      "epoch": 2.0741427247451343,
+      "grad_norm": 42.406219482421875,
+      "learning_rate": 2.6394052044609665e-05,
+      "loss": 8.9593,
+      "step": 560
+    },
+    {
+      "epoch": 2.1112140871177014,
+      "grad_norm": 52.097023010253906,
+      "learning_rate": 2.627013630731103e-05,
+      "loss": 9.0051,
+      "step": 570
+    },
+    {
+      "epoch": 2.1482854494902686,
+      "grad_norm": 83.86861419677734,
+      "learning_rate": 2.6146220570012392e-05,
+      "loss": 9.2829,
+      "step": 580
+    },
+    {
+      "epoch": 2.185356811862836,
+      "grad_norm": 38.229949951171875,
+      "learning_rate": 2.6022304832713758e-05,
+      "loss": 9.785,
+      "step": 590
+    },
+    {
+      "epoch": 2.2224281742354033,
+      "grad_norm": 50.322513580322266,
+      "learning_rate": 2.5898389095415116e-05,
+      "loss": 9.6401,
+      "step": 600
+    },
+    {
+      "epoch": 2.2224281742354033,
+      "eval_loss": 2.448084592819214,
+      "eval_runtime": 34.2525,
+      "eval_samples_per_second": 47.237,
+      "eval_steps_per_second": 6.773,
+      "step": 600
+    },
+    {
+      "epoch": 2.266913809082484,
+      "grad_norm": 39.366676330566406,
+      "learning_rate": 2.5774473358116482e-05,
+      "loss": 8.7059,
+      "step": 610
+    },
+    {
+      "epoch": 2.303985171455051,
+      "grad_norm": 41.00213623046875,
+      "learning_rate": 2.5650557620817844e-05,
+      "loss": 9.1285,
+      "step": 620
+    },
+    {
+      "epoch": 2.341056533827618,
+      "grad_norm": 63.442169189453125,
+      "learning_rate": 2.5526641883519206e-05,
+      "loss": 9.3277,
+      "step": 630
+    },
+    {
+      "epoch": 2.3781278962001853,
+      "grad_norm": 51.54194641113281,
+      "learning_rate": 2.540272614622057e-05,
+      "loss": 9.1577,
+      "step": 640
+    },
+    {
+      "epoch": 2.4151992585727524,
+      "grad_norm": 57.583885192871094,
+      "learning_rate": 2.5278810408921933e-05,
+      "loss": 9.6032,
+      "step": 650
+    },
+    {
+      "epoch": 2.4522706209453196,
+      "grad_norm": 60.13545227050781,
+      "learning_rate": 2.51548946716233e-05,
+      "loss": 8.5451,
+      "step": 660
+    },
+    {
+      "epoch": 2.489341983317887,
+      "grad_norm": 139.85794067382812,
+      "learning_rate": 2.503097893432466e-05,
+      "loss": 8.6601,
+      "step": 670
+    },
+    {
+      "epoch": 2.5264133456904543,
+      "grad_norm": 160.73171997070312,
+      "learning_rate": 2.4907063197026023e-05,
+      "loss": 9.522,
+      "step": 680
+    },
+    {
+      "epoch": 2.5634847080630214,
+      "grad_norm": 190.7194366455078,
+      "learning_rate": 2.4783147459727385e-05,
+      "loss": 10.0619,
+      "step": 690
+    },
+    {
+      "epoch": 2.6005560704355886,
+      "grad_norm": 172.5655517578125,
+      "learning_rate": 2.4659231722428747e-05,
+      "loss": 9.6444,
+      "step": 700
+    },
+    {
+      "epoch": 2.6376274328081557,
+      "grad_norm": 280.9183044433594,
+      "learning_rate": 2.4535315985130112e-05,
+      "loss": 10.7593,
+      "step": 710
+    },
+    {
+      "epoch": 2.674698795180723,
+      "grad_norm": 118.03450775146484,
+      "learning_rate": 2.4411400247831474e-05,
+      "loss": 10.4432,
+      "step": 720
+    },
+    {
+      "epoch": 2.71177015755329,
+      "grad_norm": 332.662353515625,
+      "learning_rate": 2.428748451053284e-05,
+      "loss": 9.6033,
+      "step": 730
+    },
+    {
+      "epoch": 2.748841519925857,
+      "grad_norm": 129.18788146972656,
+      "learning_rate": 2.41635687732342e-05,
+      "loss": 9.108,
+      "step": 740
+    },
+    {
+      "epoch": 2.7859128822984243,
+      "grad_norm": 350.5856628417969,
+      "learning_rate": 2.4039653035935564e-05,
+      "loss": 9.884,
+      "step": 750
+    },
+    {
+      "epoch": 2.7859128822984243,
+      "eval_loss": 2.599517583847046,
+      "eval_runtime": 34.0592,
+      "eval_samples_per_second": 47.506,
+      "eval_steps_per_second": 6.812,
+      "step": 750
+    },
+    {
+      "epoch": 2.822984244670992,
+      "grad_norm": 285.14862060546875,
+      "learning_rate": 2.391573729863693e-05,
+      "loss": 11.3952,
+      "step": 760
+    },
+    {
+      "epoch": 2.860055607043559,
+      "grad_norm": 185.5862579345703,
+      "learning_rate": 2.379182156133829e-05,
+      "loss": 10.6798,
+      "step": 770
+    },
+    {
+      "epoch": 2.897126969416126,
+      "grad_norm": 77.20765686035156,
+      "learning_rate": 2.3667905824039656e-05,
+      "loss": 9.9795,
+      "step": 780
+    },
+    {
+      "epoch": 2.9341983317886933,
+      "grad_norm": 88.75109100341797,
+      "learning_rate": 2.3543990086741015e-05,
+      "loss": 9.3694,
+      "step": 790
+    },
+    {
+      "epoch": 2.9712696941612604,
+      "grad_norm": 53.416690826416016,
+      "learning_rate": 2.3420074349442377e-05,
+      "loss": 8.4631,
+      "step": 800
+    },
+    {
+      "epoch": 3.0111214087117704,
+      "grad_norm": 72.12966918945312,
+      "learning_rate": 2.3296158612143742e-05,
+      "loss": 9.3903,
+      "step": 810
+    },
+    {
+      "epoch": 3.0481927710843375,
+      "grad_norm": 159.3909912109375,
+      "learning_rate": 2.3172242874845104e-05,
+      "loss": 8.9608,
+      "step": 820
+    },
+    {
+      "epoch": 3.0852641334569046,
+      "grad_norm": 161.03713989257812,
+      "learning_rate": 2.304832713754647e-05,
+      "loss": 9.623,
+      "step": 830
+    },
+    {
+      "epoch": 3.122335495829472,
+      "grad_norm": 136.50045776367188,
+      "learning_rate": 2.2924411400247832e-05,
+      "loss": 8.5958,
+      "step": 840
+    },
+    {
+      "epoch": 3.159406858202039,
+      "grad_norm": 60.785926818847656,
+      "learning_rate": 2.2800495662949197e-05,
+      "loss": 8.6278,
+      "step": 850
+    },
+    {
+      "epoch": 3.196478220574606,
+      "grad_norm": 115.2509536743164,
+      "learning_rate": 2.267657992565056e-05,
+      "loss": 8.661,
+      "step": 860
+    },
+    {
+      "epoch": 3.233549582947173,
+      "grad_norm": 144.38912963867188,
+      "learning_rate": 2.255266418835192e-05,
+      "loss": 9.5836,
+      "step": 870
+    },
+    {
+      "epoch": 3.2706209453197403,
+      "grad_norm": 239.74520874023438,
+      "learning_rate": 2.2428748451053287e-05,
+      "loss": 8.6221,
+      "step": 880
+    },
+    {
+      "epoch": 3.3076923076923075,
+      "grad_norm": 215.12789916992188,
+      "learning_rate": 2.2304832713754645e-05,
+      "loss": 9.1995,
+      "step": 890
+    },
+    {
+      "epoch": 3.344763670064875,
+      "grad_norm": 113.77183532714844,
+      "learning_rate": 2.218091697645601e-05,
+      "loss": 8.6909,
+      "step": 900
+    },
+    {
+      "epoch": 3.344763670064875,
+      "eval_loss": 2.4246325492858887,
+      "eval_runtime": 34.1351,
+      "eval_samples_per_second": 47.4,
+      "eval_steps_per_second": 6.797,
+      "step": 900
+    },
+    {
+      "epoch": 3.381835032437442,
+      "grad_norm": 175.02731323242188,
+      "learning_rate": 2.2057001239157373e-05,
+      "loss": 8.7632,
+      "step": 910
+    },
+    {
+      "epoch": 3.4189063948100094,
+      "grad_norm": 142.76580810546875,
+      "learning_rate": 2.1933085501858735e-05,
+      "loss": 8.5604,
+      "step": 920
+    },
+    {
+      "epoch": 3.4559777571825765,
+      "grad_norm": 163.0391387939453,
+      "learning_rate": 2.18091697645601e-05,
+      "loss": 9.3871,
+      "step": 930
+    },
+    {
+      "epoch": 3.4930491195551436,
+      "grad_norm": 386.4294738769531,
+      "learning_rate": 2.1685254027261462e-05,
+      "loss": 9.6445,
+      "step": 940
+    },
+    {
+      "epoch": 3.5301204819277108,
+      "grad_norm": 86.92581939697266,
+      "learning_rate": 2.1561338289962827e-05,
+      "loss": 9.635,
+      "step": 950
+    },
+    {
+      "epoch": 3.567191844300278,
+      "grad_norm": 80.94845581054688,
+      "learning_rate": 2.143742255266419e-05,
+      "loss": 8.8689,
+      "step": 960
+    },
+    {
+      "epoch": 3.6042632066728455,
+      "grad_norm": 69.99708557128906,
+      "learning_rate": 2.1313506815365555e-05,
+      "loss": 9.1411,
+      "step": 970
+    },
+    {
+      "epoch": 3.641334569045412,
+      "grad_norm": 80.53229522705078,
+      "learning_rate": 2.1189591078066917e-05,
+      "loss": 8.7552,
+      "step": 980
+    },
+    {
+      "epoch": 3.67840593141798,
+      "grad_norm": 53.3475341796875,
+      "learning_rate": 2.1065675340768275e-05,
+      "loss": 8.5697,
+      "step": 990
+    },
+    {
+      "epoch": 3.715477293790547,
+      "grad_norm": 54.19875717163086,
+      "learning_rate": 2.094175960346964e-05,
+      "loss": 8.9008,
+      "step": 1000
+    },
+    {
+      "epoch": 3.752548656163114,
+      "grad_norm": 52.96628952026367,
+      "learning_rate": 2.0817843866171003e-05,
+      "loss": 8.9415,
+      "step": 1010
+    },
+    {
+      "epoch": 3.789620018535681,
+      "grad_norm": 64.08312225341797,
+      "learning_rate": 2.0693928128872368e-05,
+      "loss": 8.1303,
+      "step": 1020
+    },
+    {
+      "epoch": 3.8266913809082483,
+      "grad_norm": 68.22163391113281,
+      "learning_rate": 2.057001239157373e-05,
+      "loss": 8.241,
+      "step": 1030
+    },
+    {
+      "epoch": 3.8637627432808155,
+      "grad_norm": 66.70902252197266,
+      "learning_rate": 2.0446096654275092e-05,
+      "loss": 8.6969,
+      "step": 1040
+    },
+    {
+      "epoch": 3.9008341056533826,
+      "grad_norm": 49.94658279418945,
+      "learning_rate": 2.0322180916976458e-05,
+      "loss": 9.8392,
+      "step": 1050
+    },
+    {
+      "epoch": 3.9008341056533826,
+      "eval_loss": 2.533297300338745,
+      "eval_runtime": 34.1106,
+      "eval_samples_per_second": 47.434,
+      "eval_steps_per_second": 6.801,
+      "step": 1050
+    },
+    {
+      "epoch": 3.93790546802595,
+      "grad_norm": 73.9527816772461,
+      "learning_rate": 2.6765799256505576e-05,
+      "loss": 8.5934,
+      "step": 1060
+    },
+    {
+      "epoch": 3.974976830398517,
+      "grad_norm": 76.90135955810547,
+      "learning_rate": 2.6703841387856257e-05,
+      "loss": 8.006,
+      "step": 1070
+    },
+    {
+      "epoch": 4.014828544949027,
+      "grad_norm": 85.86236572265625,
+      "learning_rate": 2.664188351920694e-05,
+      "loss": 9.0081,
+      "step": 1080
+    },
+    {
+      "epoch": 4.051899907321594,
+      "grad_norm": 106.57842254638672,
+      "learning_rate": 2.6579925650557622e-05,
+      "loss": 8.6706,
+      "step": 1090
+    },
+    {
+      "epoch": 4.088971269694161,
+      "grad_norm": 68.10344696044922,
+      "learning_rate": 2.6517967781908303e-05,
+      "loss": 9.6146,
+      "step": 1100
+    },
+    {
+      "epoch": 4.126042632066729,
+      "grad_norm": 67.02091217041016,
+      "learning_rate": 2.6456009913258984e-05,
+      "loss": 9.225,
+      "step": 1110
+    },
+    {
+      "epoch": 4.163113994439295,
+      "grad_norm": 67.66644287109375,
+      "learning_rate": 2.6394052044609665e-05,
+      "loss": 8.7522,
+      "step": 1120
+    },
+    {
+      "epoch": 4.200185356811863,
+      "grad_norm": 59.26814651489258,
+      "learning_rate": 2.633209417596035e-05,
+      "loss": 9.0221,
+      "step": 1130
+    },
+    {
+      "epoch": 4.23725671918443,
+      "grad_norm": 88.07310485839844,
+      "learning_rate": 2.627013630731103e-05,
+      "loss": 9.6458,
+      "step": 1140
+    },
+    {
+      "epoch": 4.274328081556997,
+      "grad_norm": 69.33895874023438,
+      "learning_rate": 2.620817843866171e-05,
+      "loss": 8.7692,
+      "step": 1150
+    },
+    {
+      "epoch": 4.311399443929565,
+      "grad_norm": 43.823951721191406,
+      "learning_rate": 2.6146220570012392e-05,
+      "loss": 9.2874,
+      "step": 1160
+    },
+    {
+      "epoch": 4.348470806302132,
+      "grad_norm": 63.590980529785156,
+      "learning_rate": 2.6084262701363077e-05,
+      "loss": 8.9276,
+      "step": 1170
+    },
+    {
+      "epoch": 4.385542168674699,
+      "grad_norm": 43.4519157409668,
+      "learning_rate": 2.6022304832713758e-05,
+      "loss": 8.7444,
+      "step": 1180
+    },
+    {
+      "epoch": 4.422613531047266,
+      "grad_norm": 72.1529312133789,
+      "learning_rate": 2.5960346964064435e-05,
+      "loss": 8.7265,
+      "step": 1190
+    },
+    {
+      "epoch": 4.459684893419833,
+      "grad_norm": 101.67008972167969,
+      "learning_rate": 2.5898389095415116e-05,
+      "loss": 8.7642,
+      "step": 1200
+    },
+    {
+      "epoch": 4.459684893419833,
+      "eval_loss": 2.6471314430236816,
+      "eval_runtime": 34.2723,
+      "eval_samples_per_second": 47.21,
+      "eval_steps_per_second": 6.769,
+      "step": 1200
+    },
+    {
+      "epoch": 4.4967562557924,
+      "grad_norm": 66.03606414794922,
+      "learning_rate": 2.5836431226765797e-05,
+      "loss": 8.8917,
+      "step": 1210
+    },
+    {
+      "epoch": 4.533827618164968,
+      "grad_norm": 60.01662826538086,
+      "learning_rate": 2.5774473358116482e-05,
+      "loss": 9.2155,
+      "step": 1220
+    },
+    {
+      "epoch": 4.570898980537534,
+      "grad_norm": 83.86510467529297,
+      "learning_rate": 2.5712515489467163e-05,
+      "loss": 8.6101,
+      "step": 1230
+    },
+    {
+      "epoch": 4.607970342910102,
+      "grad_norm": 64.35486602783203,
+      "learning_rate": 2.5650557620817844e-05,
+      "loss": 8.9904,
+      "step": 1240
+    },
+    {
+      "epoch": 4.645041705282669,
+      "grad_norm": 60.44017791748047,
+      "learning_rate": 2.5588599752168525e-05,
+      "loss": 9.3272,
+      "step": 1250
+    },
+    {
+      "epoch": 4.682113067655236,
+      "grad_norm": 56.501102447509766,
+      "learning_rate": 2.5526641883519206e-05,
+      "loss": 7.9367,
+      "step": 1260
+    },
+    {
+      "epoch": 4.719184430027804,
+      "grad_norm": 65.01017761230469,
+      "learning_rate": 2.546468401486989e-05,
+      "loss": 8.5891,
+      "step": 1270
+    },
+    {
+      "epoch": 4.7562557924003706,
+      "grad_norm": 63.42623519897461,
+      "learning_rate": 2.540272614622057e-05,
+      "loss": 8.6286,
+      "step": 1280
+    },
+    {
+      "epoch": 4.793327154772938,
+      "grad_norm": 58.96747589111328,
+      "learning_rate": 2.5340768277571252e-05,
+      "loss": 7.9982,
+      "step": 1290
+    },
+    {
+      "epoch": 4.830398517145505,
+      "grad_norm": 96.77368927001953,
+      "learning_rate": 2.5278810408921933e-05,
+      "loss": 7.5587,
+      "step": 1300
+    },
+    {
+      "epoch": 4.867469879518072,
+      "grad_norm": 85.92269897460938,
+      "learning_rate": 2.5216852540272614e-05,
+      "loss": 7.9405,
+      "step": 1310
+    },
+    {
+      "epoch": 4.904541241890639,
+      "grad_norm": 86.37085723876953,
+      "learning_rate": 2.51548946716233e-05,
+      "loss": 9.7092,
+      "step": 1320
+    },
+    {
+      "epoch": 4.941612604263207,
+      "grad_norm": 65.88274383544922,
+      "learning_rate": 2.509293680297398e-05,
+      "loss": 8.1475,
+      "step": 1330
+    },
+    {
+      "epoch": 4.978683966635774,
+      "grad_norm": 53.252742767333984,
+      "learning_rate": 2.503097893432466e-05,
+      "loss": 9.3603,
+      "step": 1340
+    },
+    {
+      "epoch": 5.014828544949027,
+      "grad_norm": 182.35781860351562,
+      "learning_rate": 2.4969021065675342e-05,
+      "loss": 7.6621,
+      "step": 1350
+    },
+    {
+      "epoch": 5.014828544949027,
+      "eval_loss": 2.8308892250061035,
+      "eval_runtime": 34.1063,
+      "eval_samples_per_second": 47.44,
+      "eval_steps_per_second": 6.802,
+      "step": 1350
+    },
+    {
+      "epoch": 5.051899907321594,
+      "grad_norm": 324.6659240722656,
+      "learning_rate": 2.4907063197026023e-05,
+      "loss": 9.2301,
+      "step": 1360
+    },
+    {
+      "epoch": 5.088971269694161,
+      "grad_norm": 4839.4453125,
+      "learning_rate": 2.4845105328376707e-05,
+      "loss": 9.7789,
+      "step": 1370
+    },
+    {
+      "epoch": 5.126042632066729,
+      "grad_norm": 408588.40625,
+      "learning_rate": 2.4783147459727385e-05,
+      "loss": 9.5359,
+      "step": 1380
+    },
+    {
+      "epoch": 5.163113994439295,
+      "grad_norm": 932.5144653320312,
+      "learning_rate": 2.4721189591078066e-05,
+      "loss": 10.8065,
+      "step": 1390
+    },
+    {
+      "epoch": 5.200185356811863,
+      "grad_norm": 148.0634765625,
+      "learning_rate": 2.4659231722428747e-05,
+      "loss": 10.0149,
+      "step": 1400
+    },
+    {
+      "epoch": 5.23725671918443,
+      "grad_norm": 1214.7279052734375,
+      "learning_rate": 2.459727385377943e-05,
+      "loss": 10.2582,
+      "step": 1410
+    },
+    {
+      "epoch": 5.274328081556997,
+      "grad_norm": 188.14292907714844,
+      "learning_rate": 2.4535315985130112e-05,
+      "loss": 10.16,
+      "step": 1420
+    },
+    {
+      "epoch": 5.311399443929565,
+      "grad_norm": 388.7134094238281,
+      "learning_rate": 2.4473358116480793e-05,
+      "loss": 10.0763,
+      "step": 1430
+    },
+    {
+      "epoch": 5.348470806302132,
+      "grad_norm": 270.61279296875,
+      "learning_rate": 2.4411400247831474e-05,
+      "loss": 9.5737,
+      "step": 1440
+    },
+    {
+      "epoch": 5.385542168674699,
+      "grad_norm": 1637.854736328125,
+      "learning_rate": 2.4349442379182155e-05,
+      "loss": 10.4816,
+      "step": 1450
+    },
+    {
+      "epoch": 5.422613531047266,
+      "grad_norm": 1118.7012939453125,
+      "learning_rate": 2.428748451053284e-05,
+      "loss": 8.6687,
+      "step": 1460
+    },
+    {
+      "epoch": 5.459684893419833,
+      "grad_norm": 788.9707641601562,
+      "learning_rate": 2.422552664188352e-05,
+      "loss": 8.4066,
+      "step": 1470
+    },
+    {
+      "epoch": 5.4967562557924,
+      "grad_norm": 185.22950744628906,
+      "learning_rate": 2.41635687732342e-05,
+      "loss": 9.386,
+      "step": 1480
+    },
+    {
+      "epoch": 5.533827618164968,
+      "grad_norm": 257.726806640625,
+      "learning_rate": 2.4101610904584883e-05,
+      "loss": 8.3911,
+      "step": 1490
+    },
+    {
+      "epoch": 5.570898980537534,
+      "grad_norm": 867.30908203125,
+      "learning_rate": 2.4039653035935564e-05,
+      "loss": 8.8025,
+      "step": 1500
+    },
+    {
+      "epoch": 5.570898980537534,
+      "eval_loss": 2.5407650470733643,
+      "eval_runtime": 34.0934,
+      "eval_samples_per_second": 47.458,
+      "eval_steps_per_second": 6.805,
+      "step": 1500
+    },
+    {
+      "epoch": 5.607970342910102,
+      "grad_norm": 68.35711669921875,
+      "learning_rate": 2.3977695167286248e-05,
+      "loss": 8.7939,
+      "step": 1510
+    },
+    {
+      "epoch": 5.645041705282669,
+      "grad_norm": 1419.1650390625,
+      "learning_rate": 2.391573729863693e-05,
+      "loss": 9.0903,
+      "step": 1520
+    },
+    {
+      "epoch": 5.682113067655236,
+      "grad_norm": 60.88732147216797,
+      "learning_rate": 2.385377942998761e-05,
+      "loss": 8.9878,
+      "step": 1530
+    },
+    {
+      "epoch": 5.719184430027804,
+      "grad_norm": 61.50148010253906,
+      "learning_rate": 2.379182156133829e-05,
+      "loss": 8.8642,
+      "step": 1540
+    },
+    {
+      "epoch": 5.7562557924003706,
+      "grad_norm": 73.9307861328125,
+      "learning_rate": 2.3729863692688972e-05,
+      "loss": 8.8625,
+      "step": 1550
+    },
+    {
+      "epoch": 5.793327154772938,
+      "grad_norm": 82.28329467773438,
+      "learning_rate": 2.3667905824039656e-05,
+      "loss": 8.4105,
+      "step": 1560
+    },
+    {
+      "epoch": 5.830398517145505,
+      "grad_norm": 83.54141235351562,
+      "learning_rate": 2.3605947955390337e-05,
+      "loss": 9.0163,
+      "step": 1570
+    },
+    {
+      "epoch": 5.867469879518072,
+      "grad_norm": 66.59397888183594,
+      "learning_rate": 2.3543990086741015e-05,
+      "loss": 8.8947,
+      "step": 1580
+    },
+    {
+      "epoch": 5.904541241890639,
+      "grad_norm": 55.8841667175293,
+      "learning_rate": 2.3482032218091696e-05,
+      "loss": 8.5647,
+      "step": 1590
+    },
+    {
+      "epoch": 5.941612604263207,
+      "grad_norm": 74.56892395019531,
+      "learning_rate": 2.3420074349442377e-05,
+      "loss": 7.7047,
+      "step": 1600
+    },
+    {
+      "epoch": 5.978683966635774,
+      "grad_norm": 106.54405212402344,
+      "learning_rate": 2.335811648079306e-05,
+      "loss": 8.1484,
+      "step": 1610
+    },
+    {
+      "epoch": 6.014828544949027,
+      "grad_norm": 107.8216781616211,
+      "learning_rate": 2.3296158612143742e-05,
+      "loss": 8.4079,
+      "step": 1620
+    },
+    {
+      "epoch": 6.051899907321594,
+      "grad_norm": 100.98133087158203,
+      "learning_rate": 2.3234200743494423e-05,
+      "loss": 8.5027,
+      "step": 1630
+    },
+    {
+      "epoch": 6.088971269694161,
+      "grad_norm": 67.31327819824219,
+      "learning_rate": 2.3172242874845104e-05,
+      "loss": 8.1805,
+      "step": 1640
+    },
+    {
+      "epoch": 6.126042632066729,
+      "grad_norm": 61.10900115966797,
+      "learning_rate": 2.311028500619579e-05,
+      "loss": 8.4519,
+      "step": 1650
+    },
+    {
+      "epoch": 6.126042632066729,
+      "eval_loss": 2.590090036392212,
+      "eval_runtime": 34.1392,
+      "eval_samples_per_second": 47.394,
+      "eval_steps_per_second": 6.796,
+      "step": 1650
+    },
+    {
+      "epoch": 6.163113994439295,
+      "grad_norm": 60.91183090209961,
+      "learning_rate": 2.304832713754647e-05,
+      "loss": 9.062,
+      "step": 1660
+    },
+    {
+      "epoch": 6.200185356811863,
+      "grad_norm": 76.2873306274414,
+      "learning_rate": 2.298636926889715e-05,
+      "loss": 8.8499,
+      "step": 1670
+    },
+    {
+      "epoch": 6.23725671918443,
+      "grad_norm": 74.2361068725586,
+      "learning_rate": 2.2924411400247832e-05,
+      "loss": 8.6576,
+      "step": 1680
+    },
+    {
+      "epoch": 6.274328081556997,
+      "grad_norm": 84.99951934814453,
+      "learning_rate": 2.2862453531598513e-05,
+      "loss": 8.4652,
+      "step": 1690
+    },
+    {
+      "epoch": 6.311399443929565,
+      "grad_norm": 86.40947723388672,
+      "learning_rate": 2.2800495662949197e-05,
+      "loss": 9.0782,
+      "step": 1700
+    },
+    {
+      "epoch": 6.348470806302132,
+      "grad_norm": 75.45568084716797,
+      "learning_rate": 2.2738537794299878e-05,
+      "loss": 8.1532,
+      "step": 1710
+    },
+    {
+      "epoch": 6.385542168674699,
+      "grad_norm": 86.65908813476562,
+      "learning_rate": 2.267657992565056e-05,
+      "loss": 8.5185,
+      "step": 1720
+    },
+    {
+      "epoch": 6.422613531047266,
+      "grad_norm": 62.620758056640625,
+      "learning_rate": 2.261462205700124e-05,
+      "loss": 9.5908,
+      "step": 1730
+    },
+    {
+      "epoch": 6.459684893419833,
+      "grad_norm": 73.63095092773438,
+      "learning_rate": 2.255266418835192e-05,
+      "loss": 8.4188,
+      "step": 1740
+    },
+    {
+      "epoch": 6.4967562557924,
+      "grad_norm": 55.175045013427734,
+      "learning_rate": 2.2490706319702606e-05,
+      "loss": 8.1885,
+      "step": 1750
+    },
+    {
+      "epoch": 6.533827618164968,
+      "grad_norm": 47.647621154785156,
+      "learning_rate": 2.2428748451053287e-05,
+      "loss": 8.7666,
+      "step": 1760
+    },
+    {
+      "epoch": 6.570898980537534,
+      "grad_norm": 191.0419158935547,
+      "learning_rate": 2.2366790582403964e-05,
+      "loss": 8.6105,
+      "step": 1770
+    },
+    {
+      "epoch": 6.607970342910102,
+      "grad_norm": 57.81939697265625,
+      "learning_rate": 2.2304832713754645e-05,
+      "loss": 8.664,
+      "step": 1780
+    },
+    {
+      "epoch": 6.645041705282669,
+      "grad_norm": 85.04927825927734,
+      "learning_rate": 2.2242874845105326e-05,
+      "loss": 8.5294,
+      "step": 1790
+    },
+    {
+      "epoch": 6.682113067655236,
+      "grad_norm": 55.604122161865234,
+      "learning_rate": 2.218091697645601e-05,
+      "loss": 9.1857,
+      "step": 1800
+    },
+    {
+      "epoch": 6.682113067655236,
+      "eval_loss": 2.497358560562134,
+      "eval_runtime": 34.0441,
+      "eval_samples_per_second": 47.527,
+      "eval_steps_per_second": 6.815,
+      "step": 1800
+    },
+    {
+      "epoch": 6.719184430027804,
+      "grad_norm": 75.21812438964844,
+      "learning_rate": 2.211895910780669e-05,
+      "loss": 8.7053,
+      "step": 1810
+    },
+    {
+      "epoch": 6.7562557924003706,
+      "grad_norm": 85.76676940917969,
+      "learning_rate": 2.2057001239157373e-05,
+      "loss": 8.1428,
+      "step": 1820
+    },
+    {
+      "epoch": 6.793327154772938,
+      "grad_norm": 69.85575866699219,
+      "learning_rate": 2.1995043370508054e-05,
+      "loss": 8.4988,
+      "step": 1830
+    },
+    {
+      "epoch": 6.830398517145505,
+      "grad_norm": 66.85325622558594,
+      "learning_rate": 2.1933085501858735e-05,
+      "loss": 8.4147,
+      "step": 1840
+    },
+    {
+      "epoch": 6.867469879518072,
+      "grad_norm": 60.645294189453125,
+      "learning_rate": 2.187112763320942e-05,
+      "loss": 9.069,
+      "step": 1850
+    },
+    {
+      "epoch": 6.904541241890639,
+      "grad_norm": 77.59921264648438,
+      "learning_rate": 2.18091697645601e-05,
+      "loss": 8.4405,
+      "step": 1860
+    },
+    {
+      "epoch": 6.941612604263207,
+      "grad_norm": 56.27996826171875,
+      "learning_rate": 2.174721189591078e-05,
+      "loss": 9.2157,
+      "step": 1870
+    },
+    {
+      "epoch": 6.978683966635774,
+      "grad_norm": 64.18400573730469,
+      "learning_rate": 2.1685254027261462e-05,
+      "loss": 9.5492,
+      "step": 1880
+    },
+    {
+      "epoch": 7.014828544949027,
+      "grad_norm": 76.78484344482422,
+      "learning_rate": 2.1623296158612143e-05,
+      "loss": 8.1325,
+      "step": 1890
+    },
+    {
+      "epoch": 7.051899907321594,
+      "grad_norm": 77.69871520996094,
+      "learning_rate": 2.1561338289962827e-05,
+      "loss": 8.324,
+      "step": 1900
+    },
+    {
+      "epoch": 7.088971269694161,
+      "grad_norm": 102.43340301513672,
+      "learning_rate": 2.149938042131351e-05,
+      "loss": 7.7097,
+      "step": 1910
+    },
+    {
+      "epoch": 7.126042632066729,
+      "grad_norm": 114.0189208984375,
+      "learning_rate": 2.143742255266419e-05,
+      "loss": 8.0982,
+      "step": 1920
+    },
+    {
+      "epoch": 7.163113994439295,
+      "grad_norm": 66.60838317871094,
+      "learning_rate": 2.137546468401487e-05,
+      "loss": 7.7669,
+      "step": 1930
+    },
+    {
+      "epoch": 7.200185356811863,
+      "grad_norm": 252.72503662109375,
+      "learning_rate": 2.1313506815365555e-05,
+      "loss": 7.809,
+      "step": 1940
+    },
+    {
+      "epoch": 7.23725671918443,
+      "grad_norm": 91.0379409790039,
+      "learning_rate": 2.1251548946716236e-05,
+      "loss": 7.9729,
+      "step": 1950
+    },
+    {
+      "epoch": 7.23725671918443,
+      "eval_loss": 2.610764741897583,
+      "eval_runtime": 34.0774,
+      "eval_samples_per_second": 47.48,
+      "eval_steps_per_second": 6.808,
+      "step": 1950
+    },
+    {
+      "epoch": 7.274328081556997,
+      "grad_norm": 96.09555053710938,
+      "learning_rate": 2.1189591078066917e-05,
+      "loss": 8.2125,
+      "step": 1960
+    },
+    {
+      "epoch": 7.311399443929565,
+      "grad_norm": 68.51132202148438,
+      "learning_rate": 2.1127633209417594e-05,
+      "loss": 7.7403,
+      "step": 1970
+    },
+    {
+      "epoch": 7.348470806302132,
+      "grad_norm": 94.45308685302734,
+      "learning_rate": 2.1065675340768275e-05,
+      "loss": 7.5494,
+      "step": 1980
+    },
+    {
+      "epoch": 7.385542168674699,
+      "grad_norm": 56.785587310791016,
+      "learning_rate": 2.100371747211896e-05,
+      "loss": 8.2821,
+      "step": 1990
+    },
+    {
+      "epoch": 7.422613531047266,
+      "grad_norm": 91.59173583984375,
+      "learning_rate": 2.094175960346964e-05,
+      "loss": 8.1644,
+      "step": 2000
+    },
+    {
+      "epoch": 7.459684893419833,
+      "grad_norm": 78.57572174072266,
+      "learning_rate": 2.0879801734820322e-05,
+      "loss": 8.1664,
+      "step": 2010
+    },
+    {
+      "epoch": 7.4967562557924,
+      "grad_norm": 71.83062744140625,
+      "learning_rate": 2.0817843866171003e-05,
+      "loss": 8.5876,
+      "step": 2020
+    },
+    {
+      "epoch": 7.533827618164968,
+      "grad_norm": 74.75129699707031,
+      "learning_rate": 2.0755885997521684e-05,
+      "loss": 8.2753,
+      "step": 2030
+    },
+    {
+      "epoch": 7.570898980537534,
+      "grad_norm": 96.26950073242188,
+      "learning_rate": 2.0693928128872368e-05,
+      "loss": 9.2057,
+      "step": 2040
+    },
+    {
+      "epoch": 7.607970342910102,
+      "grad_norm": 96.87144470214844,
+      "learning_rate": 2.063197026022305e-05,
+      "loss": 8.0052,
+      "step": 2050
+    },
+    {
+      "epoch": 7.645041705282669,
+      "grad_norm": 83.44422912597656,
+      "learning_rate": 2.057001239157373e-05,
+      "loss": 8.4954,
+      "step": 2060
+    },
+    {
+      "epoch": 7.682113067655236,
+      "grad_norm": 86.1534194946289,
+      "learning_rate": 2.050805452292441e-05,
+      "loss": 8.0325,
+      "step": 2070
+    },
+    {
+      "epoch": 7.719184430027804,
+      "grad_norm": 89.11744689941406,
+      "learning_rate": 2.0446096654275092e-05,
+      "loss": 8.2934,
+      "step": 2080
+    },
+    {
+      "epoch": 7.7562557924003706,
+      "grad_norm": 60.81666946411133,
+      "learning_rate": 2.0384138785625777e-05,
+      "loss": 9.4019,
+      "step": 2090
+    },
+    {
+      "epoch": 7.793327154772938,
+      "grad_norm": 82.93228912353516,
+      "learning_rate": 2.0322180916976458e-05,
+      "loss": 8.874,
+      "step": 2100
+    },
+    {
+      "epoch": 7.793327154772938,
+      "eval_loss": 2.452894926071167,
+      "eval_runtime": 34.0684,
+      "eval_samples_per_second": 47.493,
+      "eval_steps_per_second": 6.81,
+      "step": 2100
+    },
+    {
+      "epoch": 7.830398517145505,
+      "grad_norm": 62.004817962646484,
+      "learning_rate": 2.026022304832714e-05,
+      "loss": 8.0985,
+      "step": 2110
+    },
+    {
+      "epoch": 7.867469879518072,
+      "grad_norm": 72.79752349853516,
+      "learning_rate": 2.019826517967782e-05,
+      "loss": 8.9063,
+      "step": 2120
+    },
+    {
+      "epoch": 7.904541241890639,
+      "grad_norm": 1507.2855224609375,
+      "learning_rate": 2.01363073110285e-05,
+      "loss": 8.6332,
+      "step": 2130
+    },
+    {
+      "epoch": 7.941612604263207,
+      "grad_norm": 134.11378479003906,
+      "learning_rate": 2.0074349442379185e-05,
+      "loss": 9.4106,
+      "step": 2140
+    },
+    {
+      "epoch": 7.978683966635774,
+      "grad_norm": 72.19046783447266,
+      "learning_rate": 2.0012391573729866e-05,
+      "loss": 8.2304,
+      "step": 2150
+    },
+    {
+      "epoch": 8.014828544949028,
+      "grad_norm": 57.130165100097656,
+      "learning_rate": 1.9950433705080544e-05,
+      "loss": 7.9675,
+      "step": 2160
+    },
+    {
+      "epoch": 8.051899907321594,
+      "grad_norm": 72.58036041259766,
+      "learning_rate": 1.9888475836431225e-05,
+      "loss": 7.602,
+      "step": 2170
+    },
+    {
+      "epoch": 8.088971269694161,
+      "grad_norm": 91.77513885498047,
+      "learning_rate": 1.982651796778191e-05,
+      "loss": 7.9151,
+      "step": 2180
+    },
+    {
+      "epoch": 8.126042632066728,
+      "grad_norm": 111.52696228027344,
+      "learning_rate": 1.976456009913259e-05,
+      "loss": 7.5653,
+      "step": 2190
+    },
+    {
+      "epoch": 8.163113994439296,
+      "grad_norm": 74.9671401977539,
+      "learning_rate": 1.970260223048327e-05,
+      "loss": 7.1567,
+      "step": 2200
+    },
+    {
+      "epoch": 8.200185356811863,
+      "grad_norm": 124.09498596191406,
+      "learning_rate": 1.9640644361833952e-05,
+      "loss": 8.1708,
+      "step": 2210
+    },
+    {
+      "epoch": 8.23725671918443,
+      "grad_norm": 95.21754455566406,
+      "learning_rate": 1.9578686493184633e-05,
+      "loss": 7.0013,
+      "step": 2220
+    },
+    {
+      "epoch": 8.274328081556996,
+      "grad_norm": 135.3839569091797,
+      "learning_rate": 1.9516728624535318e-05,
+      "loss": 7.5999,
+      "step": 2230
+    },
+    {
+      "epoch": 8.311399443929565,
+      "grad_norm": 89.70751190185547,
+      "learning_rate": 1.9454770755886e-05,
+      "loss": 7.2028,
+      "step": 2240
+    },
+    {
+      "epoch": 8.348470806302132,
+      "grad_norm": 70.08137512207031,
+      "learning_rate": 1.939281288723668e-05,
+      "loss": 8.3759,
+      "step": 2250
+    },
+    {
+      "epoch": 8.348470806302132,
+      "eval_loss": 2.746619939804077,
+      "eval_runtime": 34.0831,
+      "eval_samples_per_second": 47.472,
+      "eval_steps_per_second": 6.807,
+      "step": 2250
+    },
+    {
+      "epoch": 8.400370713623726,
+      "grad_norm": 69.07305145263672,
+      "learning_rate": 1.933085501858736e-05,
+      "loss": 8.9083,
+      "step": 2260
+    },
+    {
+      "epoch": 8.437442075996293,
+      "grad_norm": 66.43407440185547,
+      "learning_rate": 1.926889714993804e-05,
+      "loss": 6.9349,
+      "step": 2270
+    },
+    {
+      "epoch": 8.47451343836886,
+      "grad_norm": 167.85784912109375,
+      "learning_rate": 1.9206939281288726e-05,
+      "loss": 7.5041,
+      "step": 2280
+    },
+    {
+      "epoch": 8.511584800741428,
+      "grad_norm": 173.38304138183594,
+      "learning_rate": 1.9144981412639407e-05,
+      "loss": 7.3744,
+      "step": 2290
+    },
+    {
+      "epoch": 8.548656163113995,
+      "grad_norm": 80.71511840820312,
+      "learning_rate": 1.9083023543990088e-05,
+      "loss": 8.6541,
+      "step": 2300
+    },
+    {
+      "epoch": 8.585727525486561,
+      "grad_norm": 82.77088928222656,
+      "learning_rate": 1.902106567534077e-05,
+      "loss": 8.6305,
+      "step": 2310
+    },
+    {
+      "epoch": 8.62279888785913,
+      "grad_norm": 55.3135871887207,
+      "learning_rate": 1.895910780669145e-05,
+      "loss": 8.2577,
+      "step": 2320
+    },
+    {
+      "epoch": 8.659870250231696,
+      "grad_norm": 64.61204528808594,
+      "learning_rate": 1.8897149938042134e-05,
+      "loss": 7.6382,
+      "step": 2330
+    },
+    {
+      "epoch": 8.696941612604263,
+      "grad_norm": 77.9918212890625,
+      "learning_rate": 1.8835192069392815e-05,
+      "loss": 8.114,
+      "step": 2340
+    },
+    {
+      "epoch": 8.73401297497683,
+      "grad_norm": 50.139678955078125,
+      "learning_rate": 1.8773234200743496e-05,
+      "loss": 7.8875,
+      "step": 2350
+    },
+    {
+      "epoch": 8.771084337349398,
+      "grad_norm": 241.43588256835938,
+      "learning_rate": 1.8711276332094174e-05,
+      "loss": 7.0444,
+      "step": 2360
+    },
+    {
+      "epoch": 8.808155699721965,
+      "grad_norm": 133.25645446777344,
+      "learning_rate": 1.8649318463444855e-05,
+      "loss": 7.7393,
+      "step": 2370
+    },
+    {
+      "epoch": 8.845227062094532,
+      "grad_norm": 94.1192855834961,
+      "learning_rate": 1.858736059479554e-05,
+      "loss": 8.8284,
+      "step": 2380
+    },
+    {
+      "epoch": 8.882298424467098,
+      "grad_norm": 83.68805694580078,
+      "learning_rate": 1.852540272614622e-05,
+      "loss": 7.997,
+      "step": 2390
+    },
+    {
+      "epoch": 8.919369786839667,
+      "grad_norm": 67.01426696777344,
+      "learning_rate": 1.84634448574969e-05,
+      "loss": 7.786,
+      "step": 2400
+    },
+    {
+      "epoch": 8.919369786839667,
+      "eval_loss": 2.6791422367095947,
+      "eval_runtime": 34.2417,
+      "eval_samples_per_second": 47.252,
+      "eval_steps_per_second": 6.775,
+      "step": 2400
+    },
+    {
+      "epoch": 8.956441149212234,
+      "grad_norm": 72.36073303222656,
+      "learning_rate": 1.8401486988847582e-05,
+      "loss": 7.6257,
+      "step": 2410
+    },
+    {
+      "epoch": 8.9935125115848,
+      "grad_norm": 70.3509521484375,
+      "learning_rate": 1.8339529120198267e-05,
+      "loss": 7.099,
+      "step": 2420
+    },
+    {
+      "epoch": 9.03336422613531,
+      "grad_norm": 136.34727478027344,
+      "learning_rate": 1.8277571251548948e-05,
+      "loss": 8.041,
+      "step": 2430
+    },
+    {
+      "epoch": 9.070435588507877,
+      "grad_norm": 81.48332214355469,
+      "learning_rate": 1.821561338289963e-05,
+      "loss": 7.8606,
+      "step": 2440
+    },
+    {
+      "epoch": 9.107506950880445,
+      "grad_norm": 93.1724853515625,
+      "learning_rate": 1.815365551425031e-05,
+      "loss": 7.8551,
+      "step": 2450
+    },
+    {
+      "epoch": 9.144578313253012,
+      "grad_norm": 132.82778930664062,
+      "learning_rate": 1.809169764560099e-05,
+      "loss": 7.3977,
+      "step": 2460
+    },
+    {
+      "epoch": 9.181649675625579,
+      "grad_norm": 102.73971557617188,
+      "learning_rate": 1.8029739776951675e-05,
+      "loss": 7.8721,
+      "step": 2470
+    },
+    {
+      "epoch": 9.218721037998147,
+      "grad_norm": 106.7470932006836,
+      "learning_rate": 1.7967781908302356e-05,
+      "loss": 7.5839,
+      "step": 2480
+    },
+    {
+      "epoch": 9.255792400370714,
+      "grad_norm": 84.64981842041016,
+      "learning_rate": 1.7905824039653037e-05,
+      "loss": 7.1823,
+      "step": 2490
+    },
+    {
+      "epoch": 9.29286376274328,
+      "grad_norm": 85.59486389160156,
+      "learning_rate": 1.7843866171003718e-05,
+      "loss": 7.5513,
+      "step": 2500
+    },
+    {
+      "epoch": 9.329935125115847,
+      "grad_norm": 89.53803253173828,
+      "learning_rate": 1.77819083023544e-05,
+      "loss": 8.0879,
+      "step": 2510
+    },
+    {
+      "epoch": 9.367006487488416,
+      "grad_norm": 43.886898040771484,
+      "learning_rate": 1.7719950433705084e-05,
+      "loss": 7.5694,
+      "step": 2520
+    },
+    {
+      "epoch": 9.404077849860982,
+      "grad_norm": 73.4898910522461,
+      "learning_rate": 1.7657992565055765e-05,
+      "loss": 7.3436,
+      "step": 2530
+    },
+    {
+      "epoch": 9.44114921223355,
+      "grad_norm": 100.42314147949219,
+      "learning_rate": 1.7596034696406446e-05,
+      "loss": 6.9425,
+      "step": 2540
+    },
+    {
+      "epoch": 9.478220574606116,
+      "grad_norm": 121.53675079345703,
+      "learning_rate": 1.7534076827757123e-05,
+      "loss": 7.9461,
+      "step": 2550
+    },
+    {
+      "epoch": 9.478220574606116,
+      "eval_loss": 2.6608545780181885,
+      "eval_runtime": 34.2437,
+      "eval_samples_per_second": 47.25,
+      "eval_steps_per_second": 6.775,
+      "step": 2550
+    },
+    {
+      "epoch": 9.515291936978684,
+      "grad_norm": 83.28184509277344,
+      "learning_rate": 1.7472118959107804e-05,
+      "loss": 6.782,
+      "step": 2560
+    },
+    {
+      "epoch": 9.552363299351251,
+      "grad_norm": 81.46753692626953,
+      "learning_rate": 1.741016109045849e-05,
+      "loss": 7.3027,
+      "step": 2570
+    },
+    {
+      "epoch": 9.589434661723818,
+      "grad_norm": 77.35752868652344,
+      "learning_rate": 1.734820322180917e-05,
+      "loss": 7.3348,
+      "step": 2580
+    },
+    {
+      "epoch": 9.626506024096386,
+      "grad_norm": 77.17479705810547,
+      "learning_rate": 1.728624535315985e-05,
+      "loss": 7.7864,
+      "step": 2590
+    },
+    {
+      "epoch": 9.663577386468953,
+      "grad_norm": 103.42965698242188,
+      "learning_rate": 1.722428748451053e-05,
+      "loss": 6.3552,
+      "step": 2600
+    },
+    {
+      "epoch": 9.70064874884152,
+      "grad_norm": 103.3230972290039,
+      "learning_rate": 1.7162329615861213e-05,
+      "loss": 7.151,
+      "step": 2610
+    },
+    {
+      "epoch": 9.737720111214086,
+      "grad_norm": 91.23753356933594,
+      "learning_rate": 1.7100371747211897e-05,
+      "loss": 6.1664,
+      "step": 2620
+    },
+    {
+      "epoch": 9.774791473586655,
+      "grad_norm": 68.76666259765625,
+      "learning_rate": 1.7038413878562578e-05,
+      "loss": 6.0398,
+      "step": 2630
+    },
+    {
+      "epoch": 9.811862835959221,
+      "grad_norm": 112.56900787353516,
+      "learning_rate": 1.697645600991326e-05,
+      "loss": 7.0452,
+      "step": 2640
+    },
+    {
+      "epoch": 9.848934198331788,
+      "grad_norm": 142.0828399658203,
+      "learning_rate": 1.691449814126394e-05,
+      "loss": 7.2457,
+      "step": 2650
+    },
+    {
+      "epoch": 9.886005560704357,
+      "grad_norm": 149.853515625,
+      "learning_rate": 1.685254027261462e-05,
+      "loss": 6.7531,
+      "step": 2660
+    },
+    {
+      "epoch": 9.923076923076923,
+      "grad_norm": 107.76028442382812,
+      "learning_rate": 1.6790582403965305e-05,
+      "loss": 6.7149,
+      "step": 2670
+    },
+    {
+      "epoch": 9.96014828544949,
+      "grad_norm": 83.82595825195312,
+      "learning_rate": 1.6728624535315986e-05,
+      "loss": 6.4635,
+      "step": 2680
+    },
+    {
+      "epoch": 9.997219647822057,
+      "grad_norm": 106.68073272705078,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 6.2237,
+      "step": 2690
+    },
+    {
+      "epoch": 10.037071362372567,
+      "grad_norm": 78.0780029296875,
+      "learning_rate": 1.660470879801735e-05,
+      "loss": 6.1798,
+      "step": 2700
+    },
+    {
+      "epoch": 10.037071362372567,
+      "eval_loss": 2.993870735168457,
+      "eval_runtime": 34.3527,
+      "eval_samples_per_second": 47.1,
+      "eval_steps_per_second": 6.753,
+      "step": 2700
+    },
+    {
+      "epoch": 10.074142724745135,
+      "grad_norm": 177.5696563720703,
+      "learning_rate": 1.6542750929368033e-05,
+      "loss": 7.2224,
+      "step": 2710
+    },
+    {
+      "epoch": 10.111214087117702,
+      "grad_norm": 134.7563018798828,
+      "learning_rate": 1.6480793060718714e-05,
+      "loss": 6.5327,
+      "step": 2720
+    },
+    {
+      "epoch": 10.148285449490269,
+      "grad_norm": 122.22810363769531,
+      "learning_rate": 1.6418835192069395e-05,
+      "loss": 7.4686,
+      "step": 2730
+    },
+    {
+      "epoch": 10.185356811862835,
+      "grad_norm": 137.185302734375,
+      "learning_rate": 1.6356877323420076e-05,
+      "loss": 6.1404,
+      "step": 2740
+    },
+    {
+      "epoch": 10.222428174235404,
+      "grad_norm": 100.84989166259766,
+      "learning_rate": 1.6294919454770753e-05,
+      "loss": 7.0005,
+      "step": 2750
+    },
+    {
+      "epoch": 10.25949953660797,
+      "grad_norm": 122.00653839111328,
+      "learning_rate": 1.6232961586121438e-05,
+      "loss": 5.7726,
+      "step": 2760
+    },
+    {
+      "epoch": 10.296570898980537,
+      "grad_norm": 172.2955780029297,
+      "learning_rate": 1.617100371747212e-05,
+      "loss": 6.5327,
+      "step": 2770
+    },
+    {
+      "epoch": 10.333642261353106,
+      "grad_norm": 195.36851501464844,
+      "learning_rate": 1.61090458488228e-05,
+      "loss": 7.5015,
+      "step": 2780
+    },
+    {
+      "epoch": 10.370713623725672,
+      "grad_norm": 135.3350372314453,
+      "learning_rate": 1.604708798017348e-05,
+      "loss": 6.5526,
+      "step": 2790
+    },
+    {
+      "epoch": 10.407784986098239,
+      "grad_norm": 106.01554870605469,
+      "learning_rate": 1.5985130111524162e-05,
+      "loss": 6.2078,
+      "step": 2800
+    },
+    {
+      "epoch": 10.444856348470806,
+      "grad_norm": 104.4194564819336,
+      "learning_rate": 1.5923172242874846e-05,
+      "loss": 6.1,
+      "step": 2810
+    },
+    {
+      "epoch": 10.481927710843374,
+      "grad_norm": 118.46540069580078,
+      "learning_rate": 1.5861214374225527e-05,
+      "loss": 7.1027,
+      "step": 2820
+    },
+    {
+      "epoch": 10.51899907321594,
+      "grad_norm": 108.23471069335938,
+      "learning_rate": 1.5799256505576208e-05,
+      "loss": 8.639,
+      "step": 2830
+    },
+    {
+      "epoch": 10.556070435588508,
+      "grad_norm": 144.46780395507812,
+      "learning_rate": 1.573729863692689e-05,
+      "loss": 6.9937,
+      "step": 2840
+    },
+    {
+      "epoch": 10.593141797961074,
+      "grad_norm": 108.4492416381836,
+      "learning_rate": 1.567534076827757e-05,
+      "loss": 7.2734,
+      "step": 2850
+    },
+    {
+      "epoch": 10.593141797961074,
+      "eval_loss": 2.8532466888427734,
+      "eval_runtime": 34.3677,
+      "eval_samples_per_second": 47.079,
+      "eval_steps_per_second": 6.751,
+      "step": 2850
+    },
+    {
+      "epoch": 10.630213160333643,
+      "grad_norm": 143.1586151123047,
+      "learning_rate": 1.5613382899628255e-05,
+      "loss": 7.6321,
+      "step": 2860
+    },
+    {
+      "epoch": 10.66728452270621,
+      "grad_norm": 98.63433837890625,
+      "learning_rate": 1.5551425030978936e-05,
+      "loss": 7.5788,
+      "step": 2870
+    },
+    {
+      "epoch": 10.704355885078776,
+      "grad_norm": 90.4648666381836,
+      "learning_rate": 1.5489467162329617e-05,
+      "loss": 6.7864,
+      "step": 2880
+    },
+    {
+      "epoch": 10.741427247451345,
+      "grad_norm": 141.69007873535156,
+      "learning_rate": 1.5427509293680298e-05,
+      "loss": 7.4237,
+      "step": 2890
+    },
+    {
+      "epoch": 10.778498609823911,
+      "grad_norm": 126.74280548095703,
+      "learning_rate": 1.536555142503098e-05,
+      "loss": 6.9813,
+      "step": 2900
+    },
+    {
+      "epoch": 10.815569972196478,
+      "grad_norm": 82.08953094482422,
+      "learning_rate": 1.5303593556381663e-05,
+      "loss": 6.6884,
+      "step": 2910
+    },
+    {
+      "epoch": 10.852641334569045,
+      "grad_norm": 123.8572998046875,
+      "learning_rate": 1.5241635687732344e-05,
+      "loss": 6.7464,
+      "step": 2920
+    },
+    {
+      "epoch": 10.889712696941613,
+      "grad_norm": 132.33477783203125,
+      "learning_rate": 1.5179677819083025e-05,
+      "loss": 7.7989,
+      "step": 2930
+    },
+    {
+      "epoch": 10.92678405931418,
+      "grad_norm": 81.7636489868164,
+      "learning_rate": 1.5117719950433704e-05,
+      "loss": 7.3568,
+      "step": 2940
+    },
+    {
+      "epoch": 10.963855421686747,
+      "grad_norm": 244.56277465820312,
+      "learning_rate": 1.5055762081784385e-05,
+      "loss": 8.6706,
+      "step": 2950
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 121.42695617675781,
+      "learning_rate": 1.4993804213135068e-05,
+      "loss": 6.5687,
+      "step": 2960
+    },
+    {
+      "epoch": 11.037071362372567,
+      "grad_norm": 145.1683349609375,
+      "learning_rate": 1.493184634448575e-05,
+      "loss": 5.8992,
+      "step": 2970
+    },
+    {
+      "epoch": 11.074142724745135,
+      "grad_norm": 109.68660736083984,
+      "learning_rate": 1.4869888475836432e-05,
+      "loss": 6.4543,
+      "step": 2980
+    },
+    {
+      "epoch": 11.111214087117702,
+      "grad_norm": 93.12600708007812,
+      "learning_rate": 1.4807930607187113e-05,
+      "loss": 6.1386,
+      "step": 2990
+    },
+    {
+      "epoch": 11.148285449490269,
+      "grad_norm": 167.23182678222656,
+      "learning_rate": 1.4745972738537794e-05,
+      "loss": 6.9047,
+      "step": 3000
+    },
+    {
+      "epoch": 11.148285449490269,
+      "eval_loss": 2.9146969318389893,
+      "eval_runtime": 34.386,
+      "eval_samples_per_second": 47.054,
+      "eval_steps_per_second": 6.747,
+      "step": 3000
+    },
+    {
+      "epoch": 11.185356811862835,
+      "grad_norm": 115.30802154541016,
+      "learning_rate": 1.4684014869888477e-05,
+      "loss": 7.405,
+      "step": 3010
+    },
+    {
+      "epoch": 11.222428174235404,
+      "grad_norm": 103.70664978027344,
+      "learning_rate": 1.4622057001239158e-05,
+      "loss": 7.5441,
+      "step": 3020
+    },
+    {
+      "epoch": 11.25949953660797,
+      "grad_norm": 102.01170349121094,
+      "learning_rate": 1.4560099132589839e-05,
+      "loss": 6.7524,
+      "step": 3030
+    },
+    {
+      "epoch": 11.296570898980537,
+      "grad_norm": 151.57167053222656,
+      "learning_rate": 1.4498141263940521e-05,
+      "loss": 7.698,
+      "step": 3040
+    },
+    {
+      "epoch": 11.333642261353106,
+      "grad_norm": 158.46485900878906,
+      "learning_rate": 1.4436183395291202e-05,
+      "loss": 7.6167,
+      "step": 3050
+    },
+    {
+      "epoch": 11.370713623725672,
+      "grad_norm": 160.52752685546875,
+      "learning_rate": 1.4374225526641885e-05,
+      "loss": 7.1516,
+      "step": 3060
+    },
+    {
+      "epoch": 11.407784986098239,
+      "grad_norm": 120.98091888427734,
+      "learning_rate": 1.4312267657992566e-05,
+      "loss": 6.7458,
+      "step": 3070
+    },
+    {
+      "epoch": 11.444856348470806,
+      "grad_norm": 94.3011474609375,
+      "learning_rate": 1.4250309789343247e-05,
+      "loss": 6.7608,
+      "step": 3080
+    },
+    {
+      "epoch": 11.481927710843374,
+      "grad_norm": 95.0993881225586,
+      "learning_rate": 1.4188351920693928e-05,
+      "loss": 7.1508,
+      "step": 3090
+    },
+    {
+      "epoch": 11.51899907321594,
+      "grad_norm": 114.52859497070312,
+      "learning_rate": 1.4126394052044609e-05,
+      "loss": 6.9155,
+      "step": 3100
+    },
+    {
+      "epoch": 11.556070435588508,
+      "grad_norm": 124.27045440673828,
+      "learning_rate": 1.4064436183395292e-05,
+      "loss": 6.6664,
+      "step": 3110
+    },
+    {
+      "epoch": 11.593141797961074,
+      "grad_norm": 149.13070678710938,
+      "learning_rate": 1.4002478314745973e-05,
+      "loss": 8.3841,
+      "step": 3120
+    },
+    {
+      "epoch": 11.630213160333643,
+      "grad_norm": 93.60704040527344,
+      "learning_rate": 1.3940520446096655e-05,
+      "loss": 7.1934,
+      "step": 3130
+    },
+    {
+      "epoch": 11.66728452270621,
+      "grad_norm": 104.77314758300781,
+      "learning_rate": 1.3878562577447336e-05,
+      "loss": 6.9681,
+      "step": 3140
+    },
+    {
+      "epoch": 11.704355885078776,
+      "grad_norm": 150.2197265625,
+      "learning_rate": 1.3816604708798017e-05,
+      "loss": 7.2187,
+      "step": 3150
+    },
+    {
+      "epoch": 11.704355885078776,
+      "eval_loss": 2.7509171962738037,
+      "eval_runtime": 34.3139,
+      "eval_samples_per_second": 47.153,
+      "eval_steps_per_second": 6.761,
+      "step": 3150
+    },
+    {
+      "epoch": 11.741427247451345,
+      "grad_norm": 164.05996704101562,
+      "learning_rate": 1.37546468401487e-05,
+      "loss": 7.3155,
+      "step": 3160
+    },
+    {
+      "epoch": 11.778498609823911,
+      "grad_norm": 104.55535125732422,
+      "learning_rate": 1.3692688971499381e-05,
+      "loss": 7.3103,
+      "step": 3170
+    },
+    {
+      "epoch": 11.815569972196478,
+      "grad_norm": 100.98657989501953,
+      "learning_rate": 1.3630731102850064e-05,
+      "loss": 7.1959,
+      "step": 3180
+    },
+    {
+      "epoch": 11.852641334569045,
+      "grad_norm": 109.6310043334961,
+      "learning_rate": 1.3568773234200743e-05,
+      "loss": 6.8164,
+      "step": 3190
+    },
+    {
+      "epoch": 11.889712696941613,
+      "grad_norm": 116.8626480102539,
+      "learning_rate": 1.3506815365551424e-05,
+      "loss": 7.5836,
+      "step": 3200
+    },
+    {
+      "epoch": 11.92678405931418,
+      "grad_norm": 106.15950775146484,
+      "learning_rate": 1.3444857496902107e-05,
+      "loss": 5.2671,
+      "step": 3210
+    },
+    {
+      "epoch": 11.963855421686747,
+      "grad_norm": 131.19873046875,
+      "learning_rate": 1.3382899628252788e-05,
+      "loss": 6.4929,
+      "step": 3220
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 61.416534423828125,
+      "learning_rate": 1.332094175960347e-05,
+      "loss": 7.0892,
+      "step": 3230
+    },
+    {
+      "epoch": 12.037071362372567,
+      "grad_norm": 110.03706359863281,
+      "learning_rate": 1.3258983890954152e-05,
+      "loss": 7.0877,
+      "step": 3240
+    },
+    {
+      "epoch": 12.074142724745135,
+      "grad_norm": 68.34326171875,
+      "learning_rate": 1.3197026022304833e-05,
+      "loss": 5.8302,
+      "step": 3250
+    },
+    {
+      "epoch": 12.111214087117702,
+      "grad_norm": 136.8495635986328,
+      "learning_rate": 1.3135068153655515e-05,
+      "loss": 5.6145,
+      "step": 3260
+    },
+    {
+      "epoch": 12.148285449490269,
+      "grad_norm": 103.39452362060547,
+      "learning_rate": 1.3073110285006196e-05,
+      "loss": 6.5808,
+      "step": 3270
+    },
+    {
+      "epoch": 12.185356811862835,
+      "grad_norm": 107.7593994140625,
+      "learning_rate": 1.3011152416356879e-05,
+      "loss": 6.6826,
+      "step": 3280
+    },
+    {
+      "epoch": 12.222428174235404,
+      "grad_norm": 99.79641723632812,
+      "learning_rate": 1.2949194547707558e-05,
+      "loss": 5.9819,
+      "step": 3290
+    },
+    {
+      "epoch": 12.25949953660797,
+      "grad_norm": 112.78658294677734,
+      "learning_rate": 1.2887236679058241e-05,
+      "loss": 6.68,
+      "step": 3300
+    },
+    {
+      "epoch": 12.25949953660797,
+      "eval_loss": 3.0174973011016846,
+      "eval_runtime": 34.2754,
+      "eval_samples_per_second": 47.206,
+      "eval_steps_per_second": 6.769,
+      "step": 3300
+    },
+    {
+      "epoch": 12.296570898980537,
+      "grad_norm": 139.285400390625,
+      "learning_rate": 1.2825278810408922e-05,
+      "loss": 6.1685,
+      "step": 3310
+    },
+    {
+      "epoch": 12.333642261353106,
+      "grad_norm": 121.69828796386719,
+      "learning_rate": 1.2763320941759603e-05,
+      "loss": 6.4473,
+      "step": 3320
+    },
+    {
+      "epoch": 12.370713623725672,
+      "grad_norm": 146.68112182617188,
+      "learning_rate": 1.2701363073110286e-05,
+      "loss": 6.3965,
+      "step": 3330
+    },
+    {
+      "epoch": 12.407784986098239,
+      "grad_norm": 144.31346130371094,
+      "learning_rate": 1.2639405204460967e-05,
+      "loss": 6.6278,
+      "step": 3340
+    },
+    {
+      "epoch": 12.444856348470806,
+      "grad_norm": 113.88147735595703,
+      "learning_rate": 1.257744733581165e-05,
+      "loss": 5.4575,
+      "step": 3350
+    },
+    {
+      "epoch": 12.481927710843374,
+      "grad_norm": 199.89317321777344,
+      "learning_rate": 1.251548946716233e-05,
+      "loss": 7.3019,
+      "step": 3360
+    },
+    {
+      "epoch": 12.51899907321594,
+      "grad_norm": 142.75885009765625,
+      "learning_rate": 1.2453531598513011e-05,
+      "loss": 7.4843,
+      "step": 3370
+    },
+    {
+      "epoch": 12.556070435588508,
+      "grad_norm": 185.7791748046875,
+      "learning_rate": 1.2391573729863692e-05,
+      "loss": 6.709,
+      "step": 3380
+    },
+    {
+      "epoch": 12.593141797961074,
+      "grad_norm": 100.56149291992188,
+      "learning_rate": 1.2329615861214373e-05,
+      "loss": 6.7168,
+      "step": 3390
+    },
+    {
+      "epoch": 12.630213160333643,
+      "grad_norm": 169.69461059570312,
+      "learning_rate": 1.2267657992565056e-05,
+      "loss": 7.0223,
+      "step": 3400
+    },
+    {
+      "epoch": 12.66728452270621,
+      "grad_norm": 175.87796020507812,
+      "learning_rate": 1.2205700123915737e-05,
+      "loss": 6.5089,
+      "step": 3410
+    },
+    {
+      "epoch": 12.704355885078776,
+      "grad_norm": 143.18231201171875,
+      "learning_rate": 1.214374225526642e-05,
+      "loss": 6.5094,
+      "step": 3420
+    },
+    {
+      "epoch": 12.741427247451345,
+      "grad_norm": 139.9623260498047,
+      "learning_rate": 1.20817843866171e-05,
+      "loss": 7.2317,
+      "step": 3430
+    },
+    {
+      "epoch": 12.778498609823911,
+      "grad_norm": 162.18252563476562,
+      "learning_rate": 1.2019826517967782e-05,
+      "loss": 6.6885,
+      "step": 3440
+    },
+    {
+      "epoch": 12.815569972196478,
+      "grad_norm": 146.02406311035156,
+      "learning_rate": 1.1957868649318464e-05,
+      "loss": 6.9693,
+      "step": 3450
+    },
+    {
+      "epoch": 12.815569972196478,
+      "eval_loss": 2.8461835384368896,
+      "eval_runtime": 34.1657,
+      "eval_samples_per_second": 47.357,
+      "eval_steps_per_second": 6.79,
+      "step": 3450
+    },
+    {
+      "epoch": 12.852641334569045,
+      "grad_norm": 124.50180053710938,
+      "learning_rate": 1.1895910780669145e-05,
+      "loss": 6.8242,
+      "step": 3460
+    },
+    {
+      "epoch": 12.889712696941613,
+      "grad_norm": 112.58306121826172,
+      "learning_rate": 1.1833952912019828e-05,
+      "loss": 6.6899,
+      "step": 3470
+    },
+    {
+      "epoch": 12.92678405931418,
+      "grad_norm": 122.80091857910156,
+      "learning_rate": 1.1771995043370507e-05,
+      "loss": 6.9113,
+      "step": 3480
+    },
+    {
+      "epoch": 12.963855421686747,
+      "grad_norm": 100.88201141357422,
+      "learning_rate": 1.1710037174721188e-05,
+      "loss": 7.1903,
+      "step": 3490
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 91.95454406738281,
+      "learning_rate": 1.1648079306071871e-05,
+      "loss": 7.3286,
+      "step": 3500
+    },
+    {
+      "epoch": 13.037071362372567,
+      "grad_norm": 150.1581573486328,
+      "learning_rate": 1.1586121437422552e-05,
+      "loss": 6.5465,
+      "step": 3510
+    },
+    {
+      "epoch": 13.074142724745135,
+      "grad_norm": 124.90875244140625,
+      "learning_rate": 1.1524163568773235e-05,
+      "loss": 5.6804,
+      "step": 3520
+    },
+    {
+      "epoch": 13.111214087117702,
+      "grad_norm": 89.16959381103516,
+      "learning_rate": 1.1462205700123916e-05,
+      "loss": 5.6412,
+      "step": 3530
+    },
+    {
+      "epoch": 13.148285449490269,
+      "grad_norm": 139.5684356689453,
+      "learning_rate": 1.1400247831474599e-05,
+      "loss": 6.6161,
+      "step": 3540
+    },
+    {
+      "epoch": 13.185356811862835,
+      "grad_norm": 123.66468048095703,
+      "learning_rate": 1.133828996282528e-05,
+      "loss": 5.761,
+      "step": 3550
+    },
+    {
+      "epoch": 13.222428174235404,
+      "grad_norm": 92.05863189697266,
+      "learning_rate": 1.127633209417596e-05,
+      "loss": 5.5669,
+      "step": 3560
+    },
+    {
+      "epoch": 13.25949953660797,
+      "grad_norm": 106.46834564208984,
+      "learning_rate": 1.1214374225526643e-05,
+      "loss": 5.6184,
+      "step": 3570
+    },
+    {
+      "epoch": 13.296570898980537,
+      "grad_norm": 122.37000274658203,
+      "learning_rate": 1.1152416356877323e-05,
+      "loss": 6.2996,
+      "step": 3580
+    },
+    {
+      "epoch": 13.333642261353106,
+      "grad_norm": 115.14747619628906,
+      "learning_rate": 1.1090458488228005e-05,
+      "loss": 4.99,
+      "step": 3590
+    },
+    {
+      "epoch": 13.370713623725672,
+      "grad_norm": 123.00082397460938,
+      "learning_rate": 1.1028500619578686e-05,
+      "loss": 5.9974,
+      "step": 3600
+    },
+    {
+      "epoch": 13.370713623725672,
+      "eval_loss": 3.235833168029785,
+      "eval_runtime": 34.1503,
+      "eval_samples_per_second": 47.379,
+      "eval_steps_per_second": 6.793,
+      "step": 3600
+    },
+    {
+      "epoch": 13.407784986098239,
+      "grad_norm": 97.1900634765625,
+      "learning_rate": 1.0966542750929367e-05,
+      "loss": 5.6962,
+      "step": 3610
+    },
+    {
+      "epoch": 13.444856348470806,
+      "grad_norm": 166.885986328125,
+      "learning_rate": 1.090458488228005e-05,
+      "loss": 6.3662,
+      "step": 3620
+    },
+    {
+      "epoch": 13.481927710843374,
+      "grad_norm": 153.35101318359375,
+      "learning_rate": 1.0842627013630731e-05,
+      "loss": 7.0398,
+      "step": 3630
+    },
+    {
+      "epoch": 13.51899907321594,
+      "grad_norm": 159.07012939453125,
+      "learning_rate": 1.0780669144981414e-05,
+      "loss": 7.7358,
+      "step": 3640
+    },
+    {
+      "epoch": 13.556070435588508,
+      "grad_norm": 184.1981201171875,
+      "learning_rate": 1.0718711276332095e-05,
+      "loss": 7.9063,
+      "step": 3650
+    },
+    {
+      "epoch": 13.593141797961074,
+      "grad_norm": 125.76744842529297,
+      "learning_rate": 1.0656753407682777e-05,
+      "loss": 5.7823,
+      "step": 3660
+    },
+    {
+      "epoch": 13.630213160333643,
+      "grad_norm": 168.76263427734375,
+      "learning_rate": 1.0594795539033458e-05,
+      "loss": 6.9861,
+      "step": 3670
+    },
+    {
+      "epoch": 13.66728452270621,
+      "grad_norm": 195.7327423095703,
+      "learning_rate": 1.0532837670384138e-05,
+      "loss": 7.2855,
+      "step": 3680
+    },
+    {
+      "epoch": 13.704355885078776,
+      "grad_norm": 140.83375549316406,
+      "learning_rate": 1.047087980173482e-05,
+      "loss": 5.6785,
+      "step": 3690
+    },
+    {
+      "epoch": 13.741427247451345,
+      "grad_norm": 123.63497161865234,
+      "learning_rate": 1.0408921933085501e-05,
+      "loss": 6.4071,
+      "step": 3700
+    },
+    {
+      "epoch": 13.778498609823911,
+      "grad_norm": 80.74890899658203,
+      "learning_rate": 1.0346964064436184e-05,
+      "loss": 6.4294,
+      "step": 3710
+    },
+    {
+      "epoch": 13.815569972196478,
+      "grad_norm": 120.82400512695312,
+      "learning_rate": 1.0285006195786865e-05,
+      "loss": 6.0842,
+      "step": 3720
+    },
+    {
+      "epoch": 13.852641334569045,
+      "grad_norm": 152.11407470703125,
+      "learning_rate": 1.0223048327137546e-05,
+      "loss": 5.9422,
+      "step": 3730
+    },
+    {
+      "epoch": 13.889712696941613,
+      "grad_norm": 112.44628143310547,
+      "learning_rate": 1.0161090458488229e-05,
+      "loss": 7.0778,
+      "step": 3740
+    },
+    {
+      "epoch": 13.92678405931418,
+      "grad_norm": 210.1138916015625,
+      "learning_rate": 1.009913258983891e-05,
+      "loss": 8.1597,
+      "step": 3750
+    },
+    {
+      "epoch": 13.92678405931418,
+      "eval_loss": 3.0093190670013428,
+      "eval_runtime": 34.173,
+      "eval_samples_per_second": 47.347,
+      "eval_steps_per_second": 6.789,
+      "step": 3750
+    },
+    {
+      "epoch": 13.963855421686747,
+      "grad_norm": 157.09022521972656,
+      "learning_rate": 1.0037174721189593e-05,
+      "loss": 6.3154,
+      "step": 3760
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 149.8700408935547,
+      "learning_rate": 9.975216852540272e-06,
+      "loss": 6.2416,
+      "step": 3770
+    },
+    {
+      "epoch": 14.037071362372567,
+      "grad_norm": 95.38166809082031,
+      "learning_rate": 9.913258983890955e-06,
+      "loss": 5.9958,
+      "step": 3780
+    },
+    {
+      "epoch": 14.074142724745135,
+      "grad_norm": 112.23654174804688,
+      "learning_rate": 9.851301115241636e-06,
+      "loss": 5.7032,
+      "step": 3790
+    },
+    {
+      "epoch": 14.111214087117702,
+      "grad_norm": 74.8873062133789,
+      "learning_rate": 9.789343246592317e-06,
+      "loss": 4.9524,
+      "step": 3800
+    },
+    {
+      "epoch": 14.148285449490269,
+      "grad_norm": 105.66299438476562,
+      "learning_rate": 9.727385377943e-06,
+      "loss": 5.386,
+      "step": 3810
+    },
+    {
+      "epoch": 14.185356811862835,
+      "grad_norm": 108.44865417480469,
+      "learning_rate": 9.66542750929368e-06,
+      "loss": 5.6353,
+      "step": 3820
+    },
+    {
+      "epoch": 14.222428174235404,
+      "grad_norm": 93.0536117553711,
+      "learning_rate": 9.603469640644363e-06,
+      "loss": 5.0873,
+      "step": 3830
+    },
+    {
+      "epoch": 14.25949953660797,
+      "grad_norm": 98.93279266357422,
+      "learning_rate": 9.541511771995044e-06,
+      "loss": 4.9255,
+      "step": 3840
+    },
+    {
+      "epoch": 14.296570898980537,
+      "grad_norm": 143.44992065429688,
+      "learning_rate": 9.479553903345725e-06,
+      "loss": 5.1423,
+      "step": 3850
+    },
+    {
+      "epoch": 14.333642261353106,
+      "grad_norm": 103.24166107177734,
+      "learning_rate": 9.417596034696408e-06,
+      "loss": 6.0775,
+      "step": 3860
+    },
+    {
+      "epoch": 14.370713623725672,
+      "grad_norm": 208.1169891357422,
+      "learning_rate": 9.355638166047087e-06,
+      "loss": 4.5073,
+      "step": 3870
+    },
+    {
+      "epoch": 14.407784986098239,
+      "grad_norm": 186.23892211914062,
+      "learning_rate": 9.29368029739777e-06,
+      "loss": 6.8347,
+      "step": 3880
+    },
+    {
+      "epoch": 14.444856348470806,
+      "grad_norm": 190.22607421875,
+      "learning_rate": 9.23172242874845e-06,
+      "loss": 6.5397,
+      "step": 3890
+    },
+    {
+      "epoch": 14.481927710843374,
+      "grad_norm": 186.79270935058594,
+      "learning_rate": 9.169764560099133e-06,
+      "loss": 7.2143,
+      "step": 3900
+    },
+    {
+      "epoch": 14.481927710843374,
+      "eval_loss": 3.308037042617798,
+      "eval_runtime": 41.7479,
+      "eval_samples_per_second": 38.756,
+      "eval_steps_per_second": 5.557,
+      "step": 3900
+    },
+    {
+      "epoch": 14.51899907321594,
+      "grad_norm": 146.21145629882812,
+      "learning_rate": 9.107806691449814e-06,
+      "loss": 6.1123,
+      "step": 3910
+    },
+    {
+      "epoch": 14.556070435588508,
+      "grad_norm": 170.6797637939453,
+      "learning_rate": 9.045848822800495e-06,
+      "loss": 6.6048,
+      "step": 3920
+    },
+    {
+      "epoch": 14.593141797961074,
+      "grad_norm": 118.28248596191406,
+      "learning_rate": 8.983890954151178e-06,
+      "loss": 6.3464,
+      "step": 3930
+    },
+    {
+      "epoch": 14.630213160333643,
+      "grad_norm": 170.6762237548828,
+      "learning_rate": 8.921933085501859e-06,
+      "loss": 6.3618,
+      "step": 3940
+    },
+    {
+      "epoch": 14.66728452270621,
+      "grad_norm": 148.5935516357422,
+      "learning_rate": 8.859975216852542e-06,
+      "loss": 6.5718,
+      "step": 3950
+    },
+    {
+      "epoch": 14.704355885078776,
+      "grad_norm": 72.61006164550781,
+      "learning_rate": 8.798017348203223e-06,
+      "loss": 5.9785,
+      "step": 3960
+    },
+    {
+      "epoch": 14.741427247451345,
+      "grad_norm": 164.15184020996094,
+      "learning_rate": 8.736059479553902e-06,
+      "loss": 6.5758,
+      "step": 3970
+    },
+    {
+      "epoch": 14.778498609823911,
+      "grad_norm": 140.56019592285156,
+      "learning_rate": 8.674101610904585e-06,
+      "loss": 6.4308,
+      "step": 3980
+    },
+    {
+      "epoch": 14.815569972196478,
+      "grad_norm": 127.03153991699219,
+      "learning_rate": 8.612143742255266e-06,
+      "loss": 6.0208,
+      "step": 3990
+    },
+    {
+      "epoch": 14.852641334569045,
+      "grad_norm": 146.550048828125,
+      "learning_rate": 8.550185873605949e-06,
+      "loss": 6.0303,
+      "step": 4000
+    },
+    {
+      "epoch": 14.889712696941613,
+      "grad_norm": 106.98975372314453,
+      "learning_rate": 8.48822800495663e-06,
+      "loss": 6.6396,
+      "step": 4010
+    },
+    {
+      "epoch": 14.92678405931418,
+      "grad_norm": 124.45453643798828,
+      "learning_rate": 8.42627013630731e-06,
+      "loss": 6.0184,
+      "step": 4020
+    },
+    {
+      "epoch": 14.963855421686747,
+      "grad_norm": 185.95437622070312,
+      "learning_rate": 8.364312267657993e-06,
+      "loss": 6.6248,
+      "step": 4030
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 129.69049072265625,
+      "learning_rate": 8.302354399008674e-06,
+      "loss": 6.4538,
+      "step": 4040
+    },
+    {
+      "epoch": 15.037071362372567,
+      "grad_norm": 164.9100799560547,
+      "learning_rate": 8.240396530359357e-06,
+      "loss": 6.4742,
+      "step": 4050
+    },
+    {
+      "epoch": 15.037071362372567,
+      "eval_loss": 3.176128625869751,
+      "eval_runtime": 34.1148,
+      "eval_samples_per_second": 47.428,
+      "eval_steps_per_second": 6.801,
+      "step": 4050
+    },
+    {
+      "epoch": 15.074142724745135,
+      "grad_norm": 150.71412658691406,
+      "learning_rate": 8.178438661710038e-06,
+      "loss": 5.5295,
+      "step": 4060
+    },
+    {
+      "epoch": 15.111214087117702,
+      "grad_norm": 154.99163818359375,
+      "learning_rate": 8.116480793060719e-06,
+      "loss": 6.8753,
+      "step": 4070
+    },
+    {
+      "epoch": 15.148285449490269,
+      "grad_norm": 109.33438110351562,
+      "learning_rate": 8.0545229244114e-06,
+      "loss": 5.639,
+      "step": 4080
+    },
+    {
+      "epoch": 15.185356811862835,
+      "grad_norm": 137.58786010742188,
+      "learning_rate": 7.992565055762081e-06,
+      "loss": 5.6232,
+      "step": 4090
+    },
+    {
+      "epoch": 15.222428174235404,
+      "grad_norm": 147.41519165039062,
+      "learning_rate": 7.930607187112764e-06,
+      "loss": 6.3026,
+      "step": 4100
+    },
+    {
+      "epoch": 15.25949953660797,
+      "grad_norm": 93.34049224853516,
+      "learning_rate": 7.868649318463445e-06,
+      "loss": 6.1182,
+      "step": 4110
+    },
+    {
+      "epoch": 15.296570898980537,
+      "grad_norm": 123.48411560058594,
+      "learning_rate": 7.806691449814127e-06,
+      "loss": 5.4736,
+      "step": 4120
+    },
+    {
+      "epoch": 15.333642261353106,
+      "grad_norm": 185.36781311035156,
+      "learning_rate": 7.744733581164808e-06,
+      "loss": 6.2961,
+      "step": 4130
+    },
+    {
+      "epoch": 15.370713623725672,
+      "grad_norm": 180.45494079589844,
+      "learning_rate": 7.68277571251549e-06,
+      "loss": 5.4742,
+      "step": 4140
+    },
+    {
+      "epoch": 15.407784986098239,
+      "grad_norm": 77.34858703613281,
+      "learning_rate": 7.620817843866172e-06,
+      "loss": 5.4707,
+      "step": 4150
+    },
+    {
+      "epoch": 15.444856348470806,
+      "grad_norm": 150.97511291503906,
+      "learning_rate": 7.558859975216852e-06,
+      "loss": 4.7272,
+      "step": 4160
+    },
+    {
+      "epoch": 15.481927710843374,
+      "grad_norm": 153.45291137695312,
+      "learning_rate": 7.496902106567534e-06,
+      "loss": 6.1026,
+      "step": 4170
+    },
+    {
+      "epoch": 15.51899907321594,
+      "grad_norm": 172.51651000976562,
+      "learning_rate": 7.434944237918216e-06,
+      "loss": 5.0468,
+      "step": 4180
+    },
+    {
+      "epoch": 15.556070435588508,
+      "grad_norm": 168.9851837158203,
+      "learning_rate": 7.372986369268897e-06,
+      "loss": 5.5796,
+      "step": 4190
+    },
+    {
+      "epoch": 15.593141797961074,
+      "grad_norm": 213.8069610595703,
+      "learning_rate": 7.311028500619579e-06,
+      "loss": 6.9046,
+      "step": 4200
+    },
+    {
+      "epoch": 15.593141797961074,
+      "eval_loss": 3.1433465480804443,
+      "eval_runtime": 34.1213,
+      "eval_samples_per_second": 47.419,
+      "eval_steps_per_second": 6.799,
+      "step": 4200
+    },
+    {
+      "epoch": 15.630213160333643,
+      "grad_norm": 167.3193359375,
+      "learning_rate": 7.249070631970261e-06,
+      "loss": 5.6123,
+      "step": 4210
+    },
+    {
+      "epoch": 15.66728452270621,
+      "grad_norm": 186.83468627929688,
+      "learning_rate": 7.1871127633209425e-06,
+      "loss": 6.7246,
+      "step": 4220
+    },
+    {
+      "epoch": 15.704355885078776,
+      "grad_norm": 95.93631744384766,
+      "learning_rate": 7.1251548946716235e-06,
+      "loss": 5.7076,
+      "step": 4230
+    },
+    {
+      "epoch": 15.741427247451345,
+      "grad_norm": 115.92752075195312,
+      "learning_rate": 7.0631970260223045e-06,
+      "loss": 6.6772,
+      "step": 4240
+    },
+    {
+      "epoch": 15.778498609823911,
+      "grad_norm": 103.57062530517578,
+      "learning_rate": 7.001239157372986e-06,
+      "loss": 5.6038,
+      "step": 4250
+    },
+    {
+      "epoch": 15.815569972196478,
+      "grad_norm": 75.92886352539062,
+      "learning_rate": 6.939281288723668e-06,
+      "loss": 4.9544,
+      "step": 4260
+    },
+    {
+      "epoch": 15.852641334569045,
+      "grad_norm": 194.57139587402344,
+      "learning_rate": 6.87732342007435e-06,
+      "loss": 5.0661,
+      "step": 4270
+    },
+    {
+      "epoch": 15.889712696941613,
+      "grad_norm": 192.36314392089844,
+      "learning_rate": 6.815365551425032e-06,
+      "loss": 5.291,
+      "step": 4280
+    },
+    {
+      "epoch": 15.92678405931418,
+      "grad_norm": 224.52699279785156,
+      "learning_rate": 6.753407682775712e-06,
+      "loss": 6.6652,
+      "step": 4290
+    },
+    {
+      "epoch": 15.963855421686747,
+      "grad_norm": 140.450927734375,
+      "learning_rate": 6.691449814126394e-06,
+      "loss": 5.6797,
+      "step": 4300
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 114.00956726074219,
+      "learning_rate": 6.629491945477076e-06,
+      "loss": 5.1129,
+      "step": 4310
+    },
+    {
+      "epoch": 16.03707136237257,
+      "grad_norm": 207.12156677246094,
+      "learning_rate": 6.567534076827758e-06,
+      "loss": 5.4445,
+      "step": 4320
+    },
+    {
+      "epoch": 16.074142724745133,
+      "grad_norm": 197.20050048828125,
+      "learning_rate": 6.5055762081784395e-06,
+      "loss": 4.8946,
+      "step": 4330
+    },
+    {
+      "epoch": 16.111214087117702,
+      "grad_norm": 180.85137939453125,
+      "learning_rate": 6.4436183395291205e-06,
+      "loss": 6.3929,
+      "step": 4340
+    },
+    {
+      "epoch": 16.14828544949027,
+      "grad_norm": 192.41107177734375,
+      "learning_rate": 6.3816604708798015e-06,
+      "loss": 6.0633,
+      "step": 4350
+    },
+    {
+      "epoch": 16.14828544949027,
+      "eval_loss": 3.142592668533325,
+      "eval_runtime": 34.1151,
+      "eval_samples_per_second": 47.428,
+      "eval_steps_per_second": 6.801,
+      "step": 4350
+    },
+    {
+      "epoch": 16.185356811862835,
+      "grad_norm": 135.17002868652344,
+      "learning_rate": 6.319702602230483e-06,
+      "loss": 5.522,
+      "step": 4360
+    },
+    {
+      "epoch": 16.222428174235404,
+      "grad_norm": 196.92721557617188,
+      "learning_rate": 6.257744733581165e-06,
+      "loss": 4.7067,
+      "step": 4370
+    },
+    {
+      "epoch": 16.25949953660797,
+      "grad_norm": 166.54722595214844,
+      "learning_rate": 6.195786864931846e-06,
+      "loss": 5.4688,
+      "step": 4380
+    },
+    {
+      "epoch": 16.296570898980537,
+      "grad_norm": 142.71371459960938,
+      "learning_rate": 6.133828996282528e-06,
+      "loss": 5.6009,
+      "step": 4390
+    },
+    {
+      "epoch": 16.333642261353106,
+      "grad_norm": 193.82192993164062,
+      "learning_rate": 6.07187112763321e-06,
+      "loss": 5.1376,
+      "step": 4400
+    },
+    {
+      "epoch": 16.37071362372567,
+      "grad_norm": 105.82157897949219,
+      "learning_rate": 6.009913258983891e-06,
+      "loss": 4.5196,
+      "step": 4410
+    },
+    {
+      "epoch": 16.40778498609824,
+      "grad_norm": 168.8805694580078,
+      "learning_rate": 5.947955390334573e-06,
+      "loss": 5.5109,
+      "step": 4420
+    },
+    {
+      "epoch": 16.444856348470807,
+      "grad_norm": 196.2225799560547,
+      "learning_rate": 5.885997521685254e-06,
+      "loss": 5.1888,
+      "step": 4430
+    },
+    {
+      "epoch": 16.481927710843372,
+      "grad_norm": 230.24151611328125,
+      "learning_rate": 5.824039653035936e-06,
+      "loss": 6.0305,
+      "step": 4440
+    },
+    {
+      "epoch": 16.51899907321594,
+      "grad_norm": 211.2703094482422,
+      "learning_rate": 5.7620817843866174e-06,
+      "loss": 5.2791,
+      "step": 4450
+    },
+    {
+      "epoch": 16.55607043558851,
+      "grad_norm": 163.81448364257812,
+      "learning_rate": 5.700123915737299e-06,
+      "loss": 5.4005,
+      "step": 4460
+    },
+    {
+      "epoch": 16.593141797961074,
+      "grad_norm": 134.9607696533203,
+      "learning_rate": 5.63816604708798e-06,
+      "loss": 5.255,
+      "step": 4470
+    },
+    {
+      "epoch": 16.630213160333643,
+      "grad_norm": 252.0573272705078,
+      "learning_rate": 5.576208178438661e-06,
+      "loss": 6.2026,
+      "step": 4480
+    },
+    {
+      "epoch": 16.66728452270621,
+      "grad_norm": 260.19677734375,
+      "learning_rate": 5.514250309789343e-06,
+      "loss": 6.6388,
+      "step": 4490
+    },
+    {
+      "epoch": 16.704355885078776,
+      "grad_norm": 194.9749755859375,
+      "learning_rate": 5.452292441140025e-06,
+      "loss": 5.6138,
+      "step": 4500
+    },
+    {
+      "epoch": 16.704355885078776,
+      "eval_loss": 3.2811691761016846,
+      "eval_runtime": 34.1081,
+      "eval_samples_per_second": 47.437,
+      "eval_steps_per_second": 6.802,
+      "step": 4500
+    },
+    {
+      "epoch": 16.741427247451345,
+      "grad_norm": 142.59588623046875,
+      "learning_rate": 5.390334572490707e-06,
+      "loss": 4.7913,
+      "step": 4510
+    },
+    {
+      "epoch": 16.77849860982391,
+      "grad_norm": 170.17701721191406,
+      "learning_rate": 5.328376703841389e-06,
+      "loss": 5.6675,
+      "step": 4520
+    },
+    {
+      "epoch": 16.815569972196478,
+      "grad_norm": 125.95365142822266,
+      "learning_rate": 5.266418835192069e-06,
+      "loss": 5.8975,
+      "step": 4530
+    },
+    {
+      "epoch": 16.852641334569046,
+      "grad_norm": 104.74299621582031,
+      "learning_rate": 5.204460966542751e-06,
+      "loss": 5.4597,
+      "step": 4540
+    },
+    {
+      "epoch": 16.88971269694161,
+      "grad_norm": 103.75862121582031,
+      "learning_rate": 5.1425030978934326e-06,
+      "loss": 5.137,
+      "step": 4550
+    },
+    {
+      "epoch": 16.92678405931418,
+      "grad_norm": 151.0890655517578,
+      "learning_rate": 5.0805452292441144e-06,
+      "loss": 4.5395,
+      "step": 4560
+    },
+    {
+      "epoch": 16.96385542168675,
+      "grad_norm": 146.775146484375,
+      "learning_rate": 5.018587360594796e-06,
+      "loss": 4.6304,
+      "step": 4570
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 57.623138427734375,
+      "learning_rate": 4.956629491945477e-06,
+      "loss": 5.8098,
+      "step": 4580
+    },
+    {
+      "epoch": 17.03707136237257,
+      "grad_norm": 396.8329162597656,
+      "learning_rate": 4.894671623296158e-06,
+      "loss": 4.0267,
+      "step": 4590
+    },
+    {
+      "epoch": 17.074142724745133,
+      "grad_norm": 131.9137725830078,
+      "learning_rate": 4.83271375464684e-06,
+      "loss": 4.9194,
+      "step": 4600
+    },
+    {
+      "epoch": 17.111214087117702,
+      "grad_norm": 73.31439971923828,
+      "learning_rate": 4.770755885997522e-06,
+      "loss": 4.1852,
+      "step": 4610
+    },
+    {
+      "epoch": 17.14828544949027,
+      "grad_norm": 162.74197387695312,
+      "learning_rate": 4.708798017348204e-06,
+      "loss": 5.129,
+      "step": 4620
+    },
+    {
+      "epoch": 17.185356811862835,
+      "grad_norm": 134.66238403320312,
+      "learning_rate": 4.646840148698885e-06,
+      "loss": 4.469,
+      "step": 4630
+    },
+    {
+      "epoch": 17.222428174235404,
+      "grad_norm": 164.04136657714844,
+      "learning_rate": 4.584882280049567e-06,
+      "loss": 5.4298,
+      "step": 4640
+    },
+    {
+      "epoch": 17.25949953660797,
+      "grad_norm": 128.1541290283203,
+      "learning_rate": 4.522924411400248e-06,
+      "loss": 4.5234,
+      "step": 4650
+    },
+    {
+      "epoch": 17.25949953660797,
+      "eval_loss": 3.344738006591797,
+      "eval_runtime": 34.1153,
+      "eval_samples_per_second": 47.427,
+      "eval_steps_per_second": 6.8,
+      "step": 4650
+    },
+    {
+      "epoch": 17.296570898980537,
+      "grad_norm": 210.09783935546875,
+      "learning_rate": 4.4609665427509296e-06,
+      "loss": 4.6856,
+      "step": 4660
+    },
+    {
+      "epoch": 17.333642261353106,
+      "grad_norm": 310.232666015625,
+      "learning_rate": 4.399008674101611e-06,
+      "loss": 6.3431,
+      "step": 4670
+    },
+    {
+      "epoch": 17.37071362372567,
+      "grad_norm": 176.26223754882812,
+      "learning_rate": 4.337050805452292e-06,
+      "loss": 5.347,
+      "step": 4680
+    },
+    {
+      "epoch": 17.40778498609824,
+      "grad_norm": 272.3112487792969,
+      "learning_rate": 4.275092936802974e-06,
+      "loss": 4.9223,
+      "step": 4690
+    },
+    {
+      "epoch": 17.444856348470807,
+      "grad_norm": 220.5677947998047,
+      "learning_rate": 4.213135068153655e-06,
+      "loss": 5.4404,
+      "step": 4700
+    },
+    {
+      "epoch": 17.481927710843372,
+      "grad_norm": 207.5516357421875,
+      "learning_rate": 4.151177199504337e-06,
+      "loss": 4.916,
+      "step": 4710
+    },
+    {
+      "epoch": 17.51899907321594,
+      "grad_norm": 201.2340545654297,
+      "learning_rate": 4.089219330855019e-06,
+      "loss": 6.1744,
+      "step": 4720
+    },
+    {
+      "epoch": 17.55607043558851,
+      "grad_norm": 200.8380126953125,
+      "learning_rate": 4.0272614622057e-06,
+      "loss": 4.8039,
+      "step": 4730
+    },
+    {
+      "epoch": 17.593141797961074,
+      "grad_norm": 274.0273742675781,
+      "learning_rate": 3.965303593556382e-06,
+      "loss": 5.2276,
+      "step": 4740
+    },
+    {
+      "epoch": 17.630213160333643,
+      "grad_norm": 132.97317504882812,
+      "learning_rate": 3.903345724907064e-06,
+      "loss": 4.4189,
+      "step": 4750
+    },
+    {
+      "epoch": 17.66728452270621,
+      "grad_norm": 126.97086334228516,
+      "learning_rate": 3.841387856257745e-06,
+      "loss": 4.1434,
+      "step": 4760
+    },
+    {
+      "epoch": 17.704355885078776,
+      "grad_norm": 118.29164123535156,
+      "learning_rate": 3.779429987608426e-06,
+      "loss": 4.9443,
+      "step": 4770
+    },
+    {
+      "epoch": 17.741427247451345,
+      "grad_norm": 498.6371765136719,
+      "learning_rate": 3.717472118959108e-06,
+      "loss": 5.6975,
+      "step": 4780
+    },
+    {
+      "epoch": 17.77849860982391,
+      "grad_norm": 154.814453125,
+      "learning_rate": 3.6555142503097894e-06,
+      "loss": 4.6667,
+      "step": 4790
+    },
+    {
+      "epoch": 17.815569972196478,
+      "grad_norm": 207.75082397460938,
+      "learning_rate": 3.5935563816604712e-06,
+      "loss": 4.9876,
+      "step": 4800
+    },
+    {
+      "epoch": 17.815569972196478,
+      "eval_loss": 3.2923643589019775,
+      "eval_runtime": 34.1089,
+      "eval_samples_per_second": 47.436,
+      "eval_steps_per_second": 6.802,
+      "step": 4800
+    },
+    {
+      "epoch": 17.852641334569046,
+      "grad_norm": 199.7575225830078,
+      "learning_rate": 3.5315985130111522e-06,
+      "loss": 4.4342,
+      "step": 4810
+    },
+    {
+      "epoch": 17.88971269694161,
+      "grad_norm": 103.82642364501953,
+      "learning_rate": 3.469640644361834e-06,
+      "loss": 5.2595,
+      "step": 4820
+    },
+    {
+      "epoch": 17.92678405931418,
+      "grad_norm": 188.52745056152344,
+      "learning_rate": 3.407682775712516e-06,
+      "loss": 5.6566,
+      "step": 4830
+    },
+    {
+      "epoch": 17.96385542168675,
+      "grad_norm": 124.60482025146484,
+      "learning_rate": 3.345724907063197e-06,
+      "loss": 5.5452,
+      "step": 4840
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 106.7363052368164,
+      "learning_rate": 3.283767038413879e-06,
+      "loss": 4.4986,
+      "step": 4850
+    },
+    {
+      "epoch": 18.03707136237257,
+      "grad_norm": 160.66836547851562,
+      "learning_rate": 3.2218091697645602e-06,
+      "loss": 4.8155,
+      "step": 4860
+    },
+    {
+      "epoch": 18.074142724745133,
+      "grad_norm": 155.60548400878906,
+      "learning_rate": 3.1598513011152417e-06,
+      "loss": 4.2278,
+      "step": 4870
+    },
+    {
+      "epoch": 18.111214087117702,
+      "grad_norm": 222.5984344482422,
+      "learning_rate": 3.097893432465923e-06,
+      "loss": 5.4733,
+      "step": 4880
+    },
+    {
+      "epoch": 18.14828544949027,
+      "grad_norm": 115.56200408935547,
+      "learning_rate": 3.035935563816605e-06,
+      "loss": 4.2394,
+      "step": 4890
+    },
+    {
+      "epoch": 18.185356811862835,
+      "grad_norm": 181.39199829101562,
+      "learning_rate": 2.9739776951672864e-06,
+      "loss": 5.1253,
+      "step": 4900
+    },
+    {
+      "epoch": 18.222428174235404,
+      "grad_norm": 53.604591369628906,
+      "learning_rate": 2.912019826517968e-06,
+      "loss": 4.7498,
+      "step": 4910
+    },
+    {
+      "epoch": 18.25949953660797,
+      "grad_norm": 166.7299041748047,
+      "learning_rate": 2.8500619578686496e-06,
+      "loss": 4.9775,
+      "step": 4920
+    },
+    {
+      "epoch": 18.296570898980537,
+      "grad_norm": 151.07249450683594,
+      "learning_rate": 2.7881040892193307e-06,
+      "loss": 4.797,
+      "step": 4930
+    },
+    {
+      "epoch": 18.333642261353106,
+      "grad_norm": 169.59800720214844,
+      "learning_rate": 2.7261462205700125e-06,
+      "loss": 4.5694,
+      "step": 4940
+    },
+    {
+      "epoch": 18.37071362372567,
+      "grad_norm": 122.23992156982422,
+      "learning_rate": 2.6641883519206944e-06,
+      "loss": 4.6192,
+      "step": 4950
+    },
+    {
+      "epoch": 18.37071362372567,
+      "eval_loss": 3.6614646911621094,
+      "eval_runtime": 34.1096,
+      "eval_samples_per_second": 47.435,
+      "eval_steps_per_second": 6.802,
+      "step": 4950
+    },
+    {
+      "epoch": 18.40778498609824,
+      "grad_norm": 180.71498107910156,
+      "learning_rate": 2.6022304832713754e-06,
+      "loss": 5.8114,
+      "step": 4960
+    },
+    {
+      "epoch": 18.444856348470807,
+      "grad_norm": 214.1206512451172,
+      "learning_rate": 2.5402726146220572e-06,
+      "loss": 4.8035,
+      "step": 4970
+    },
+    {
+      "epoch": 18.481927710843372,
+      "grad_norm": 123.4474868774414,
+      "learning_rate": 2.4783147459727386e-06,
+      "loss": 4.6944,
+      "step": 4980
+    },
+    {
+      "epoch": 18.51899907321594,
+      "grad_norm": 107.80017852783203,
+      "learning_rate": 2.41635687732342e-06,
+      "loss": 4.8664,
+      "step": 4990
+    },
+    {
+      "epoch": 18.55607043558851,
+      "grad_norm": 229.9811248779297,
+      "learning_rate": 2.354399008674102e-06,
+      "loss": 4.6916,
+      "step": 5000
+    },
+    {
+      "epoch": 18.593141797961074,
+      "grad_norm": 147.27993774414062,
+      "learning_rate": 2.2924411400247833e-06,
+      "loss": 4.3352,
+      "step": 5010
+    },
+    {
+      "epoch": 18.630213160333643,
+      "grad_norm": 221.84120178222656,
+      "learning_rate": 2.2304832713754648e-06,
+      "loss": 5.9779,
+      "step": 5020
+    },
+    {
+      "epoch": 18.66728452270621,
+      "grad_norm": 205.40257263183594,
+      "learning_rate": 2.168525402726146e-06,
+      "loss": 4.7813,
+      "step": 5030
+    },
+    {
+      "epoch": 18.704355885078776,
+      "grad_norm": 112.90933227539062,
+      "learning_rate": 2.1065675340768276e-06,
+      "loss": 4.632,
+      "step": 5040
+    },
+    {
+      "epoch": 18.741427247451345,
+      "grad_norm": 191.73028564453125,
+      "learning_rate": 2.0446096654275095e-06,
+      "loss": 4.7411,
+      "step": 5050
+    },
+    {
+      "epoch": 18.77849860982391,
+      "grad_norm": 117.94806671142578,
+      "learning_rate": 1.982651796778191e-06,
+      "loss": 3.6489,
+      "step": 5060
+    },
+    {
+      "epoch": 18.815569972196478,
+      "grad_norm": 196.677978515625,
+      "learning_rate": 1.9206939281288723e-06,
+      "loss": 4.5373,
+      "step": 5070
+    },
+    {
+      "epoch": 18.852641334569046,
+      "grad_norm": 188.91744995117188,
+      "learning_rate": 1.858736059479554e-06,
+      "loss": 5.6129,
+      "step": 5080
+    },
+    {
+      "epoch": 18.88971269694161,
+      "grad_norm": 165.15834045410156,
+      "learning_rate": 1.7967781908302356e-06,
+      "loss": 4.8933,
+      "step": 5090
+    },
+    {
+      "epoch": 18.92678405931418,
+      "grad_norm": 209.0921173095703,
+      "learning_rate": 1.734820322180917e-06,
+      "loss": 4.27,
+      "step": 5100
+    },
+    {
+      "epoch": 18.92678405931418,
+      "eval_loss": 3.695683002471924,
+      "eval_runtime": 34.0964,
+      "eval_samples_per_second": 47.454,
+      "eval_steps_per_second": 6.804,
+      "step": 5100
+    },
+    {
+      "epoch": 18.96385542168675,
+      "grad_norm": 227.1733856201172,
+      "learning_rate": 1.6728624535315985e-06,
+      "loss": 4.5338,
+      "step": 5110
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 124.29000091552734,
+      "learning_rate": 1.6109045848822801e-06,
+      "loss": 5.5175,
+      "step": 5120
+    },
+    {
+      "epoch": 19.03707136237257,
+      "grad_norm": 266.28924560546875,
+      "learning_rate": 1.5489467162329615e-06,
+      "loss": 5.0835,
+      "step": 5130
+    },
+    {
+      "epoch": 19.074142724745133,
+      "grad_norm": 195.56568908691406,
+      "learning_rate": 1.4869888475836432e-06,
+      "loss": 4.6826,
+      "step": 5140
+    },
+    {
+      "epoch": 19.111214087117702,
+      "grad_norm": 194.1629638671875,
+      "learning_rate": 1.4250309789343248e-06,
+      "loss": 4.5391,
+      "step": 5150
+    },
+    {
+      "epoch": 19.14828544949027,
+      "grad_norm": 146.10855102539062,
+      "learning_rate": 1.3630731102850063e-06,
+      "loss": 5.3723,
+      "step": 5160
+    },
+    {
+      "epoch": 19.185356811862835,
+      "grad_norm": 233.69000244140625,
+      "learning_rate": 1.3011152416356877e-06,
+      "loss": 4.8095,
+      "step": 5170
+    },
+    {
+      "epoch": 19.222428174235404,
+      "grad_norm": 188.99301147460938,
+      "learning_rate": 1.2391573729863693e-06,
+      "loss": 4.7402,
+      "step": 5180
+    },
+    {
+      "epoch": 19.25949953660797,
+      "grad_norm": 151.8994598388672,
+      "learning_rate": 1.177199504337051e-06,
+      "loss": 4.0488,
+      "step": 5190
+    },
+    {
+      "epoch": 19.296570898980537,
+      "grad_norm": 202.1588134765625,
+      "learning_rate": 1.1152416356877324e-06,
+      "loss": 3.6424,
+      "step": 5200
+    },
+    {
+      "epoch": 19.333642261353106,
+      "grad_norm": 266.9206848144531,
+      "learning_rate": 1.0532837670384138e-06,
+      "loss": 4.2256,
+      "step": 5210
+    },
+    {
+      "epoch": 19.37071362372567,
+      "grad_norm": 171.10662841796875,
+      "learning_rate": 9.913258983890955e-07,
+      "loss": 4.4607,
+      "step": 5220
+    },
+    {
+      "epoch": 19.40778498609824,
+      "grad_norm": 90.18572998046875,
+      "learning_rate": 9.29368029739777e-07,
+      "loss": 3.5702,
+      "step": 5230
+    },
+    {
+      "epoch": 19.444856348470807,
+      "grad_norm": 199.90965270996094,
+      "learning_rate": 8.674101610904585e-07,
+      "loss": 4.3062,
+      "step": 5240
+    },
+    {
+      "epoch": 19.481927710843372,
+      "grad_norm": 185.57383728027344,
+      "learning_rate": 8.054522924411401e-07,
+      "loss": 4.2919,
+      "step": 5250
+    },
+    {
+      "epoch": 19.481927710843372,
+      "eval_loss": 3.659385919570923,
+      "eval_runtime": 34.0906,
+      "eval_samples_per_second": 47.462,
+      "eval_steps_per_second": 6.805,
+      "step": 5250
+    },
+    {
+      "epoch": 19.51899907321594,
+      "grad_norm": 167.98460388183594,
+      "learning_rate": 7.434944237918216e-07,
+      "loss": 4.6985,
+      "step": 5260
+    },
+    {
+      "epoch": 19.55607043558851,
+      "grad_norm": 200.6823272705078,
+      "learning_rate": 6.815365551425031e-07,
+      "loss": 4.6907,
+      "step": 5270
+    },
+    {
+      "epoch": 19.593141797961074,
+      "grad_norm": 154.13650512695312,
+      "learning_rate": 6.195786864931847e-07,
+      "loss": 4.3865,
+      "step": 5280
+    },
+    {
+      "epoch": 19.630213160333643,
+      "grad_norm": 132.1691131591797,
+      "learning_rate": 5.576208178438662e-07,
+      "loss": 3.9818,
+      "step": 5290
+    },
+    {
+      "epoch": 19.66728452270621,
+      "grad_norm": 144.57684326171875,
+      "learning_rate": 4.956629491945477e-07,
+      "loss": 4.3166,
+      "step": 5300
+    },
+    {
+      "epoch": 19.704355885078776,
+      "grad_norm": 180.27993774414062,
+      "learning_rate": 4.3370508054522926e-07,
+      "loss": 4.9131,
+      "step": 5310
+    },
+    {
+      "epoch": 19.741427247451345,
+      "grad_norm": 165.4918670654297,
+      "learning_rate": 3.717472118959108e-07,
+      "loss": 4.7641,
+      "step": 5320
+    },
+    {
+      "epoch": 19.77849860982391,
+      "grad_norm": 263.624755859375,
+      "learning_rate": 3.0978934324659233e-07,
+      "loss": 5.419,
+      "step": 5330
+    },
+    {
+      "epoch": 19.815569972196478,
+      "grad_norm": 142.11463928222656,
+      "learning_rate": 2.4783147459727386e-07,
+      "loss": 4.068,
+      "step": 5340
+    },
+    {
+      "epoch": 19.852641334569046,
+      "grad_norm": 225.3741912841797,
+      "learning_rate": 1.858736059479554e-07,
+      "loss": 4.1094,
+      "step": 5350
+    },
+    {
+      "epoch": 19.88971269694161,
+      "grad_norm": 246.1002655029297,
+      "learning_rate": 1.2391573729863693e-07,
+      "loss": 5.2279,
+      "step": 5360
+    },
+    {
+      "epoch": 19.92678405931418,
+      "grad_norm": 154.55587768554688,
+      "learning_rate": 6.195786864931847e-08,
+      "loss": 4.4818,
+      "step": 5370
+    },
+    {
+      "epoch": 19.96385542168675,
+      "grad_norm": 163.97137451171875,
+      "learning_rate": 0.0,
+      "loss": 4.3103,
+      "step": 5380
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5380,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 7,
+  "trial_name": null,
+  "trial_params": null
+}