{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7278761061946902,
  "eval_steps": 500,
  "global_step": 329,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011061946902654867,
      "grad_norm": 13.461091995239258,
      "learning_rate": 2.162496240601504e-06,
      "loss": 0.4134,
      "mean_token_accuracy": 0.8850920587778092,
      "num_tokens": 846838.0,
      "step": 5
    },
    {
      "epoch": 0.022123893805309734,
      "grad_norm": 2.7622671127319336,
      "learning_rate": 4.865616541353383e-06,
      "loss": 0.2508,
      "mean_token_accuracy": 0.9402594447135926,
      "num_tokens": 1682073.0,
      "step": 10
    },
    {
      "epoch": 0.033185840707964605,
      "grad_norm": 1.2914806604385376,
      "learning_rate": 7.568736842105265e-06,
      "loss": 0.1746,
      "mean_token_accuracy": 0.9484462857246398,
      "num_tokens": 2529190.0,
      "step": 15
    },
    {
      "epoch": 0.04424778761061947,
      "grad_norm": 0.9317694306373596,
      "learning_rate": 1.0271857142857143e-05,
      "loss": 0.1495,
      "mean_token_accuracy": 0.9573983639478684,
      "num_tokens": 3375960.0,
      "step": 20
    },
    {
      "epoch": 0.05530973451327434,
      "grad_norm": 0.9030012488365173,
      "learning_rate": 1.2974977443609024e-05,
      "loss": 0.1506,
      "mean_token_accuracy": 0.9576296597719193,
      "num_tokens": 4213632.0,
      "step": 25
    },
    {
      "epoch": 0.06637168141592921,
      "grad_norm": 0.9992048144340515,
      "learning_rate": 1.5678097744360906e-05,
      "loss": 0.1514,
      "mean_token_accuracy": 0.9582346022129059,
      "num_tokens": 5059314.0,
      "step": 30
    },
    {
      "epoch": 0.07743362831858407,
      "grad_norm": 0.7621418237686157,
      "learning_rate": 1.8381218045112784e-05,
      "loss": 0.1271,
      "mean_token_accuracy": 0.9617503315210343,
      "num_tokens": 5896932.0,
      "step": 35
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 1.0772463083267212,
      "learning_rate": 1.8918604941067526e-05,
      "loss": 0.1272,
      "mean_token_accuracy": 0.9630205810070038,
      "num_tokens": 6751111.0,
      "step": 40
    },
    {
      "epoch": 0.09955752212389381,
      "grad_norm": 0.878653883934021,
      "learning_rate": 1.8905459023589886e-05,
      "loss": 0.1491,
      "mean_token_accuracy": 0.9587506353855133,
      "num_tokens": 7592572.0,
      "step": 45
    },
    {
      "epoch": 0.11061946902654868,
      "grad_norm": 0.8564369082450867,
      "learning_rate": 1.8882220756628106e-05,
      "loss": 0.1431,
      "mean_token_accuracy": 0.9584101676940918,
      "num_tokens": 8427957.0,
      "step": 50
    },
    {
      "epoch": 0.12168141592920353,
      "grad_norm": 1.0373573303222656,
      "learning_rate": 1.8848923268945807e-05,
      "loss": 0.1382,
      "mean_token_accuracy": 0.9592803955078125,
      "num_tokens": 9277999.0,
      "step": 55
    },
    {
      "epoch": 0.13274336283185842,
      "grad_norm": 0.8327059745788574,
      "learning_rate": 1.8805614029857285e-05,
      "loss": 0.1205,
      "mean_token_accuracy": 0.9648381650447846,
      "num_tokens": 10121798.0,
      "step": 60
    },
    {
      "epoch": 0.14380530973451328,
      "grad_norm": 0.8707285523414612,
      "learning_rate": 1.8752354781554696e-05,
      "loss": 0.131,
      "mean_token_accuracy": 0.9600728780031205,
      "num_tokens": 10968515.0,
      "step": 65
    },
    {
      "epoch": 0.15486725663716813,
      "grad_norm": 0.64393550157547,
      "learning_rate": 1.8689221451087584e-05,
      "loss": 0.1271,
      "mean_token_accuracy": 0.9621491193771362,
      "num_tokens": 11806719.0,
      "step": 70
    },
    {
      "epoch": 0.16592920353982302,
      "grad_norm": 0.6001170873641968,
      "learning_rate": 1.8616304042120364e-05,
      "loss": 0.1158,
      "mean_token_accuracy": 0.965711510181427,
      "num_tokens": 12652845.0,
      "step": 75
    },
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 0.8036424517631531,
      "learning_rate": 1.8533706506621947e-05,
      "loss": 0.1282,
      "mean_token_accuracy": 0.9618031561374665,
      "num_tokens": 13502885.0,
      "step": 80
    },
    {
      "epoch": 0.18805309734513273,
      "grad_norm": 0.8204980492591858,
      "learning_rate": 1.8441546596670535e-05,
      "loss": 0.1324,
      "mean_token_accuracy": 0.9598487824201584,
      "num_tokens": 14350146.0,
      "step": 85
    },
    {
      "epoch": 0.19911504424778761,
      "grad_norm": 0.6891230940818787,
      "learning_rate": 1.8339955696584762e-05,
      "loss": 0.1399,
      "mean_token_accuracy": 0.9580721437931061,
      "num_tokens": 15184916.0,
      "step": 90
    },
    {
      "epoch": 0.21017699115044247,
      "grad_norm": 0.6431946754455566,
      "learning_rate": 1.8229078635620596e-05,
      "loss": 0.1409,
      "mean_token_accuracy": 0.9597247928380966,
      "num_tokens": 16029524.0,
      "step": 95
    },
    {
      "epoch": 0.22123893805309736,
      "grad_norm": 0.6083735823631287,
      "learning_rate": 1.810907348150093e-05,
      "loss": 0.1203,
      "mean_token_accuracy": 0.9644614964723587,
      "num_tokens": 16864801.0,
      "step": 100
    },
    {
      "epoch": 0.2323008849557522,
      "grad_norm": 0.6242711544036865,
      "learning_rate": 1.7980111315072266e-05,
      "loss": 0.1248,
      "mean_token_accuracy": 0.9646881937980651,
      "num_tokens": 17708413.0,
      "step": 105
    },
    {
      "epoch": 0.24336283185840707,
      "grad_norm": 0.73357093334198,
      "learning_rate": 1.7842375986409714e-05,
      "loss": 0.1208,
      "mean_token_accuracy": 0.9634551048278809,
      "num_tokens": 18544637.0,
      "step": 110
    },
    {
      "epoch": 0.25442477876106195,
      "grad_norm": 1.324249267578125,
      "learning_rate": 1.7696063852718036e-05,
      "loss": 0.1402,
      "mean_token_accuracy": 0.9579836875200272,
      "num_tokens": 19384925.0,
      "step": 115
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": 0.6341578960418701,
      "learning_rate": 1.754138349840237e-05,
      "loss": 0.1293,
      "mean_token_accuracy": 0.9616625785827637,
      "num_tokens": 20226562.0,
      "step": 120
    },
    {
      "epoch": 0.27654867256637167,
      "grad_norm": 0.40425291657447815,
      "learning_rate": 1.7378555437707684e-05,
      "loss": 0.1047,
      "mean_token_accuracy": 0.9698164403438568,
      "num_tokens": 21062753.0,
      "step": 125
    },
    {
      "epoch": 0.28761061946902655,
      "grad_norm": 0.5786776542663574,
      "learning_rate": 1.7207811800350917e-05,
      "loss": 0.1071,
      "mean_token_accuracy": 0.9678044021129608,
      "num_tokens": 21910336.0,
      "step": 130
    },
    {
      "epoch": 0.29867256637168144,
      "grad_norm": 0.6888148188591003,
      "learning_rate": 1.702939600059396e-05,
      "loss": 0.136,
      "mean_token_accuracy": 0.962011530995369,
      "num_tokens": 22742905.0,
      "step": 135
    },
    {
      "epoch": 0.30973451327433627,
      "grad_norm": 0.5954065918922424,
      "learning_rate": 1.6843562390229243e-05,
      "loss": 0.1279,
      "mean_token_accuracy": 0.9627850383520127,
      "num_tokens": 23597974.0,
      "step": 140
    },
    {
      "epoch": 0.32079646017699115,
      "grad_norm": 0.5564700365066528,
      "learning_rate": 1.6650575895972645e-05,
      "loss": 0.1267,
      "mean_token_accuracy": 0.9612752169370651,
      "num_tokens": 24440526.0,
      "step": 145
    },
    {
      "epoch": 0.33185840707964603,
      "grad_norm": 0.7850887775421143,
      "learning_rate": 1.645071164178065e-05,
      "loss": 0.1187,
      "mean_token_accuracy": 0.9634008407592773,
      "num_tokens": 25282642.0,
      "step": 150
    },
    {
      "epoch": 0.34292035398230086,
      "grad_norm": 0.5256094336509705,
      "learning_rate": 1.624425455663021e-05,
      "loss": 0.1067,
      "mean_token_accuracy": 0.9682290345430374,
      "num_tokens": 26136259.0,
      "step": 155
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.6862473487854004,
      "learning_rate": 1.603149896832042e-05,
      "loss": 0.1108,
      "mean_token_accuracy": 0.9675305336713791,
      "num_tokens": 26982185.0,
      "step": 160
    },
    {
      "epoch": 0.36504424778761063,
      "grad_norm": 0.4837939143180847,
      "learning_rate": 1.581274818387516e-05,
      "loss": 0.1079,
      "mean_token_accuracy": 0.9676101803779602,
      "num_tokens": 27827244.0,
      "step": 165
    },
    {
      "epoch": 0.37610619469026546,
      "grad_norm": 0.5552247762680054,
      "learning_rate": 1.5588314057144782e-05,
      "loss": 0.1144,
      "mean_token_accuracy": 0.964342150092125,
      "num_tokens": 28660382.0,
      "step": 170
    },
    {
      "epoch": 0.38716814159292035,
      "grad_norm": 0.5585025548934937,
      "learning_rate": 1.5358516544223398e-05,
      "loss": 0.1256,
      "mean_token_accuracy": 0.9610821902751923,
      "num_tokens": 29527541.0,
      "step": 175
    },
    {
      "epoch": 0.39823008849557523,
      "grad_norm": 0.4463709592819214,
      "learning_rate": 1.5123683247315437e-05,
      "loss": 0.1085,
      "mean_token_accuracy": 0.9661611169576645,
      "num_tokens": 30384680.0,
      "step": 180
    },
    {
      "epoch": 0.4092920353982301,
      "grad_norm": 0.5831905603408813,
      "learning_rate": 1.4884148947701893e-05,
      "loss": 0.117,
      "mean_token_accuracy": 0.9654515415430069,
      "num_tokens": 31228614.0,
      "step": 185
    },
    {
      "epoch": 0.42035398230088494,
      "grad_norm": 0.4131219983100891,
      "learning_rate": 1.4640255128471913e-05,
      "loss": 0.1186,
      "mean_token_accuracy": 0.9669954717159271,
      "num_tokens": 32080556.0,
      "step": 190
    },
    {
      "epoch": 0.4314159292035398,
      "grad_norm": 0.3618049919605255,
      "learning_rate": 1.4392349487700268e-05,
      "loss": 0.13,
      "mean_token_accuracy": 0.9625168412923812,
      "num_tokens": 32925476.0,
      "step": 195
    },
    {
      "epoch": 0.4424778761061947,
      "grad_norm": 0.4708753228187561,
      "learning_rate": 1.4140785442764624e-05,
      "loss": 0.1394,
      "mean_token_accuracy": 0.9613620102405548,
      "num_tokens": 33767036.0,
      "step": 200
    },
    {
      "epoch": 0.45353982300884954,
      "grad_norm": 0.5939691066741943,
      "learning_rate": 1.3885921626509305e-05,
      "loss": 0.1179,
      "mean_token_accuracy": 0.964636293053627,
      "num_tokens": 34611445.0,
      "step": 205
    },
    {
      "epoch": 0.4646017699115044,
      "grad_norm": 0.46983635425567627,
      "learning_rate": 1.362812137597385e-05,
      "loss": 0.1224,
      "mean_token_accuracy": 0.9625515252351761,
      "num_tokens": 35447156.0,
      "step": 210
    },
    {
      "epoch": 0.4756637168141593,
      "grad_norm": 0.6745828986167908,
      "learning_rate": 1.3367752214415174e-05,
      "loss": 0.1445,
      "mean_token_accuracy": 0.9614503085613251,
      "num_tokens": 36288301.0,
      "step": 215
    },
    {
      "epoch": 0.48672566371681414,
      "grad_norm": 0.8108320832252502,
      "learning_rate": 1.3105185327361837e-05,
      "loss": 0.1285,
      "mean_token_accuracy": 0.9619213432073593,
      "num_tokens": 37132678.0,
      "step": 220
    },
    {
      "epoch": 0.497787610619469,
      "grad_norm": 0.46032506227493286,
      "learning_rate": 1.284079503344731e-05,
      "loss": 0.1091,
      "mean_token_accuracy": 0.9660203218460083,
      "num_tokens": 37967586.0,
      "step": 225
    },
    {
      "epoch": 0.5088495575221239,
      "grad_norm": 0.6448680758476257,
      "learning_rate": 1.2574958250776656e-05,
      "loss": 0.1096,
      "mean_token_accuracy": 0.9665733218193054,
      "num_tokens": 38811748.0,
      "step": 230
    },
    {
      "epoch": 0.5199115044247787,
      "grad_norm": 0.5390487313270569,
      "learning_rate": 1.230805395958738e-05,
      "loss": 0.1151,
      "mean_token_accuracy": 0.9652928560972214,
      "num_tokens": 39657513.0,
      "step": 235
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 0.7396034598350525,
      "learning_rate": 1.204046266197046e-05,
      "loss": 0.1047,
      "mean_token_accuracy": 0.9676766693592072,
      "num_tokens": 40480394.0,
      "step": 240
    },
    {
      "epoch": 0.5420353982300885,
      "grad_norm": 0.5048537850379944,
      "learning_rate": 1.1772565839421815e-05,
      "loss": 0.1191,
      "mean_token_accuracy": 0.9638701856136322,
      "num_tokens": 41333513.0,
      "step": 245
    },
    {
      "epoch": 0.5530973451327433,
      "grad_norm": 0.5635956525802612,
      "learning_rate": 1.150474540899753e-05,
      "loss": 0.129,
      "mean_token_accuracy": 0.9641528844833374,
      "num_tokens": 42176314.0,
      "step": 250
    },
    {
      "epoch": 0.5641592920353983,
      "grad_norm": 0.6472644805908203,
      "learning_rate": 1.1237383178848112e-05,
      "loss": 0.1163,
      "mean_token_accuracy": 0.9671437740325928,
      "num_tokens": 43033840.0,
      "step": 255
    },
    {
      "epoch": 0.5752212389380531,
      "grad_norm": 0.5855692625045776,
      "learning_rate": 1.0970860303908045e-05,
      "loss": 0.1136,
      "mean_token_accuracy": 0.9656757831573486,
      "num_tokens": 43860660.0,
      "step": 260
    },
    {
      "epoch": 0.5862831858407079,
      "grad_norm": 0.503114640712738,
      "learning_rate": 1.0705556742516538e-05,
      "loss": 0.097,
      "mean_token_accuracy": 0.9691111803054809,
      "num_tokens": 44705721.0,
      "step": 265
    },
    {
      "epoch": 0.5973451327433629,
      "grad_norm": 0.6158783435821533,
      "learning_rate": 1.0441850714744179e-05,
      "loss": 0.129,
      "mean_token_accuracy": 0.961165776848793,
      "num_tokens": 45558134.0,
      "step": 270
    },
    {
      "epoch": 0.6084070796460177,
      "grad_norm": 0.5727131366729736,
      "learning_rate": 1.0180118163197672e-05,
      "loss": 0.1176,
      "mean_token_accuracy": 0.9660899013280868,
      "num_tokens": 46410748.0,
      "step": 275
    },
    {
      "epoch": 0.6194690265486725,
      "grad_norm": 0.5033449530601501,
      "learning_rate": 9.920732217071372e-06,
      "loss": 0.1062,
      "mean_token_accuracy": 0.96670863032341,
      "num_tokens": 47255205.0,
      "step": 280
    },
    {
      "epoch": 0.6305309734513275,
      "grad_norm": 0.4222841262817383,
      "learning_rate": 9.664062660209635e-06,
      "loss": 0.1028,
      "mean_token_accuracy": 0.9677979677915574,
      "num_tokens": 48104541.0,
      "step": 285
    },
    {
      "epoch": 0.6415929203539823,
      "grad_norm": 0.667140007019043,
      "learning_rate": 9.410475403938355e-06,
      "loss": 0.1245,
      "mean_token_accuracy": 0.9632324069738388,
      "num_tokens": 48938330.0,
      "step": 290
    },
    {
      "epoch": 0.6526548672566371,
      "grad_norm": 0.3784688711166382,
      "learning_rate": 9.160331965417215e-06,
      "loss": 0.1092,
      "mean_token_accuracy": 0.9666803032159805,
      "num_tokens": 49782057.0,
      "step": 295
    },
    {
      "epoch": 0.6637168141592921,
      "grad_norm": 0.4222528040409088,
      "learning_rate": 8.913988952256295e-06,
      "loss": 0.0974,
      "mean_token_accuracy": 0.9699580252170563,
      "num_tokens": 50631025.0,
      "step": 300
    },
    {
      "epoch": 0.6747787610619469,
      "grad_norm": 0.3361203372478485,
      "learning_rate": 8.671797554131816e-06,
      "loss": 0.1003,
      "mean_token_accuracy": 0.9684587985277175,
      "num_tokens": 51467651.0,
      "step": 305
    },
    {
      "epoch": 0.6858407079646017,
      "grad_norm": 0.534888505935669,
      "learning_rate": 8.43410304212576e-06,
      "loss": 0.1228,
      "mean_token_accuracy": 0.9649948716163635,
      "num_tokens": 52309897.0,
      "step": 310
    },
    {
      "epoch": 0.6969026548672567,
      "grad_norm": 0.5749210715293884,
      "learning_rate": 8.201244276503093e-06,
      "loss": 0.1103,
      "mean_token_accuracy": 0.9665466219186782,
      "num_tokens": 53142689.0,
      "step": 315
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.525931715965271,
      "learning_rate": 7.97355322362833e-06,
      "loss": 0.1102,
      "mean_token_accuracy": 0.9656654626131058,
      "num_tokens": 53991586.0,
      "step": 320
    },
    {
      "epoch": 0.7190265486725663,
      "grad_norm": 0.6085832715034485,
      "learning_rate": 7.751354482710171e-06,
      "loss": 0.106,
      "mean_token_accuracy": 0.9676532536745072,
      "num_tokens": 54843276.0,
      "step": 325
    }
  ],
  "logging_steps": 5,
  "max_steps": 451,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.309949686630056e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}