{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "aux_loss": 8.045117378234863,
      "entropy": 0.05226727016270161,
      "epoch": 0.024096385542168676,
      "grad_norm": 0.5021907687187195,
      "learning_rate": 0.0,
      "loss": 0.09741637855768204,
      "mean_token_accuracy": 0.9888820052146912,
      "num_tokens": 154362.0,
      "step": 1
    },
    {
      "aux_loss": 8.047614574432373,
      "entropy": 0.05835266411304474,
      "epoch": 0.04819277108433735,
      "grad_norm": 0.551396369934082,
      "learning_rate": 1.4500000000000001e-07,
      "loss": 0.09991507232189178,
      "mean_token_accuracy": 0.9883801937103271,
      "num_tokens": 310702.0,
      "step": 2
    },
    {
      "aux_loss": 8.049727439880371,
      "entropy": 0.052583809942007065,
      "epoch": 0.07228915662650602,
      "grad_norm": 0.4750031530857086,
      "learning_rate": 2.9000000000000003e-07,
      "loss": 0.09806497395038605,
      "mean_token_accuracy": 0.9886206984519958,
      "num_tokens": 493904.0,
      "step": 3
    },
    {
      "aux_loss": 8.047826766967773,
      "entropy": 0.05231792479753494,
      "epoch": 0.0963855421686747,
      "grad_norm": 0.4863564074039459,
      "learning_rate": 4.35e-07,
      "loss": 0.09776315838098526,
      "mean_token_accuracy": 0.9888334274291992,
      "num_tokens": 663136.0,
      "step": 4
    },
    {
      "aux_loss": 8.047198295593262,
      "entropy": 0.04943128302693367,
      "epoch": 0.12048192771084337,
      "grad_norm": 0.5010114908218384,
      "learning_rate": 5.800000000000001e-07,
      "loss": 0.09543517231941223,
      "mean_token_accuracy": 0.9894405901432037,
      "num_tokens": 812532.0,
      "step": 5
    },
    {
      "aux_loss": 8.049106121063232,
      "entropy": 0.063042301684618,
      "epoch": 0.14457831325301204,
      "grad_norm": 0.5165722966194153,
      "learning_rate": 7.25e-07,
      "loss": 0.10346449911594391,
      "mean_token_accuracy": 0.987544983625412,
      "num_tokens": 973071.0,
      "step": 6
    },
    {
      "aux_loss": 8.047893047332764,
      "entropy": 0.0672433041036129,
      "epoch": 0.1686746987951807,
      "grad_norm": 0.5849524736404419,
      "learning_rate": 8.7e-07,
      "loss": 0.10626787692308426,
      "mean_token_accuracy": 0.9862557649612427,
      "num_tokens": 1110326.0,
      "step": 7
    },
    {
      "aux_loss": 8.04862642288208,
      "entropy": 0.06088166497647762,
      "epoch": 0.1927710843373494,
      "grad_norm": 0.48005586862564087,
      "learning_rate": 1.015e-06,
      "loss": 0.1021210104227066,
      "mean_token_accuracy": 0.9877255260944366,
      "num_tokens": 1259440.0,
      "step": 8
    },
    {
      "aux_loss": 8.047185897827148,
      "entropy": 0.049826065078377724,
      "epoch": 0.21686746987951808,
      "grad_norm": 0.43366947770118713,
      "learning_rate": 1.1600000000000001e-06,
      "loss": 0.09475715458393097,
      "mean_token_accuracy": 0.9898165464401245,
      "num_tokens": 1417756.0,
      "step": 9
    },
    {
      "aux_loss": 8.04772663116455,
      "entropy": 0.054957231506705284,
      "epoch": 0.24096385542168675,
      "grad_norm": 0.4529463052749634,
      "learning_rate": 1.3050000000000002e-06,
      "loss": 0.09896557033061981,
      "mean_token_accuracy": 0.9889253675937653,
      "num_tokens": 1579862.0,
      "step": 10
    },
    {
      "aux_loss": 8.047585487365723,
      "entropy": 0.05796742998063564,
      "epoch": 0.26506024096385544,
      "grad_norm": 0.45284125208854675,
      "learning_rate": 1.45e-06,
      "loss": 0.10001235455274582,
      "mean_token_accuracy": 0.9876790642738342,
      "num_tokens": 1731184.0,
      "step": 11
    },
    {
      "aux_loss": 8.04898738861084,
      "entropy": 0.05215233750641346,
      "epoch": 0.2891566265060241,
      "grad_norm": 0.4420299828052521,
      "learning_rate": 1.4499995904705798e-06,
      "loss": 0.09724222123622894,
      "mean_token_accuracy": 0.9884337782859802,
      "num_tokens": 1893932.0,
      "step": 12
    },
    {
      "aux_loss": 8.04798412322998,
      "entropy": 0.05265074409544468,
      "epoch": 0.3132530120481928,
      "grad_norm": 0.40204742550849915,
      "learning_rate": 1.4499983618832442e-06,
      "loss": 0.0970243290066719,
      "mean_token_accuracy": 0.989496260881424,
      "num_tokens": 2053005.0,
      "step": 13
    },
    {
      "aux_loss": 8.05030107498169,
      "entropy": 0.049178898334503174,
      "epoch": 0.3373493975903614,
      "grad_norm": 0.4108814597129822,
      "learning_rate": 1.4499963142407692e-06,
      "loss": 0.09499870240688324,
      "mean_token_accuracy": 0.9897345900535583,
      "num_tokens": 2217039.0,
      "step": 14
    },
    {
      "aux_loss": 8.046091079711914,
      "entropy": 0.0504351407289505,
      "epoch": 0.3614457831325301,
      "grad_norm": 0.4030505418777466,
      "learning_rate": 1.4499934475477814e-06,
      "loss": 0.09597203135490417,
      "mean_token_accuracy": 0.9898054599761963,
      "num_tokens": 2386769.0,
      "step": 15
    },
    {
      "aux_loss": 8.047934532165527,
      "entropy": 0.04648676887154579,
      "epoch": 0.3855421686746988,
      "grad_norm": 0.4123123586177826,
      "learning_rate": 1.4499897618107582e-06,
      "loss": 0.09345895051956177,
      "mean_token_accuracy": 0.989924967288971,
      "num_tokens": 2551093.0,
      "step": 16
    },
    {
      "aux_loss": 8.04793405532837,
      "entropy": 0.04946734011173248,
      "epoch": 0.40963855421686746,
      "grad_norm": 0.42739129066467285,
      "learning_rate": 1.4499852570380272e-06,
      "loss": 0.09633760154247284,
      "mean_token_accuracy": 0.9889810979366302,
      "num_tokens": 2704860.0,
      "step": 17
    },
    {
      "aux_loss": 8.048253536224365,
      "entropy": 0.0546275470405817,
      "epoch": 0.43373493975903615,
      "grad_norm": 0.44881728291511536,
      "learning_rate": 1.449979933239767e-06,
      "loss": 0.09820500761270523,
      "mean_token_accuracy": 0.9885384142398834,
      "num_tokens": 2850860.0,
      "step": 18
    },
    {
      "aux_loss": 8.050773620605469,
      "entropy": 0.05041976273059845,
      "epoch": 0.4578313253012048,
      "grad_norm": 0.46621593832969666,
      "learning_rate": 1.4499737904280063e-06,
      "loss": 0.09671641141176224,
      "mean_token_accuracy": 0.9887768924236298,
      "num_tokens": 3039323.0,
      "step": 19
    },
    {
      "aux_loss": 8.050614356994629,
      "entropy": 0.050554944202303886,
      "epoch": 0.4819277108433735,
      "grad_norm": 0.47147253155708313,
      "learning_rate": 1.449966828616625e-06,
      "loss": 0.09628961980342865,
      "mean_token_accuracy": 0.9888468682765961,
      "num_tokens": 3195488.0,
      "step": 20
    },
    {
      "aux_loss": 8.050609111785889,
      "entropy": 0.04489951767027378,
      "epoch": 0.5060240963855421,
      "grad_norm": 0.4890425503253937,
      "learning_rate": 1.4499590478213525e-06,
      "loss": 0.09394823014736176,
      "mean_token_accuracy": 0.9896246194839478,
      "num_tokens": 3369627.0,
      "step": 21
    },
    {
      "aux_loss": 8.047994613647461,
      "entropy": 0.0530005544424057,
      "epoch": 0.5301204819277109,
      "grad_norm": 0.5181686878204346,
      "learning_rate": 1.4499504480597702e-06,
      "loss": 0.09846185147762299,
      "mean_token_accuracy": 0.9879846572875977,
      "num_tokens": 3520643.0,
      "step": 22
    },
    {
      "aux_loss": 8.049047946929932,
      "entropy": 0.039870962500572205,
      "epoch": 0.5542168674698795,
      "grad_norm": 0.41603270173072815,
      "learning_rate": 1.4499410293513081e-06,
      "loss": 0.09075028449296951,
      "mean_token_accuracy": 0.9908623099327087,
      "num_tokens": 3702510.0,
      "step": 23
    },
    {
      "aux_loss": 8.050177097320557,
      "entropy": 0.05053388141095638,
      "epoch": 0.5783132530120482,
      "grad_norm": 0.4234795570373535,
      "learning_rate": 1.449930791717248e-06,
      "loss": 0.09689382463693619,
      "mean_token_accuracy": 0.9886369109153748,
      "num_tokens": 3867610.0,
      "step": 24
    },
    {
      "aux_loss": 8.048462867736816,
      "entropy": 0.049235520884394646,
      "epoch": 0.6024096385542169,
      "grad_norm": 0.4375890791416168,
      "learning_rate": 1.4499197351807219e-06,
      "loss": 0.09504671394824982,
      "mean_token_accuracy": 0.9891063868999481,
      "num_tokens": 4021186.0,
      "step": 25
    },
    {
      "aux_loss": 8.050186157226562,
      "entropy": 0.048021236434578896,
      "epoch": 0.6265060240963856,
      "grad_norm": 0.42389488220214844,
      "learning_rate": 1.449907859766711e-06,
      "loss": 0.09462042152881622,
      "mean_token_accuracy": 0.9893973469734192,
      "num_tokens": 4183102.0,
      "step": 26
    },
    {
      "aux_loss": 8.04945182800293,
      "entropy": 0.042689668014645576,
      "epoch": 0.6506024096385542,
      "grad_norm": 0.40038207173347473,
      "learning_rate": 1.4498951655020479e-06,
      "loss": 0.09214234352111816,
      "mean_token_accuracy": 0.9904394745826721,
      "num_tokens": 4348628.0,
      "step": 27
    },
    {
      "aux_loss": 8.050597667694092,
      "entropy": 0.05143065005540848,
      "epoch": 0.6746987951807228,
      "grad_norm": 0.4422961473464966,
      "learning_rate": 1.4498816524154148e-06,
      "loss": 0.09722501039505005,
      "mean_token_accuracy": 0.9888282418251038,
      "num_tokens": 4511217.0,
      "step": 28
    },
    {
      "aux_loss": 8.048704147338867,
      "entropy": 0.044764744117856026,
      "epoch": 0.6987951807228916,
      "grad_norm": 0.4279940128326416,
      "learning_rate": 1.4498673205373443e-06,
      "loss": 0.09300120174884796,
      "mean_token_accuracy": 0.9899511337280273,
      "num_tokens": 4684266.0,
      "step": 29
    },
    {
      "aux_loss": 8.047113418579102,
      "entropy": 0.04995520040392876,
      "epoch": 0.7228915662650602,
      "grad_norm": 0.45497408509254456,
      "learning_rate": 1.4498521699002187e-06,
      "loss": 0.0966445729136467,
      "mean_token_accuracy": 0.9883378744125366,
      "num_tokens": 4858009.0,
      "step": 30
    },
    {
      "aux_loss": 8.050236701965332,
      "entropy": 0.04773502238094807,
      "epoch": 0.7469879518072289,
      "grad_norm": 0.40059739351272583,
      "learning_rate": 1.4498362005382707e-06,
      "loss": 0.09425598382949829,
      "mean_token_accuracy": 0.9895853698253632,
      "num_tokens": 5041560.0,
      "step": 31
    },
    {
      "aux_loss": 8.0483078956604,
      "entropy": 0.04463958367705345,
      "epoch": 0.7710843373493976,
      "grad_norm": 0.421403706073761,
      "learning_rate": 1.4498194124875822e-06,
      "loss": 0.0921817421913147,
      "mean_token_accuracy": 0.9903146624565125,
      "num_tokens": 5207925.0,
      "step": 32
    },
    {
      "aux_loss": 8.051517486572266,
      "entropy": 0.0455746091902256,
      "epoch": 0.7951807228915663,
      "grad_norm": 0.39467114210128784,
      "learning_rate": 1.449801805786086e-06,
      "loss": 0.09311801195144653,
      "mean_token_accuracy": 0.9897293448448181,
      "num_tokens": 5410900.0,
      "step": 33
    },
    {
      "aux_loss": 8.047285079956055,
      "entropy": 0.04475598596036434,
      "epoch": 0.8192771084337349,
      "grad_norm": 0.3885505795478821,
      "learning_rate": 1.4497833804735631e-06,
      "loss": 0.09283807128667831,
      "mean_token_accuracy": 0.9904457926750183,
      "num_tokens": 5579379.0,
      "step": 34
    },
    {
      "aux_loss": 8.049206733703613,
      "entropy": 0.045768845826387405,
      "epoch": 0.8433734939759037,
      "grad_norm": 0.38822969794273376,
      "learning_rate": 1.4497641365916457e-06,
      "loss": 0.0930660218000412,
      "mean_token_accuracy": 0.9898505806922913,
      "num_tokens": 5756181.0,
      "step": 35
    },
    {
      "aux_loss": 8.049548149108887,
      "entropy": 0.0442772526293993,
      "epoch": 0.8674698795180723,
      "grad_norm": 0.42765918374061584,
      "learning_rate": 1.4497440741838147e-06,
      "loss": 0.09213966131210327,
      "mean_token_accuracy": 0.9906859695911407,
      "num_tokens": 5913888.0,
      "step": 36
    },
    {
      "aux_loss": 8.047310829162598,
      "entropy": 0.05137152969837189,
      "epoch": 0.891566265060241,
      "grad_norm": 0.46749433875083923,
      "learning_rate": 1.4497231932954002e-06,
      "loss": 0.09635019302368164,
      "mean_token_accuracy": 0.9894134104251862,
      "num_tokens": 6073822.0,
      "step": 37
    },
    {
      "aux_loss": 8.04575777053833,
      "entropy": 0.04952680319547653,
      "epoch": 0.9156626506024096,
      "grad_norm": 0.40102288126945496,
      "learning_rate": 1.4497014939735825e-06,
      "loss": 0.09520888328552246,
      "mean_token_accuracy": 0.9900149703025818,
      "num_tokens": 6228998.0,
      "step": 38
    },
    {
      "aux_loss": 8.05048656463623,
      "entropy": 0.05141362361609936,
      "epoch": 0.9397590361445783,
      "grad_norm": 0.45891159772872925,
      "learning_rate": 1.4496789762673903e-06,
      "loss": 0.09608915448188782,
      "mean_token_accuracy": 0.9895050525665283,
      "num_tokens": 6380479.0,
      "step": 39
    },
    {
      "aux_loss": 8.049390316009521,
      "entropy": 0.0542642492800951,
      "epoch": 0.963855421686747,
      "grad_norm": 0.4678654968738556,
      "learning_rate": 1.4496556402277018e-06,
      "loss": 0.0986521765589714,
      "mean_token_accuracy": 0.9882148206233978,
      "num_tokens": 6514347.0,
      "step": 40
    },
    {
      "aux_loss": 8.047286033630371,
      "entropy": 0.04129311256110668,
      "epoch": 0.9879518072289156,
      "grad_norm": 0.42529988288879395,
      "learning_rate": 1.4496314859072443e-06,
      "loss": 0.09138549864292145,
      "mean_token_accuracy": 0.9908298254013062,
      "num_tokens": 6684739.0,
      "step": 41
    },
    {
      "aux_loss": 8.050637245178223,
      "entropy": 0.04988313093781471,
      "epoch": 1.0,
      "grad_norm": 0.5628013610839844,
      "learning_rate": 1.4496065133605937e-06,
      "loss": 0.06163128837943077,
      "mean_token_accuracy": 0.9887231588363647,
      "num_tokens": 6741463.0,
      "step": 42
    }
  ],
  "logging_steps": 1,
  "max_steps": 2100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "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": 1.3965576798533059e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}