{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9956108266276518,
  "eval_steps": 500,
  "global_step": 1023,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029261155815654718,
      "grad_norm": 2.817451946105921,
      "learning_rate": 5e-06,
      "loss": 0.7976,
      "step": 10
    },
    {
      "epoch": 0.058522311631309436,
      "grad_norm": 1.284434355820121,
      "learning_rate": 5e-06,
      "loss": 0.7389,
      "step": 20
    },
    {
      "epoch": 0.08778346744696415,
      "grad_norm": 1.2876126989168348,
      "learning_rate": 5e-06,
      "loss": 0.7071,
      "step": 30
    },
    {
      "epoch": 0.11704462326261887,
      "grad_norm": 1.094058121641866,
      "learning_rate": 5e-06,
      "loss": 0.6965,
      "step": 40
    },
    {
      "epoch": 0.14630577907827358,
      "grad_norm": 1.148621345747248,
      "learning_rate": 5e-06,
      "loss": 0.687,
      "step": 50
    },
    {
      "epoch": 0.1755669348939283,
      "grad_norm": 0.9050464163153896,
      "learning_rate": 5e-06,
      "loss": 0.6765,
      "step": 60
    },
    {
      "epoch": 0.20482809070958302,
      "grad_norm": 0.5948745622322165,
      "learning_rate": 5e-06,
      "loss": 0.6699,
      "step": 70
    },
    {
      "epoch": 0.23408924652523774,
      "grad_norm": 0.4179284598235861,
      "learning_rate": 5e-06,
      "loss": 0.6647,
      "step": 80
    },
    {
      "epoch": 0.26335040234089246,
      "grad_norm": 0.4320197149625007,
      "learning_rate": 5e-06,
      "loss": 0.6619,
      "step": 90
    },
    {
      "epoch": 0.29261155815654716,
      "grad_norm": 0.45765152029005024,
      "learning_rate": 5e-06,
      "loss": 0.6543,
      "step": 100
    },
    {
      "epoch": 0.3218727139722019,
      "grad_norm": 0.4044893755849006,
      "learning_rate": 5e-06,
      "loss": 0.6632,
      "step": 110
    },
    {
      "epoch": 0.3511338697878566,
      "grad_norm": 0.35821605431124326,
      "learning_rate": 5e-06,
      "loss": 0.668,
      "step": 120
    },
    {
      "epoch": 0.38039502560351135,
      "grad_norm": 0.3756878575578981,
      "learning_rate": 5e-06,
      "loss": 0.6518,
      "step": 130
    },
    {
      "epoch": 0.40965618141916604,
      "grad_norm": 0.3621384928557948,
      "learning_rate": 5e-06,
      "loss": 0.6525,
      "step": 140
    },
    {
      "epoch": 0.4389173372348208,
      "grad_norm": 0.3496185059505636,
      "learning_rate": 5e-06,
      "loss": 0.648,
      "step": 150
    },
    {
      "epoch": 0.4681784930504755,
      "grad_norm": 0.3872142083182003,
      "learning_rate": 5e-06,
      "loss": 0.6498,
      "step": 160
    },
    {
      "epoch": 0.49743964886613024,
      "grad_norm": 0.3658858276235106,
      "learning_rate": 5e-06,
      "loss": 0.6549,
      "step": 170
    },
    {
      "epoch": 0.5267008046817849,
      "grad_norm": 0.3357007312829614,
      "learning_rate": 5e-06,
      "loss": 0.6546,
      "step": 180
    },
    {
      "epoch": 0.5559619604974396,
      "grad_norm": 0.3562481959188732,
      "learning_rate": 5e-06,
      "loss": 0.6431,
      "step": 190
    },
    {
      "epoch": 0.5852231163130943,
      "grad_norm": 0.344934498132061,
      "learning_rate": 5e-06,
      "loss": 0.6443,
      "step": 200
    },
    {
      "epoch": 0.6144842721287491,
      "grad_norm": 0.34218669140197133,
      "learning_rate": 5e-06,
      "loss": 0.6509,
      "step": 210
    },
    {
      "epoch": 0.6437454279444038,
      "grad_norm": 0.35256592076055937,
      "learning_rate": 5e-06,
      "loss": 0.6389,
      "step": 220
    },
    {
      "epoch": 0.6730065837600585,
      "grad_norm": 0.36473082870109524,
      "learning_rate": 5e-06,
      "loss": 0.6388,
      "step": 230
    },
    {
      "epoch": 0.7022677395757132,
      "grad_norm": 0.3299100883057849,
      "learning_rate": 5e-06,
      "loss": 0.6456,
      "step": 240
    },
    {
      "epoch": 0.731528895391368,
      "grad_norm": 0.3416365052817771,
      "learning_rate": 5e-06,
      "loss": 0.644,
      "step": 250
    },
    {
      "epoch": 0.7607900512070227,
      "grad_norm": 0.34197703127811097,
      "learning_rate": 5e-06,
      "loss": 0.6466,
      "step": 260
    },
    {
      "epoch": 0.7900512070226774,
      "grad_norm": 0.37223452358809667,
      "learning_rate": 5e-06,
      "loss": 0.6489,
      "step": 270
    },
    {
      "epoch": 0.8193123628383321,
      "grad_norm": 0.33976179205185286,
      "learning_rate": 5e-06,
      "loss": 0.6477,
      "step": 280
    },
    {
      "epoch": 0.8485735186539868,
      "grad_norm": 0.3398894606792935,
      "learning_rate": 5e-06,
      "loss": 0.6399,
      "step": 290
    },
    {
      "epoch": 0.8778346744696416,
      "grad_norm": 0.3510531345907806,
      "learning_rate": 5e-06,
      "loss": 0.6318,
      "step": 300
    },
    {
      "epoch": 0.9070958302852963,
      "grad_norm": 0.3558397390544605,
      "learning_rate": 5e-06,
      "loss": 0.6449,
      "step": 310
    },
    {
      "epoch": 0.936356986100951,
      "grad_norm": 0.3356596511911474,
      "learning_rate": 5e-06,
      "loss": 0.6369,
      "step": 320
    },
    {
      "epoch": 0.9656181419166057,
      "grad_norm": 0.37733017841506045,
      "learning_rate": 5e-06,
      "loss": 0.6401,
      "step": 330
    },
    {
      "epoch": 0.9948792977322605,
      "grad_norm": 0.34951561267640846,
      "learning_rate": 5e-06,
      "loss": 0.6361,
      "step": 340
    },
    {
      "epoch": 0.9978054133138259,
      "eval_loss": 0.6406562924385071,
      "eval_runtime": 346.2688,
      "eval_samples_per_second": 26.595,
      "eval_steps_per_second": 0.416,
      "step": 341
    },
    {
      "epoch": 1.025237746891002,
      "grad_norm": 0.3690522380396755,
      "learning_rate": 5e-06,
      "loss": 0.6513,
      "step": 350
    },
    {
      "epoch": 1.054498902706657,
      "grad_norm": 0.34935298880477006,
      "learning_rate": 5e-06,
      "loss": 0.6055,
      "step": 360
    },
    {
      "epoch": 1.0837600585223117,
      "grad_norm": 0.4071561749341452,
      "learning_rate": 5e-06,
      "loss": 0.6089,
      "step": 370
    },
    {
      "epoch": 1.1130212143379663,
      "grad_norm": 0.3423935118081486,
      "learning_rate": 5e-06,
      "loss": 0.6063,
      "step": 380
    },
    {
      "epoch": 1.142282370153621,
      "grad_norm": 0.40033069734559046,
      "learning_rate": 5e-06,
      "loss": 0.6116,
      "step": 390
    },
    {
      "epoch": 1.1715435259692757,
      "grad_norm": 0.35662843692652024,
      "learning_rate": 5e-06,
      "loss": 0.613,
      "step": 400
    },
    {
      "epoch": 1.2008046817849305,
      "grad_norm": 0.3579810712341978,
      "learning_rate": 5e-06,
      "loss": 0.6127,
      "step": 410
    },
    {
      "epoch": 1.2300658376005853,
      "grad_norm": 0.4145283245344341,
      "learning_rate": 5e-06,
      "loss": 0.6009,
      "step": 420
    },
    {
      "epoch": 1.2593269934162399,
      "grad_norm": 0.3559214339096793,
      "learning_rate": 5e-06,
      "loss": 0.611,
      "step": 430
    },
    {
      "epoch": 1.2885881492318947,
      "grad_norm": 0.3413599580993331,
      "learning_rate": 5e-06,
      "loss": 0.6037,
      "step": 440
    },
    {
      "epoch": 1.3178493050475493,
      "grad_norm": 0.3622841783657278,
      "learning_rate": 5e-06,
      "loss": 0.6074,
      "step": 450
    },
    {
      "epoch": 1.347110460863204,
      "grad_norm": 0.3746581322669035,
      "learning_rate": 5e-06,
      "loss": 0.6051,
      "step": 460
    },
    {
      "epoch": 1.3763716166788589,
      "grad_norm": 0.31849740102906093,
      "learning_rate": 5e-06,
      "loss": 0.6024,
      "step": 470
    },
    {
      "epoch": 1.4056327724945135,
      "grad_norm": 0.3734761795611288,
      "learning_rate": 5e-06,
      "loss": 0.6033,
      "step": 480
    },
    {
      "epoch": 1.4348939283101683,
      "grad_norm": 0.34675275832571,
      "learning_rate": 5e-06,
      "loss": 0.6097,
      "step": 490
    },
    {
      "epoch": 1.464155084125823,
      "grad_norm": 0.33843498837923025,
      "learning_rate": 5e-06,
      "loss": 0.598,
      "step": 500
    },
    {
      "epoch": 1.4934162399414777,
      "grad_norm": 0.350146725219343,
      "learning_rate": 5e-06,
      "loss": 0.606,
      "step": 510
    },
    {
      "epoch": 1.5226773957571325,
      "grad_norm": 0.39166843083583675,
      "learning_rate": 5e-06,
      "loss": 0.6084,
      "step": 520
    },
    {
      "epoch": 1.5519385515727873,
      "grad_norm": 0.350003587462171,
      "learning_rate": 5e-06,
      "loss": 0.607,
      "step": 530
    },
    {
      "epoch": 1.5811997073884418,
      "grad_norm": 0.3667439111520098,
      "learning_rate": 5e-06,
      "loss": 0.6135,
      "step": 540
    },
    {
      "epoch": 1.6104608632040964,
      "grad_norm": 0.3537244934912836,
      "learning_rate": 5e-06,
      "loss": 0.6046,
      "step": 550
    },
    {
      "epoch": 1.6397220190197512,
      "grad_norm": 0.3530231160276065,
      "learning_rate": 5e-06,
      "loss": 0.6063,
      "step": 560
    },
    {
      "epoch": 1.668983174835406,
      "grad_norm": 0.323025619993113,
      "learning_rate": 5e-06,
      "loss": 0.5969,
      "step": 570
    },
    {
      "epoch": 1.6982443306510606,
      "grad_norm": 0.349358548931987,
      "learning_rate": 5e-06,
      "loss": 0.6062,
      "step": 580
    },
    {
      "epoch": 1.7275054864667154,
      "grad_norm": 0.39980408460241657,
      "learning_rate": 5e-06,
      "loss": 0.6065,
      "step": 590
    },
    {
      "epoch": 1.7567666422823702,
      "grad_norm": 0.34113313353194774,
      "learning_rate": 5e-06,
      "loss": 0.6033,
      "step": 600
    },
    {
      "epoch": 1.7860277980980248,
      "grad_norm": 0.34531388262994633,
      "learning_rate": 5e-06,
      "loss": 0.6058,
      "step": 610
    },
    {
      "epoch": 1.8152889539136796,
      "grad_norm": 0.32514799592510446,
      "learning_rate": 5e-06,
      "loss": 0.6062,
      "step": 620
    },
    {
      "epoch": 1.8445501097293344,
      "grad_norm": 0.35614080019739464,
      "learning_rate": 5e-06,
      "loss": 0.6053,
      "step": 630
    },
    {
      "epoch": 1.873811265544989,
      "grad_norm": 0.3300616433320744,
      "learning_rate": 5e-06,
      "loss": 0.6002,
      "step": 640
    },
    {
      "epoch": 1.9030724213606436,
      "grad_norm": 0.3622402238263096,
      "learning_rate": 5e-06,
      "loss": 0.6058,
      "step": 650
    },
    {
      "epoch": 1.9323335771762986,
      "grad_norm": 0.3444768451054272,
      "learning_rate": 5e-06,
      "loss": 0.6064,
      "step": 660
    },
    {
      "epoch": 1.9615947329919532,
      "grad_norm": 0.32853379599999255,
      "learning_rate": 5e-06,
      "loss": 0.5952,
      "step": 670
    },
    {
      "epoch": 1.9908558888076078,
      "grad_norm": 0.3587293884689086,
      "learning_rate": 5e-06,
      "loss": 0.6097,
      "step": 680
    },
    {
      "epoch": 1.9967081199707388,
      "eval_loss": 0.6332100629806519,
      "eval_runtime": 347.8152,
      "eval_samples_per_second": 26.477,
      "eval_steps_per_second": 0.414,
      "step": 682
    },
    {
      "epoch": 2.0212143379663496,
      "grad_norm": 0.3914747236499232,
      "learning_rate": 5e-06,
      "loss": 0.6197,
      "step": 690
    },
    {
      "epoch": 2.050475493782004,
      "grad_norm": 0.4451317704931522,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 700
    },
    {
      "epoch": 2.0797366495976592,
      "grad_norm": 0.35310727796985897,
      "learning_rate": 5e-06,
      "loss": 0.5694,
      "step": 710
    },
    {
      "epoch": 2.108997805413314,
      "grad_norm": 0.3748176044370228,
      "learning_rate": 5e-06,
      "loss": 0.5704,
      "step": 720
    },
    {
      "epoch": 2.1382589612289684,
      "grad_norm": 0.3494354561294143,
      "learning_rate": 5e-06,
      "loss": 0.5723,
      "step": 730
    },
    {
      "epoch": 2.1675201170446234,
      "grad_norm": 0.35129264971107693,
      "learning_rate": 5e-06,
      "loss": 0.5775,
      "step": 740
    },
    {
      "epoch": 2.196781272860278,
      "grad_norm": 0.31508074197114816,
      "learning_rate": 5e-06,
      "loss": 0.5763,
      "step": 750
    },
    {
      "epoch": 2.2260424286759326,
      "grad_norm": 0.3670643138923896,
      "learning_rate": 5e-06,
      "loss": 0.5737,
      "step": 760
    },
    {
      "epoch": 2.255303584491587,
      "grad_norm": 0.3304298759476488,
      "learning_rate": 5e-06,
      "loss": 0.5725,
      "step": 770
    },
    {
      "epoch": 2.284564740307242,
      "grad_norm": 0.3388699840011243,
      "learning_rate": 5e-06,
      "loss": 0.5716,
      "step": 780
    },
    {
      "epoch": 2.313825896122897,
      "grad_norm": 0.3280155833683051,
      "learning_rate": 5e-06,
      "loss": 0.5699,
      "step": 790
    },
    {
      "epoch": 2.3430870519385514,
      "grad_norm": 0.35970533064711685,
      "learning_rate": 5e-06,
      "loss": 0.5777,
      "step": 800
    },
    {
      "epoch": 2.3723482077542064,
      "grad_norm": 0.33656864947696286,
      "learning_rate": 5e-06,
      "loss": 0.5728,
      "step": 810
    },
    {
      "epoch": 2.401609363569861,
      "grad_norm": 0.33260691432954365,
      "learning_rate": 5e-06,
      "loss": 0.5791,
      "step": 820
    },
    {
      "epoch": 2.4308705193855156,
      "grad_norm": 0.3167221056111725,
      "learning_rate": 5e-06,
      "loss": 0.5714,
      "step": 830
    },
    {
      "epoch": 2.4601316752011706,
      "grad_norm": 0.3552708228986059,
      "learning_rate": 5e-06,
      "loss": 0.5719,
      "step": 840
    },
    {
      "epoch": 2.489392831016825,
      "grad_norm": 0.3504786037960249,
      "learning_rate": 5e-06,
      "loss": 0.5741,
      "step": 850
    },
    {
      "epoch": 2.5186539868324798,
      "grad_norm": 0.35601444454617853,
      "learning_rate": 5e-06,
      "loss": 0.5671,
      "step": 860
    },
    {
      "epoch": 2.547915142648135,
      "grad_norm": 0.3992627060706797,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 870
    },
    {
      "epoch": 2.5771762984637894,
      "grad_norm": 0.3511848795894042,
      "learning_rate": 5e-06,
      "loss": 0.5738,
      "step": 880
    },
    {
      "epoch": 2.606437454279444,
      "grad_norm": 0.3640553368412107,
      "learning_rate": 5e-06,
      "loss": 0.5731,
      "step": 890
    },
    {
      "epoch": 2.6356986100950985,
      "grad_norm": 0.3426464519086621,
      "learning_rate": 5e-06,
      "loss": 0.5777,
      "step": 900
    },
    {
      "epoch": 2.6649597659107536,
      "grad_norm": 0.3610877908075611,
      "learning_rate": 5e-06,
      "loss": 0.5778,
      "step": 910
    },
    {
      "epoch": 2.694220921726408,
      "grad_norm": 0.3556310393337805,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 920
    },
    {
      "epoch": 2.723482077542063,
      "grad_norm": 0.3504629693430583,
      "learning_rate": 5e-06,
      "loss": 0.5758,
      "step": 930
    },
    {
      "epoch": 2.7527432333577178,
      "grad_norm": 0.3486578461965166,
      "learning_rate": 5e-06,
      "loss": 0.5748,
      "step": 940
    },
    {
      "epoch": 2.7820043891733723,
      "grad_norm": 0.3422817889043645,
      "learning_rate": 5e-06,
      "loss": 0.5735,
      "step": 950
    },
    {
      "epoch": 2.811265544989027,
      "grad_norm": 0.37588989818519764,
      "learning_rate": 5e-06,
      "loss": 0.5774,
      "step": 960
    },
    {
      "epoch": 2.840526700804682,
      "grad_norm": 0.34577188011968074,
      "learning_rate": 5e-06,
      "loss": 0.5731,
      "step": 970
    },
    {
      "epoch": 2.8697878566203365,
      "grad_norm": 0.3788340529933626,
      "learning_rate": 5e-06,
      "loss": 0.5729,
      "step": 980
    },
    {
      "epoch": 2.899049012435991,
      "grad_norm": 0.3263212597720765,
      "learning_rate": 5e-06,
      "loss": 0.5659,
      "step": 990
    },
    {
      "epoch": 2.928310168251646,
      "grad_norm": 0.32654471141276226,
      "learning_rate": 5e-06,
      "loss": 0.5737,
      "step": 1000
    },
    {
      "epoch": 2.9575713240673007,
      "grad_norm": 0.350030993954914,
      "learning_rate": 5e-06,
      "loss": 0.5654,
      "step": 1010
    },
    {
      "epoch": 2.9868324798829553,
      "grad_norm": 0.33894932153015206,
      "learning_rate": 5e-06,
      "loss": 0.5771,
      "step": 1020
    },
    {
      "epoch": 2.9956108266276518,
      "eval_loss": 0.6330604553222656,
      "eval_runtime": 347.7245,
      "eval_samples_per_second": 26.484,
      "eval_steps_per_second": 0.414,
      "step": 1023
    },
    {
      "epoch": 2.9956108266276518,
      "step": 1023,
      "total_flos": 2144987064041472.0,
      "train_loss": 0.6141412728925837,
      "train_runtime": 55205.9507,
      "train_samples_per_second": 9.507,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 10,
  "max_steps": 1023,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2144987064041472.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}