{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9065155807365439,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0113314447592068,
      "grad_norm": 2.122056007385254,
      "learning_rate": 2.247191011235955e-06,
      "loss": 0.9897969245910645,
      "step": 5
    },
    {
      "epoch": 0.0226628895184136,
      "grad_norm": 17.6800594329834,
      "learning_rate": 5.056179775280899e-06,
      "loss": 1.0432443618774414,
      "step": 10
    },
    {
      "epoch": 0.0339943342776204,
      "grad_norm": 2.0127477645874023,
      "learning_rate": 7.865168539325843e-06,
      "loss": 0.8075703620910645,
      "step": 15
    },
    {
      "epoch": 0.0453257790368272,
      "grad_norm": 1.3711857795715332,
      "learning_rate": 1.0674157303370787e-05,
      "loss": 0.8119368553161621,
      "step": 20
    },
    {
      "epoch": 0.056657223796033995,
      "grad_norm": 2.0571818351745605,
      "learning_rate": 1.348314606741573e-05,
      "loss": 0.7943171501159668,
      "step": 25
    },
    {
      "epoch": 0.0679886685552408,
      "grad_norm": 1.2746798992156982,
      "learning_rate": 1.6292134831460676e-05,
      "loss": 0.6019079685211182,
      "step": 30
    },
    {
      "epoch": 0.07932011331444759,
      "grad_norm": 0.8943267464637756,
      "learning_rate": 1.9101123595505618e-05,
      "loss": 0.5811184406280517,
      "step": 35
    },
    {
      "epoch": 0.0906515580736544,
      "grad_norm": 0.974899172782898,
      "learning_rate": 2.1910112359550563e-05,
      "loss": 0.4773231029510498,
      "step": 40
    },
    {
      "epoch": 0.10198300283286119,
      "grad_norm": 2.413506031036377,
      "learning_rate": 2.4719101123595505e-05,
      "loss": 0.6373977661132812,
      "step": 45
    },
    {
      "epoch": 0.11331444759206799,
      "grad_norm": 0.8175360560417175,
      "learning_rate": 2.752808988764045e-05,
      "loss": 0.3264909744262695,
      "step": 50
    },
    {
      "epoch": 0.12464589235127478,
      "grad_norm": 0.7170977592468262,
      "learning_rate": 3.0337078651685396e-05,
      "loss": 0.4823625564575195,
      "step": 55
    },
    {
      "epoch": 0.1359773371104816,
      "grad_norm": 1.3019003868103027,
      "learning_rate": 3.314606741573034e-05,
      "loss": 0.46833462715148927,
      "step": 60
    },
    {
      "epoch": 0.14730878186968838,
      "grad_norm": 0.7885598540306091,
      "learning_rate": 3.595505617977528e-05,
      "loss": 0.411859130859375,
      "step": 65
    },
    {
      "epoch": 0.15864022662889518,
      "grad_norm": 1.6470946073532104,
      "learning_rate": 3.876404494382023e-05,
      "loss": 0.5116501331329346,
      "step": 70
    },
    {
      "epoch": 0.16997167138810199,
      "grad_norm": 1.0545003414154053,
      "learning_rate": 4.157303370786517e-05,
      "loss": 0.4329397678375244,
      "step": 75
    },
    {
      "epoch": 0.1813031161473088,
      "grad_norm": 1.4362479448318481,
      "learning_rate": 4.438202247191011e-05,
      "loss": 0.524379825592041,
      "step": 80
    },
    {
      "epoch": 0.19263456090651557,
      "grad_norm": 0.9161525964736938,
      "learning_rate": 4.719101123595506e-05,
      "loss": 0.4873896598815918,
      "step": 85
    },
    {
      "epoch": 0.20396600566572237,
      "grad_norm": 0.9398213624954224,
      "learning_rate": 5e-05,
      "loss": 0.3370382308959961,
      "step": 90
    },
    {
      "epoch": 0.21529745042492918,
      "grad_norm": 0.9127558469772339,
      "learning_rate": 4.999512020721228e-05,
      "loss": 0.43856964111328123,
      "step": 95
    },
    {
      "epoch": 0.22662889518413598,
      "grad_norm": 1.115868330001831,
      "learning_rate": 4.99804827338393e-05,
      "loss": 0.5081729412078857,
      "step": 100
    },
    {
      "epoch": 0.23796033994334279,
      "grad_norm": 0.8525002002716064,
      "learning_rate": 4.995609329410804e-05,
      "loss": 0.4288600444793701,
      "step": 105
    },
    {
      "epoch": 0.24929178470254956,
      "grad_norm": 0.7350711822509766,
      "learning_rate": 4.9921961409251464e-05,
      "loss": 0.36382455825805665,
      "step": 110
    },
    {
      "epoch": 0.26062322946175637,
      "grad_norm": 0.8869081139564514,
      "learning_rate": 4.98781004037916e-05,
      "loss": 0.4126336097717285,
      "step": 115
    },
    {
      "epoch": 0.2719546742209632,
      "grad_norm": 0.8808944821357727,
      "learning_rate": 4.982452740033793e-05,
      "loss": 0.5013623714447022,
      "step": 120
    },
    {
      "epoch": 0.28328611898017,
      "grad_norm": 1.688800573348999,
      "learning_rate": 4.9761263312902895e-05,
      "loss": 0.3734902858734131,
      "step": 125
    },
    {
      "epoch": 0.29461756373937675,
      "grad_norm": 0.854536771774292,
      "learning_rate": 4.9688332838737504e-05,
      "loss": 0.3330167293548584,
      "step": 130
    },
    {
      "epoch": 0.3059490084985836,
      "grad_norm": 0.8838964104652405,
      "learning_rate": 4.960576444868992e-05,
      "loss": 0.4687922477722168,
      "step": 135
    },
    {
      "epoch": 0.31728045325779036,
      "grad_norm": 1.2479231357574463,
      "learning_rate": 4.951359037609088e-05,
      "loss": 0.5538063526153565,
      "step": 140
    },
    {
      "epoch": 0.3286118980169972,
      "grad_norm": 0.9001554250717163,
      "learning_rate": 4.9411846604170345e-05,
      "loss": 0.3675175666809082,
      "step": 145
    },
    {
      "epoch": 0.33994334277620397,
      "grad_norm": 1.3334121704101562,
      "learning_rate": 4.930057285201027e-05,
      "loss": 0.34098784923553466,
      "step": 150
    },
    {
      "epoch": 0.35127478753541075,
      "grad_norm": 0.8316202163696289,
      "learning_rate": 4.917981255903893e-05,
      "loss": 0.27486042976379393,
      "step": 155
    },
    {
      "epoch": 0.3626062322946176,
      "grad_norm": 0.8910505175590515,
      "learning_rate": 4.9049612868072844e-05,
      "loss": 0.4869553089141846,
      "step": 160
    },
    {
      "epoch": 0.37393767705382436,
      "grad_norm": 0.6928417086601257,
      "learning_rate": 4.891002460691306e-05,
      "loss": 0.34002320766448973,
      "step": 165
    },
    {
      "epoch": 0.38526912181303113,
      "grad_norm": 0.5460754036903381,
      "learning_rate": 4.876110226850278e-05,
      "loss": 0.49013099670410154,
      "step": 170
    },
    {
      "epoch": 0.39660056657223797,
      "grad_norm": 0.6613168120384216,
      "learning_rate": 4.8602903989654224e-05,
      "loss": 0.33164176940917967,
      "step": 175
    },
    {
      "epoch": 0.40793201133144474,
      "grad_norm": 0.8668295741081238,
      "learning_rate": 4.8435491528353026e-05,
      "loss": 0.3509191989898682,
      "step": 180
    },
    {
      "epoch": 0.4192634560906516,
      "grad_norm": 0.7438768148422241,
      "learning_rate": 4.8258930239648865e-05,
      "loss": 0.2707263946533203,
      "step": 185
    },
    {
      "epoch": 0.43059490084985835,
      "grad_norm": 0.7994551062583923,
      "learning_rate": 4.807328905014201e-05,
      "loss": 0.47815761566162107,
      "step": 190
    },
    {
      "epoch": 0.44192634560906513,
      "grad_norm": 0.8858820796012878,
      "learning_rate": 4.787864043107546e-05,
      "loss": 0.2694305181503296,
      "step": 195
    },
    {
      "epoch": 0.45325779036827196,
      "grad_norm": 0.9021828174591064,
      "learning_rate": 4.767506037004344e-05,
      "loss": 0.3334247350692749,
      "step": 200
    },
    {
      "epoch": 0.46458923512747874,
      "grad_norm": 0.7257297039031982,
      "learning_rate": 4.7462628341326995e-05,
      "loss": 0.4210684776306152,
      "step": 205
    },
    {
      "epoch": 0.47592067988668557,
      "grad_norm": 0.5886158347129822,
      "learning_rate": 4.724142727486869e-05,
      "loss": 0.4695872783660889,
      "step": 210
    },
    {
      "epoch": 0.48725212464589235,
      "grad_norm": 0.5792116522789001,
      "learning_rate": 4.7011543523897996e-05,
      "loss": 0.25666112899780275,
      "step": 215
    },
    {
      "epoch": 0.4985835694050991,
      "grad_norm": 1.0046709775924683,
      "learning_rate": 4.677306683122054e-05,
      "loss": 0.4950394630432129,
      "step": 220
    },
    {
      "epoch": 0.509915014164306,
      "grad_norm": 0.5250871777534485,
      "learning_rate": 4.652609029418389e-05,
      "loss": 0.2860694885253906,
      "step": 225
    },
    {
      "epoch": 0.5212464589235127,
      "grad_norm": 0.6448274850845337,
      "learning_rate": 4.6270710328334004e-05,
      "loss": 0.5050464630126953,
      "step": 230
    },
    {
      "epoch": 0.5325779036827195,
      "grad_norm": 0.815632700920105,
      "learning_rate": 4.6007026629776104e-05,
      "loss": 0.36529276371002195,
      "step": 235
    },
    {
      "epoch": 0.5439093484419264,
      "grad_norm": 0.6050383448600769,
      "learning_rate": 4.573514213625505e-05,
      "loss": 0.33652830123901367,
      "step": 240
    },
    {
      "epoch": 0.5552407932011332,
      "grad_norm": 0.9683236479759216,
      "learning_rate": 4.545516298697006e-05,
      "loss": 0.3598660945892334,
      "step": 245
    },
    {
      "epoch": 0.56657223796034,
      "grad_norm": 0.6836624145507812,
      "learning_rate": 4.5167198481139825e-05,
      "loss": 0.32996649742126466,
      "step": 250
    },
    {
      "epoch": 0.5779036827195467,
      "grad_norm": 0.6328911185264587,
      "learning_rate": 4.4871361035333836e-05,
      "loss": 0.414959716796875,
      "step": 255
    },
    {
      "epoch": 0.5892351274787535,
      "grad_norm": 0.6919077634811401,
      "learning_rate": 4.456776613958683e-05,
      "loss": 0.24719634056091308,
      "step": 260
    },
    {
      "epoch": 0.6005665722379604,
      "grad_norm": 1.066320538520813,
      "learning_rate": 4.425653231231344e-05,
      "loss": 0.2967464685440063,
      "step": 265
    },
    {
      "epoch": 0.6118980169971672,
      "grad_norm": 1.1447703838348389,
      "learning_rate": 4.3937781054040505e-05,
      "loss": 0.5102629661560059,
      "step": 270
    },
    {
      "epoch": 0.623229461756374,
      "grad_norm": 0.696940541267395,
      "learning_rate": 4.361163679997532e-05,
      "loss": 0.40943374633789065,
      "step": 275
    },
    {
      "epoch": 0.6345609065155807,
      "grad_norm": 0.971284031867981,
      "learning_rate": 4.327822687142819e-05,
      "loss": 0.27406275272369385,
      "step": 280
    },
    {
      "epoch": 0.6458923512747875,
      "grad_norm": 0.5769820809364319,
      "learning_rate": 4.293768142610828e-05,
      "loss": 0.43962855339050294,
      "step": 285
    },
    {
      "epoch": 0.6572237960339944,
      "grad_norm": 0.7735850214958191,
      "learning_rate": 4.259013340731224e-05,
      "loss": 0.3719588041305542,
      "step": 290
    },
    {
      "epoch": 0.6685552407932012,
      "grad_norm": 0.7028021812438965,
      "learning_rate": 4.22357184920253e-05,
      "loss": 0.32131032943725585,
      "step": 295
    },
    {
      "epoch": 0.6798866855524079,
      "grad_norm": 0.7551348805427551,
      "learning_rate": 4.187457503795527e-05,
      "loss": 0.432879638671875,
      "step": 300
    },
    {
      "epoch": 0.6912181303116147,
      "grad_norm": 0.701796293258667,
      "learning_rate": 4.150684402951994e-05,
      "loss": 0.37615275382995605,
      "step": 305
    },
    {
      "epoch": 0.7025495750708215,
      "grad_norm": 0.5740243792533875,
      "learning_rate": 4.1132669022809136e-05,
      "loss": 0.31838488578796387,
      "step": 310
    },
    {
      "epoch": 0.7138810198300283,
      "grad_norm": 0.475755512714386,
      "learning_rate": 4.075219608954278e-05,
      "loss": 0.37903852462768556,
      "step": 315
    },
    {
      "epoch": 0.7252124645892352,
      "grad_norm": 1.3921504020690918,
      "learning_rate": 4.036557376004694e-05,
      "loss": 0.48739376068115237,
      "step": 320
    },
    {
      "epoch": 0.7365439093484419,
      "grad_norm": 0.6479005813598633,
      "learning_rate": 3.9972952965270006e-05,
      "loss": 0.44881558418273926,
      "step": 325
    },
    {
      "epoch": 0.7478753541076487,
      "grad_norm": 0.7648313641548157,
      "learning_rate": 3.95744869778618e-05,
      "loss": 0.26784167289733884,
      "step": 330
    },
    {
      "epoch": 0.7592067988668555,
      "grad_norm": 0.6832091808319092,
      "learning_rate": 3.917033135233845e-05,
      "loss": 0.3547700881958008,
      "step": 335
    },
    {
      "epoch": 0.7705382436260623,
      "grad_norm": 0.5492965579032898,
      "learning_rate": 3.876064386435646e-05,
      "loss": 0.4471108436584473,
      "step": 340
    },
    {
      "epoch": 0.7818696883852692,
      "grad_norm": 0.5076380968093872,
      "learning_rate": 3.8345584449119776e-05,
      "loss": 0.3807786464691162,
      "step": 345
    },
    {
      "epoch": 0.7932011331444759,
      "grad_norm": 1.0112333297729492,
      "learning_rate": 3.7925315138943655e-05,
      "loss": 0.34582831859588625,
      "step": 350
    },
    {
      "epoch": 0.8045325779036827,
      "grad_norm": 0.6434851288795471,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.48055739402770997,
      "step": 355
    },
    {
      "epoch": 0.8158640226628895,
      "grad_norm": 0.5997300744056702,
      "learning_rate": 3.706980506826863e-05,
      "loss": 0.29955766201019285,
      "step": 360
    },
    {
      "epoch": 0.8271954674220963,
      "grad_norm": 0.6214690804481506,
      "learning_rate": 3.663489828471953e-05,
      "loss": 0.5157360076904297,
      "step": 365
    },
    {
      "epoch": 0.8385269121813032,
      "grad_norm": 0.5965062379837036,
      "learning_rate": 3.619544942975158e-05,
      "loss": 0.4225013256072998,
      "step": 370
    },
    {
      "epoch": 0.8498583569405099,
      "grad_norm": 0.7531642317771912,
      "learning_rate": 3.575163005691302e-05,
      "loss": 0.6868666172027588,
      "step": 375
    },
    {
      "epoch": 0.8611898016997167,
      "grad_norm": 0.526151716709137,
      "learning_rate": 3.530361342592981e-05,
      "loss": 0.33634586334228517,
      "step": 380
    },
    {
      "epoch": 0.8725212464589235,
      "grad_norm": 0.4799348711967468,
      "learning_rate": 3.485157443506792e-05,
      "loss": 0.27149507999420164,
      "step": 385
    },
    {
      "epoch": 0.8838526912181303,
      "grad_norm": 0.5290740132331848,
      "learning_rate": 3.4395689552855955e-05,
      "loss": 0.3871570587158203,
      "step": 390
    },
    {
      "epoch": 0.8951841359773371,
      "grad_norm": 0.6749078631401062,
      "learning_rate": 3.393613674919473e-05,
      "loss": 0.45883984565734864,
      "step": 395
    },
    {
      "epoch": 0.9065155807365439,
      "grad_norm": 1.2738566398620605,
      "learning_rate": 3.3473095425880796e-05,
      "loss": 0.4699589252471924,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 884,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.125471987316398e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}