{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 904,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011071132023249377,
      "grad_norm": 0.2982485890388489,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5438612461090088,
      "step": 10
    },
    {
      "epoch": 0.022142264046498755,
      "grad_norm": 0.2238633632659912,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.4879115104675293,
      "step": 20
    },
    {
      "epoch": 0.03321339606974813,
      "grad_norm": 0.19642046093940735,
      "learning_rate": 4.9999358393573445e-05,
      "loss": 0.5164765357971192,
      "step": 30
    },
    {
      "epoch": 0.04428452809299751,
      "grad_norm": 0.17894092202186584,
      "learning_rate": 4.997690562638874e-05,
      "loss": 0.5168572425842285,
      "step": 40
    },
    {
      "epoch": 0.05535566011624689,
      "grad_norm": 0.20002231001853943,
      "learning_rate": 4.992240546298341e-05,
      "loss": 0.4712099552154541,
      "step": 50
    },
    {
      "epoch": 0.06642679213949626,
      "grad_norm": 0.18889793753623962,
      "learning_rate": 4.983592783148856e-05,
      "loss": 0.4723380088806152,
      "step": 60
    },
    {
      "epoch": 0.07749792416274565,
      "grad_norm": 0.1800369769334793,
      "learning_rate": 4.9717583689721046e-05,
      "loss": 0.4957925319671631,
      "step": 70
    },
    {
      "epoch": 0.08856905618599502,
      "grad_norm": 0.18672174215316772,
      "learning_rate": 4.9567524882815686e-05,
      "loss": 0.4966912269592285,
      "step": 80
    },
    {
      "epoch": 0.09964018820924439,
      "grad_norm": 0.19791601598262787,
      "learning_rate": 4.938594394839555e-05,
      "loss": 0.45592079162597654,
      "step": 90
    },
    {
      "epoch": 0.11071132023249378,
      "grad_norm": 0.17983797192573547,
      "learning_rate": 4.917307386953062e-05,
      "loss": 0.47900638580322263,
      "step": 100
    },
    {
      "epoch": 0.12178245225574315,
      "grad_norm": 0.19228127598762512,
      "learning_rate": 4.892918777580161e-05,
      "loss": 0.47019343376159667,
      "step": 110
    },
    {
      "epoch": 0.13285358427899252,
      "grad_norm": 0.19917553663253784,
      "learning_rate": 4.865459859285251e-05,
      "loss": 0.5000853061676025,
      "step": 120
    },
    {
      "epoch": 0.1439247163022419,
      "grad_norm": 0.19071853160858154,
      "learning_rate": 4.834965864088164e-05,
      "loss": 0.45295085906982424,
      "step": 130
    },
    {
      "epoch": 0.1549958483254913,
      "grad_norm": 0.16079416871070862,
      "learning_rate": 4.8014759182586274e-05,
      "loss": 0.4652396202087402,
      "step": 140
    },
    {
      "epoch": 0.16606698034874065,
      "grad_norm": 0.19701199233531952,
      "learning_rate": 4.765032992114078e-05,
      "loss": 0.48296642303466797,
      "step": 150
    },
    {
      "epoch": 0.17713811237199004,
      "grad_norm": 0.21357282996177673,
      "learning_rate": 4.725683844885266e-05,
      "loss": 0.49079251289367676,
      "step": 160
    },
    {
      "epoch": 0.18820924439523942,
      "grad_norm": 0.2039526402950287,
      "learning_rate": 4.6834789647203656e-05,
      "loss": 0.4890737056732178,
      "step": 170
    },
    {
      "epoch": 0.19928037641848878,
      "grad_norm": 0.21518221497535706,
      "learning_rate": 4.638472503904583e-05,
      "loss": 0.45900492668151854,
      "step": 180
    },
    {
      "epoch": 0.21035150844173817,
      "grad_norm": 0.21490415930747986,
      "learning_rate": 4.590722209378387e-05,
      "loss": 0.5259706974029541,
      "step": 190
    },
    {
      "epoch": 0.22142264046498755,
      "grad_norm": 0.168563112616539,
      "learning_rate": 4.540289348643493e-05,
      "loss": 0.460019588470459,
      "step": 200
    },
    {
      "epoch": 0.2324937724882369,
      "grad_norm": 0.1914004385471344,
      "learning_rate": 4.487238631151691e-05,
      "loss": 0.44524073600769043,
      "step": 210
    },
    {
      "epoch": 0.2435649045114863,
      "grad_norm": 0.17691361904144287,
      "learning_rate": 4.4316381252773696e-05,
      "loss": 0.46790690422058107,
      "step": 220
    },
    {
      "epoch": 0.25463603653473565,
      "grad_norm": 0.2210698425769806,
      "learning_rate": 4.373559170980271e-05,
      "loss": 0.4862049579620361,
      "step": 230
    },
    {
      "epoch": 0.26570716855798504,
      "grad_norm": 0.22967994213104248,
      "learning_rate": 4.3130762882705286e-05,
      "loss": 0.4924201011657715,
      "step": 240
    },
    {
      "epoch": 0.2767783005812344,
      "grad_norm": 0.16751348972320557,
      "learning_rate": 4.2502670815934566e-05,
      "loss": 0.4716155529022217,
      "step": 250
    },
    {
      "epoch": 0.2878494326044838,
      "grad_norm": 0.21026551723480225,
      "learning_rate": 4.185212140256745e-05,
      "loss": 0.4572009563446045,
      "step": 260
    },
    {
      "epoch": 0.2989205646277332,
      "grad_norm": 0.22434744238853455,
      "learning_rate": 4.1179949350278416e-05,
      "loss": 0.45023150444030763,
      "step": 270
    },
    {
      "epoch": 0.3099916966509826,
      "grad_norm": 0.20906312763690948,
      "learning_rate": 4.0487017110341885e-05,
      "loss": 0.4625581741333008,
      "step": 280
    },
    {
      "epoch": 0.3210628286742319,
      "grad_norm": 0.2559385895729065,
      "learning_rate": 3.977421377103721e-05,
      "loss": 0.4705606460571289,
      "step": 290
    },
    {
      "epoch": 0.3321339606974813,
      "grad_norm": 0.19080273807048798,
      "learning_rate": 3.9042453916876346e-05,
      "loss": 0.4363286018371582,
      "step": 300
    },
    {
      "epoch": 0.3432050927207307,
      "grad_norm": 0.19936195015907288,
      "learning_rate": 3.829267645511766e-05,
      "loss": 0.4401339054107666,
      "step": 310
    },
    {
      "epoch": 0.3542762247439801,
      "grad_norm": 0.201541930437088,
      "learning_rate": 3.75258434110718e-05,
      "loss": 0.4440303802490234,
      "step": 320
    },
    {
      "epoch": 0.36534735676722946,
      "grad_norm": 0.21206802129745483,
      "learning_rate": 3.6742938693745186e-05,
      "loss": 0.4457419395446777,
      "step": 330
    },
    {
      "epoch": 0.37641848879047884,
      "grad_norm": 0.20935574173927307,
      "learning_rate": 3.594496683340485e-05,
      "loss": 0.446307897567749,
      "step": 340
    },
    {
      "epoch": 0.38748962081372823,
      "grad_norm": 0.1839415729045868,
      "learning_rate": 3.513295169268469e-05,
      "loss": 0.44975647926330564,
      "step": 350
    },
    {
      "epoch": 0.39856075283697756,
      "grad_norm": 0.24826107919216156,
      "learning_rate": 3.430793515288663e-05,
      "loss": 0.46418194770812987,
      "step": 360
    },
    {
      "epoch": 0.40963188486022695,
      "grad_norm": 0.1801632046699524,
      "learning_rate": 3.347097577716236e-05,
      "loss": 0.48062825202941895,
      "step": 370
    },
    {
      "epoch": 0.42070301688347633,
      "grad_norm": 0.2788636386394501,
      "learning_rate": 3.262314745229097e-05,
      "loss": 0.4637604713439941,
      "step": 380
    },
    {
      "epoch": 0.4317741489067257,
      "grad_norm": 0.20094694197177887,
      "learning_rate": 3.176553801079502e-05,
      "loss": 0.4522414207458496,
      "step": 390
    },
    {
      "epoch": 0.4428452809299751,
      "grad_norm": 0.20372502505779266,
      "learning_rate": 3.0899247835163284e-05,
      "loss": 0.4449589729309082,
      "step": 400
    },
    {
      "epoch": 0.4539164129532245,
      "grad_norm": 0.24644096195697784,
      "learning_rate": 3.0025388445970632e-05,
      "loss": 0.46959652900695803,
      "step": 410
    },
    {
      "epoch": 0.4649875449764738,
      "grad_norm": 0.1820651739835739,
      "learning_rate": 2.9145081075707e-05,
      "loss": 0.4682285785675049,
      "step": 420
    },
    {
      "epoch": 0.4760586769997232,
      "grad_norm": 0.22257454693317413,
      "learning_rate": 2.8259455230145153e-05,
      "loss": 0.4520132541656494,
      "step": 430
    },
    {
      "epoch": 0.4871298090229726,
      "grad_norm": 0.21487396955490112,
      "learning_rate": 2.7369647239093137e-05,
      "loss": 0.45970830917358396,
      "step": 440
    },
    {
      "epoch": 0.498200941046222,
      "grad_norm": 0.19929295778274536,
      "learning_rate": 2.6476798798390933e-05,
      "loss": 0.48697819709777834,
      "step": 450
    },
    {
      "epoch": 0.5092720730694713,
      "grad_norm": 0.19580361247062683,
      "learning_rate": 2.558205550502211e-05,
      "loss": 0.442689323425293,
      "step": 460
    },
    {
      "epoch": 0.5203432050927207,
      "grad_norm": 0.2583716809749603,
      "learning_rate": 2.4686565387219925e-05,
      "loss": 0.45048093795776367,
      "step": 470
    },
    {
      "epoch": 0.5314143371159701,
      "grad_norm": 0.21075128018856049,
      "learning_rate": 2.3791477431453946e-05,
      "loss": 0.4816279411315918,
      "step": 480
    },
    {
      "epoch": 0.5424854691392195,
      "grad_norm": 0.2000635415315628,
      "learning_rate": 2.289794010818724e-05,
      "loss": 0.44063844680786135,
      "step": 490
    },
    {
      "epoch": 0.5535566011624689,
      "grad_norm": 0.308988094329834,
      "learning_rate": 2.2007099898295597e-05,
      "loss": 0.5063977241516113,
      "step": 500
    },
    {
      "epoch": 0.5646277331857182,
      "grad_norm": 0.17804710566997528,
      "learning_rate": 2.112009982203951e-05,
      "loss": 0.4599731922149658,
      "step": 510
    },
    {
      "epoch": 0.5756988652089676,
      "grad_norm": 0.22322002053260803,
      "learning_rate": 2.0238077972476493e-05,
      "loss": 0.4338075160980225,
      "step": 520
    },
    {
      "epoch": 0.586769997232217,
      "grad_norm": 0.22158072888851166,
      "learning_rate": 1.9362166055195333e-05,
      "loss": 0.45435776710510256,
      "step": 530
    },
    {
      "epoch": 0.5978411292554664,
      "grad_norm": 0.21982787549495697,
      "learning_rate": 1.849348793624604e-05,
      "loss": 0.45902328491210936,
      "step": 540
    },
    {
      "epoch": 0.6089122612787158,
      "grad_norm": 0.21599163115024567,
      "learning_rate": 1.7633158200128486e-05,
      "loss": 0.46292743682861326,
      "step": 550
    },
    {
      "epoch": 0.6199833933019652,
      "grad_norm": 0.17219366133213043,
      "learning_rate": 1.67822807196901e-05,
      "loss": 0.44576573371887207,
      "step": 560
    },
    {
      "epoch": 0.6310545253252146,
      "grad_norm": 0.25163161754608154,
      "learning_rate": 1.594194723976744e-05,
      "loss": 0.49637713432312014,
      "step": 570
    },
    {
      "epoch": 0.6421256573484638,
      "grad_norm": 0.2211240828037262,
      "learning_rate": 1.5113235976388995e-05,
      "loss": 0.44209861755371094,
      "step": 580
    },
    {
      "epoch": 0.6531967893717132,
      "grad_norm": 0.23704175651073456,
      "learning_rate": 1.4297210233336567e-05,
      "loss": 0.47528576850891113,
      "step": 590
    },
    {
      "epoch": 0.6642679213949626,
      "grad_norm": 0.1952650547027588,
      "learning_rate": 1.3494917037840226e-05,
      "loss": 0.44990553855896,
      "step": 600
    },
    {
      "epoch": 0.675339053418212,
      "grad_norm": 0.23648826777935028,
      "learning_rate": 1.2707385797157445e-05,
      "loss": 0.4471109867095947,
      "step": 610
    },
    {
      "epoch": 0.6864101854414614,
      "grad_norm": 0.18498748540878296,
      "learning_rate": 1.1935626977760081e-05,
      "loss": 0.47311859130859374,
      "step": 620
    },
    {
      "epoch": 0.6974813174647108,
      "grad_norm": 0.22625111043453217,
      "learning_rate": 1.1180630808823936e-05,
      "loss": 0.478549861907959,
      "step": 630
    },
    {
      "epoch": 0.7085524494879601,
      "grad_norm": 0.23048552870750427,
      "learning_rate": 1.0443366011684319e-05,
      "loss": 0.4929988384246826,
      "step": 640
    },
    {
      "epoch": 0.7196235815112095,
      "grad_norm": 0.21760839223861694,
      "learning_rate": 9.724778556888078e-06,
      "loss": 0.45112242698669436,
      "step": 650
    },
    {
      "epoch": 0.7306947135344589,
      "grad_norm": 0.21399666368961334,
      "learning_rate": 9.025790450436555e-06,
      "loss": 0.45237131118774415,
      "step": 660
    },
    {
      "epoch": 0.7417658455577083,
      "grad_norm": 0.20168475806713104,
      "learning_rate": 8.347298550777177e-06,
      "loss": 0.44932117462158205,
      "step": 670
    },
    {
      "epoch": 0.7528369775809577,
      "grad_norm": 0.20694777369499207,
      "learning_rate": 7.690173418061215e-06,
      "loss": 0.46954689025878904,
      "step": 680
    },
    {
      "epoch": 0.7639081096042071,
      "grad_norm": 0.24068519473075867,
      "learning_rate": 7.055258197144551e-06,
      "loss": 0.47182540893554686,
      "step": 690
    },
    {
      "epoch": 0.7749792416274565,
      "grad_norm": 0.2288457453250885,
      "learning_rate": 6.443367535764414e-06,
      "loss": 0.45500984191894533,
      "step": 700
    },
    {
      "epoch": 0.7860503736507057,
      "grad_norm": 0.192505344748497,
      "learning_rate": 5.855286539280203e-06,
      "loss": 0.43417630195617674,
      "step": 710
    },
    {
      "epoch": 0.7971215056739551,
      "grad_norm": 0.20437484979629517,
      "learning_rate": 5.291769763319684e-06,
      "loss": 0.47623233795166015,
      "step": 720
    },
    {
      "epoch": 0.8081926376972045,
      "grad_norm": 0.21906627714633942,
      "learning_rate": 4.75354024562284e-06,
      "loss": 0.43716044425964357,
      "step": 730
    },
    {
      "epoch": 0.8192637697204539,
      "grad_norm": 0.20373809337615967,
      "learning_rate": 4.241288578325842e-06,
      "loss": 0.47289414405822755,
      "step": 740
    },
    {
      "epoch": 0.8303349017437033,
      "grad_norm": 0.19537311792373657,
      "learning_rate": 3.755672021875273e-06,
      "loss": 0.44959001541137694,
      "step": 750
    },
    {
      "epoch": 0.8414060337669527,
      "grad_norm": 0.2127528190612793,
      "learning_rate": 3.2973136617096917e-06,
      "loss": 0.5204972743988037,
      "step": 760
    },
    {
      "epoch": 0.852477165790202,
      "grad_norm": 0.21742160618305206,
      "learning_rate": 2.8668016087904424e-06,
      "loss": 0.46805849075317385,
      "step": 770
    },
    {
      "epoch": 0.8635482978134514,
      "grad_norm": 0.23823955655097961,
      "learning_rate": 2.4646882450075737e-06,
      "loss": 0.46898465156555175,
      "step": 780
    },
    {
      "epoch": 0.8746194298367008,
      "grad_norm": 0.2252834439277649,
      "learning_rate": 2.0914895144290845e-06,
      "loss": 0.4386277675628662,
      "step": 790
    },
    {
      "epoch": 0.8856905618599502,
      "grad_norm": 0.2196691781282425,
      "learning_rate": 1.7476842613028011e-06,
      "loss": 0.4420029640197754,
      "step": 800
    },
    {
      "epoch": 0.8967616938831996,
      "grad_norm": 0.23585157096385956,
      "learning_rate": 1.433713615660387e-06,
      "loss": 0.4560047149658203,
      "step": 810
    },
    {
      "epoch": 0.907832825906449,
      "grad_norm": 0.21041040122509003,
      "learning_rate": 1.149980427311703e-06,
      "loss": 0.4705744743347168,
      "step": 820
    },
    {
      "epoch": 0.9189039579296983,
      "grad_norm": 0.21200747787952423,
      "learning_rate": 8.968487489558253e-07,
      "loss": 0.43934082984924316,
      "step": 830
    },
    {
      "epoch": 0.9299750899529476,
      "grad_norm": 0.1721661537885666,
      "learning_rate": 6.746433690719145e-07,
      "loss": 0.46813287734985354,
      "step": 840
    },
    {
      "epoch": 0.941046221976197,
      "grad_norm": 0.24086591601371765,
      "learning_rate": 4.836493951892119e-07,
      "loss": 0.4672842025756836,
      "step": 850
    },
    {
      "epoch": 0.9521173539994464,
      "grad_norm": 0.19945469498634338,
      "learning_rate": 3.241118880709826e-07,
      "loss": 0.45268807411193845,
      "step": 860
    },
    {
      "epoch": 0.9631884860226958,
      "grad_norm": 0.21253763139247894,
      "learning_rate": 1.962355472816646e-07,
      "loss": 0.45673418045043945,
      "step": 870
    },
    {
      "epoch": 0.9742596180459452,
      "grad_norm": 0.2631364166736603,
      "learning_rate": 1.0018444854071885e-07,
      "loss": 0.48882236480712893,
      "step": 880
    },
    {
      "epoch": 0.9853307500691946,
      "grad_norm": 0.21766266226768494,
      "learning_rate": 3.6081833200163337e-08,
      "loss": 0.48557772636413576,
      "step": 890
    },
    {
      "epoch": 0.996401882092444,
      "grad_norm": 0.2388443946838379,
      "learning_rate": 4.009950115940741e-09,
      "loss": 0.4435438632965088,
      "step": 900
    }
  ],
  "logging_steps": 10,
  "max_steps": 904,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.789693109946778e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}