{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5325168075617387,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005325168075617386,
      "grad_norm": 1.179490566253662,
      "learning_rate": 4.787234042553191e-06,
      "loss": 0.7552515983581543,
      "step": 10
    },
    {
      "epoch": 0.010650336151234773,
      "grad_norm": 0.7021263837814331,
      "learning_rate": 1.0106382978723404e-05,
      "loss": 0.7758663654327392,
      "step": 20
    },
    {
      "epoch": 0.01597550422685216,
      "grad_norm": 0.6242384314537048,
      "learning_rate": 1.5425531914893617e-05,
      "loss": 0.620504903793335,
      "step": 30
    },
    {
      "epoch": 0.021300672302469546,
      "grad_norm": 0.4310513138771057,
      "learning_rate": 2.074468085106383e-05,
      "loss": 0.6261196613311768,
      "step": 40
    },
    {
      "epoch": 0.026625840378086935,
      "grad_norm": 0.5022103786468506,
      "learning_rate": 2.6063829787234046e-05,
      "loss": 0.6593732833862305,
      "step": 50
    },
    {
      "epoch": 0.03195100845370432,
      "grad_norm": 0.6999115943908691,
      "learning_rate": 3.1382978723404254e-05,
      "loss": 0.687755012512207,
      "step": 60
    },
    {
      "epoch": 0.037276176529321706,
      "grad_norm": 0.4458341598510742,
      "learning_rate": 3.670212765957447e-05,
      "loss": 0.6062395572662354,
      "step": 70
    },
    {
      "epoch": 0.04260134460493909,
      "grad_norm": 0.5636934638023376,
      "learning_rate": 4.2021276595744684e-05,
      "loss": 0.6789586544036865,
      "step": 80
    },
    {
      "epoch": 0.04792651268055648,
      "grad_norm": 0.47693607211112976,
      "learning_rate": 4.734042553191489e-05,
      "loss": 0.5777320384979248,
      "step": 90
    },
    {
      "epoch": 0.05325168075617387,
      "grad_norm": 0.5000275373458862,
      "learning_rate": 4.985986547085202e-05,
      "loss": 0.5979567527770996,
      "step": 100
    },
    {
      "epoch": 0.058576848831791255,
      "grad_norm": 0.7978994250297546,
      "learning_rate": 4.9579596412556055e-05,
      "loss": 0.5918041229248047,
      "step": 110
    },
    {
      "epoch": 0.06390201690740864,
      "grad_norm": 0.6180557012557983,
      "learning_rate": 4.9299327354260097e-05,
      "loss": 0.6245941162109375,
      "step": 120
    },
    {
      "epoch": 0.06922718498302603,
      "grad_norm": 0.8771600723266602,
      "learning_rate": 4.9019058295964125e-05,
      "loss": 0.5516412258148193,
      "step": 130
    },
    {
      "epoch": 0.07455235305864341,
      "grad_norm": 0.570806622505188,
      "learning_rate": 4.8738789237668166e-05,
      "loss": 0.6044556140899658,
      "step": 140
    },
    {
      "epoch": 0.0798775211342608,
      "grad_norm": 0.5548396110534668,
      "learning_rate": 4.84585201793722e-05,
      "loss": 0.5861228466033935,
      "step": 150
    },
    {
      "epoch": 0.08520268920987818,
      "grad_norm": 0.3578498661518097,
      "learning_rate": 4.8178251121076236e-05,
      "loss": 0.5874335289001464,
      "step": 160
    },
    {
      "epoch": 0.09052785728549557,
      "grad_norm": 0.6209887266159058,
      "learning_rate": 4.789798206278027e-05,
      "loss": 0.5836649894714355,
      "step": 170
    },
    {
      "epoch": 0.09585302536111295,
      "grad_norm": 0.5073224902153015,
      "learning_rate": 4.7617713004484306e-05,
      "loss": 0.5651541233062745,
      "step": 180
    },
    {
      "epoch": 0.10117819343673035,
      "grad_norm": 0.5013888478279114,
      "learning_rate": 4.733744394618834e-05,
      "loss": 0.5798611164093017,
      "step": 190
    },
    {
      "epoch": 0.10650336151234774,
      "grad_norm": 0.2958514094352722,
      "learning_rate": 4.705717488789238e-05,
      "loss": 0.5263164520263672,
      "step": 200
    },
    {
      "epoch": 0.11182852958796512,
      "grad_norm": 0.5098234415054321,
      "learning_rate": 4.677690582959641e-05,
      "loss": 0.6066572189331054,
      "step": 210
    },
    {
      "epoch": 0.11715369766358251,
      "grad_norm": 0.68392413854599,
      "learning_rate": 4.649663677130045e-05,
      "loss": 0.501525592803955,
      "step": 220
    },
    {
      "epoch": 0.12247886573919989,
      "grad_norm": 0.5342642068862915,
      "learning_rate": 4.621636771300449e-05,
      "loss": 0.5538065910339356,
      "step": 230
    },
    {
      "epoch": 0.12780403381481728,
      "grad_norm": 0.46322742104530334,
      "learning_rate": 4.593609865470852e-05,
      "loss": 0.6028264999389649,
      "step": 240
    },
    {
      "epoch": 0.13312920189043467,
      "grad_norm": 0.5507689714431763,
      "learning_rate": 4.565582959641256e-05,
      "loss": 0.524617338180542,
      "step": 250
    },
    {
      "epoch": 0.13845436996605207,
      "grad_norm": 0.5451244711875916,
      "learning_rate": 4.537556053811659e-05,
      "loss": 0.5184399604797363,
      "step": 260
    },
    {
      "epoch": 0.14377953804166943,
      "grad_norm": 0.4679802656173706,
      "learning_rate": 4.509529147982063e-05,
      "loss": 0.5906213760375977,
      "step": 270
    },
    {
      "epoch": 0.14910470611728682,
      "grad_norm": 0.4486578702926636,
      "learning_rate": 4.481502242152467e-05,
      "loss": 0.5088740348815918,
      "step": 280
    },
    {
      "epoch": 0.15442987419290422,
      "grad_norm": 0.3085339665412903,
      "learning_rate": 4.4534753363228704e-05,
      "loss": 0.5231688499450684,
      "step": 290
    },
    {
      "epoch": 0.1597550422685216,
      "grad_norm": 0.8423092365264893,
      "learning_rate": 4.425448430493274e-05,
      "loss": 0.5785892963409424,
      "step": 300
    },
    {
      "epoch": 0.165080210344139,
      "grad_norm": 0.8173497319221497,
      "learning_rate": 4.3974215246636774e-05,
      "loss": 0.5546716690063477,
      "step": 310
    },
    {
      "epoch": 0.17040537841975636,
      "grad_norm": 0.4842700958251953,
      "learning_rate": 4.369394618834081e-05,
      "loss": 0.5258895874023437,
      "step": 320
    },
    {
      "epoch": 0.17573054649537376,
      "grad_norm": 0.645687460899353,
      "learning_rate": 4.3413677130044844e-05,
      "loss": 0.5903552532196045,
      "step": 330
    },
    {
      "epoch": 0.18105571457099115,
      "grad_norm": 0.5248221755027771,
      "learning_rate": 4.313340807174888e-05,
      "loss": 0.5313117027282714,
      "step": 340
    },
    {
      "epoch": 0.18638088264660854,
      "grad_norm": 0.4039202928543091,
      "learning_rate": 4.2853139013452914e-05,
      "loss": 0.5434175491333008,
      "step": 350
    },
    {
      "epoch": 0.1917060507222259,
      "grad_norm": 0.6575778126716614,
      "learning_rate": 4.257286995515695e-05,
      "loss": 0.5336236476898193,
      "step": 360
    },
    {
      "epoch": 0.1970312187978433,
      "grad_norm": 0.6030762791633606,
      "learning_rate": 4.229260089686099e-05,
      "loss": 0.5873087406158447,
      "step": 370
    },
    {
      "epoch": 0.2023563868734607,
      "grad_norm": 0.36645743250846863,
      "learning_rate": 4.201233183856502e-05,
      "loss": 0.44643635749816896,
      "step": 380
    },
    {
      "epoch": 0.20768155494907808,
      "grad_norm": 0.38583752512931824,
      "learning_rate": 4.173206278026906e-05,
      "loss": 0.48238911628723147,
      "step": 390
    },
    {
      "epoch": 0.21300672302469548,
      "grad_norm": 0.3569328486919403,
      "learning_rate": 4.1451793721973096e-05,
      "loss": 0.5249658107757569,
      "step": 400
    },
    {
      "epoch": 0.21833189110031284,
      "grad_norm": 0.5705183744430542,
      "learning_rate": 4.117152466367713e-05,
      "loss": 0.5840038299560547,
      "step": 410
    },
    {
      "epoch": 0.22365705917593023,
      "grad_norm": 0.5844929218292236,
      "learning_rate": 4.0891255605381166e-05,
      "loss": 0.49370269775390624,
      "step": 420
    },
    {
      "epoch": 0.22898222725154763,
      "grad_norm": 0.4003148376941681,
      "learning_rate": 4.061098654708521e-05,
      "loss": 0.5035266876220703,
      "step": 430
    },
    {
      "epoch": 0.23430739532716502,
      "grad_norm": 0.4637913405895233,
      "learning_rate": 4.0330717488789236e-05,
      "loss": 0.4923057556152344,
      "step": 440
    },
    {
      "epoch": 0.2396325634027824,
      "grad_norm": 0.41266828775405884,
      "learning_rate": 4.005044843049328e-05,
      "loss": 0.48969035148620604,
      "step": 450
    },
    {
      "epoch": 0.24495773147839978,
      "grad_norm": 0.6229465007781982,
      "learning_rate": 3.977017937219731e-05,
      "loss": 0.5537493228912354,
      "step": 460
    },
    {
      "epoch": 0.25028289955401717,
      "grad_norm": 0.3518058657646179,
      "learning_rate": 3.948991031390135e-05,
      "loss": 0.5104994297027587,
      "step": 470
    },
    {
      "epoch": 0.25560806762963456,
      "grad_norm": 0.3331281840801239,
      "learning_rate": 3.920964125560538e-05,
      "loss": 0.48421249389648435,
      "step": 480
    },
    {
      "epoch": 0.26093323570525195,
      "grad_norm": 0.6162995100021362,
      "learning_rate": 3.8929372197309424e-05,
      "loss": 0.5097816944122314,
      "step": 490
    },
    {
      "epoch": 0.26625840378086935,
      "grad_norm": 0.7575991153717041,
      "learning_rate": 3.864910313901345e-05,
      "loss": 0.538728666305542,
      "step": 500
    },
    {
      "epoch": 0.27158357185648674,
      "grad_norm": 0.6776933073997498,
      "learning_rate": 3.8368834080717494e-05,
      "loss": 0.48033552169799804,
      "step": 510
    },
    {
      "epoch": 0.27690873993210413,
      "grad_norm": 0.46453195810317993,
      "learning_rate": 3.808856502242152e-05,
      "loss": 0.502266263961792,
      "step": 520
    },
    {
      "epoch": 0.28223390800772147,
      "grad_norm": 0.6419550776481628,
      "learning_rate": 3.7808295964125564e-05,
      "loss": 0.6008513450622559,
      "step": 530
    },
    {
      "epoch": 0.28755907608333886,
      "grad_norm": 0.5964445471763611,
      "learning_rate": 3.75280269058296e-05,
      "loss": 0.5803821086883545,
      "step": 540
    },
    {
      "epoch": 0.29288424415895625,
      "grad_norm": 0.5661990642547607,
      "learning_rate": 3.7247757847533634e-05,
      "loss": 0.534914493560791,
      "step": 550
    },
    {
      "epoch": 0.29820941223457365,
      "grad_norm": 0.5758841037750244,
      "learning_rate": 3.696748878923767e-05,
      "loss": 0.5404681205749512,
      "step": 560
    },
    {
      "epoch": 0.30353458031019104,
      "grad_norm": 0.38775309920310974,
      "learning_rate": 3.668721973094171e-05,
      "loss": 0.4564009666442871,
      "step": 570
    },
    {
      "epoch": 0.30885974838580843,
      "grad_norm": 0.48926347494125366,
      "learning_rate": 3.640695067264574e-05,
      "loss": 0.5140261650085449,
      "step": 580
    },
    {
      "epoch": 0.3141849164614258,
      "grad_norm": 0.512454092502594,
      "learning_rate": 3.612668161434978e-05,
      "loss": 0.5441798686981201,
      "step": 590
    },
    {
      "epoch": 0.3195100845370432,
      "grad_norm": 0.6558932065963745,
      "learning_rate": 3.5846412556053815e-05,
      "loss": 0.5184391021728516,
      "step": 600
    },
    {
      "epoch": 0.3248352526126606,
      "grad_norm": 0.5081777572631836,
      "learning_rate": 3.556614349775785e-05,
      "loss": 0.4453147888183594,
      "step": 610
    },
    {
      "epoch": 0.330160420688278,
      "grad_norm": 0.4490305483341217,
      "learning_rate": 3.5285874439461885e-05,
      "loss": 0.48638916015625,
      "step": 620
    },
    {
      "epoch": 0.33548558876389534,
      "grad_norm": 0.6985098123550415,
      "learning_rate": 3.500560538116593e-05,
      "loss": 0.5312550067901611,
      "step": 630
    },
    {
      "epoch": 0.34081075683951273,
      "grad_norm": 0.6176907420158386,
      "learning_rate": 3.4725336322869955e-05,
      "loss": 0.4945085525512695,
      "step": 640
    },
    {
      "epoch": 0.3461359249151301,
      "grad_norm": 0.5329240560531616,
      "learning_rate": 3.4445067264574e-05,
      "loss": 0.5552109241485595,
      "step": 650
    },
    {
      "epoch": 0.3514610929907475,
      "grad_norm": 0.5098716020584106,
      "learning_rate": 3.4164798206278025e-05,
      "loss": 0.534635353088379,
      "step": 660
    },
    {
      "epoch": 0.3567862610663649,
      "grad_norm": 0.5351388454437256,
      "learning_rate": 3.388452914798207e-05,
      "loss": 0.5524871349334717,
      "step": 670
    },
    {
      "epoch": 0.3621114291419823,
      "grad_norm": 0.2978927195072174,
      "learning_rate": 3.36042600896861e-05,
      "loss": 0.4628488063812256,
      "step": 680
    },
    {
      "epoch": 0.3674365972175997,
      "grad_norm": 0.29183733463287354,
      "learning_rate": 3.3323991031390137e-05,
      "loss": 0.49717202186584475,
      "step": 690
    },
    {
      "epoch": 0.3727617652932171,
      "grad_norm": 0.35929256677627563,
      "learning_rate": 3.304372197309417e-05,
      "loss": 0.5281675338745118,
      "step": 700
    },
    {
      "epoch": 0.3780869333688345,
      "grad_norm": 0.45750725269317627,
      "learning_rate": 3.2763452914798206e-05,
      "loss": 0.4717850208282471,
      "step": 710
    },
    {
      "epoch": 0.3834121014444518,
      "grad_norm": 0.3303137719631195,
      "learning_rate": 3.248318385650224e-05,
      "loss": 0.4823610782623291,
      "step": 720
    },
    {
      "epoch": 0.3887372695200692,
      "grad_norm": 0.3863198161125183,
      "learning_rate": 3.2202914798206276e-05,
      "loss": 0.44127840995788575,
      "step": 730
    },
    {
      "epoch": 0.3940624375956866,
      "grad_norm": 0.4643816351890564,
      "learning_rate": 3.192264573991032e-05,
      "loss": 0.5454273700714112,
      "step": 740
    },
    {
      "epoch": 0.399387605671304,
      "grad_norm": 0.49157482385635376,
      "learning_rate": 3.1642376681614346e-05,
      "loss": 0.5360610008239746,
      "step": 750
    },
    {
      "epoch": 0.4047127737469214,
      "grad_norm": 0.4481538236141205,
      "learning_rate": 3.136210762331839e-05,
      "loss": 0.5228201389312744,
      "step": 760
    },
    {
      "epoch": 0.4100379418225388,
      "grad_norm": 0.3987141251564026,
      "learning_rate": 3.108183856502242e-05,
      "loss": 0.5480076313018799,
      "step": 770
    },
    {
      "epoch": 0.41536310989815617,
      "grad_norm": 0.3665584921836853,
      "learning_rate": 3.080156950672646e-05,
      "loss": 0.5201095104217529,
      "step": 780
    },
    {
      "epoch": 0.42068827797377356,
      "grad_norm": 0.803251326084137,
      "learning_rate": 3.052130044843049e-05,
      "loss": 0.5136742115020752,
      "step": 790
    },
    {
      "epoch": 0.42601344604939095,
      "grad_norm": 0.35160404443740845,
      "learning_rate": 3.0241031390134535e-05,
      "loss": 0.4411343574523926,
      "step": 800
    },
    {
      "epoch": 0.43133861412500835,
      "grad_norm": 0.29174962639808655,
      "learning_rate": 2.9960762331838566e-05,
      "loss": 0.44309115409851074,
      "step": 810
    },
    {
      "epoch": 0.4366637822006257,
      "grad_norm": 0.5460541844367981,
      "learning_rate": 2.9680493273542605e-05,
      "loss": 0.435715389251709,
      "step": 820
    },
    {
      "epoch": 0.4419889502762431,
      "grad_norm": 0.5169834494590759,
      "learning_rate": 2.9400224215246636e-05,
      "loss": 0.4440354347229004,
      "step": 830
    },
    {
      "epoch": 0.44731411835186047,
      "grad_norm": 0.6184332370758057,
      "learning_rate": 2.9119955156950674e-05,
      "loss": 0.5376930713653565,
      "step": 840
    },
    {
      "epoch": 0.45263928642747786,
      "grad_norm": 0.6049388647079468,
      "learning_rate": 2.8839686098654713e-05,
      "loss": 0.5526479244232178,
      "step": 850
    },
    {
      "epoch": 0.45796445450309525,
      "grad_norm": 0.5835752487182617,
      "learning_rate": 2.8559417040358744e-05,
      "loss": 0.4482475757598877,
      "step": 860
    },
    {
      "epoch": 0.46328962257871265,
      "grad_norm": 0.6599181890487671,
      "learning_rate": 2.8279147982062783e-05,
      "loss": 0.4716318607330322,
      "step": 870
    },
    {
      "epoch": 0.46861479065433004,
      "grad_norm": 1.169771432876587,
      "learning_rate": 2.7998878923766818e-05,
      "loss": 0.484691858291626,
      "step": 880
    },
    {
      "epoch": 0.47393995872994743,
      "grad_norm": 0.7327702045440674,
      "learning_rate": 2.7718609865470853e-05,
      "loss": 0.49949216842651367,
      "step": 890
    },
    {
      "epoch": 0.4792651268055648,
      "grad_norm": 0.355288565158844,
      "learning_rate": 2.743834080717489e-05,
      "loss": 0.47687301635742185,
      "step": 900
    },
    {
      "epoch": 0.48459029488118216,
      "grad_norm": 0.4060805141925812,
      "learning_rate": 2.7158071748878926e-05,
      "loss": 0.49724478721618653,
      "step": 910
    },
    {
      "epoch": 0.48991546295679955,
      "grad_norm": 0.3232281506061554,
      "learning_rate": 2.687780269058296e-05,
      "loss": 0.4345158576965332,
      "step": 920
    },
    {
      "epoch": 0.49524063103241694,
      "grad_norm": 0.2930939495563507,
      "learning_rate": 2.6597533632286996e-05,
      "loss": 0.5002622604370117,
      "step": 930
    },
    {
      "epoch": 0.5005657991080343,
      "grad_norm": 0.27968496084213257,
      "learning_rate": 2.6317264573991034e-05,
      "loss": 0.41611757278442385,
      "step": 940
    },
    {
      "epoch": 0.5058909671836518,
      "grad_norm": 0.36835038661956787,
      "learning_rate": 2.6036995515695066e-05,
      "loss": 0.4969151973724365,
      "step": 950
    },
    {
      "epoch": 0.5112161352592691,
      "grad_norm": 0.2818012535572052,
      "learning_rate": 2.5756726457399104e-05,
      "loss": 0.4511505126953125,
      "step": 960
    },
    {
      "epoch": 0.5165413033348865,
      "grad_norm": 0.405793160200119,
      "learning_rate": 2.5476457399103142e-05,
      "loss": 0.4167983055114746,
      "step": 970
    },
    {
      "epoch": 0.5218664714105039,
      "grad_norm": 0.3238755762577057,
      "learning_rate": 2.5196188340807174e-05,
      "loss": 0.43145551681518557,
      "step": 980
    },
    {
      "epoch": 0.5271916394861212,
      "grad_norm": 0.38960742950439453,
      "learning_rate": 2.4915919282511212e-05,
      "loss": 0.435044527053833,
      "step": 990
    },
    {
      "epoch": 0.5325168075617387,
      "grad_norm": 1.2799712419509888,
      "learning_rate": 2.4635650224215247e-05,
      "loss": 0.5337179183959961,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1878,
  "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": 4.185382709003059e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}