{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 766,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013061224489795919,
      "grad_norm": 0.013593924231827259,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 1.0348053932189942,
      "step": 10
    },
    {
      "epoch": 0.026122448979591838,
      "grad_norm": 0.010592319071292877,
      "learning_rate": 3.8974358974358976e-05,
      "loss": 0.9912956237792969,
      "step": 20
    },
    {
      "epoch": 0.03918367346938775,
      "grad_norm": 0.008065517991781235,
      "learning_rate": 5.9487179487179495e-05,
      "loss": 0.9145261764526367,
      "step": 30
    },
    {
      "epoch": 0.052244897959183675,
      "grad_norm": 0.006928236689418554,
      "learning_rate": 8e-05,
      "loss": 0.8690940856933593,
      "step": 40
    },
    {
      "epoch": 0.0653061224489796,
      "grad_norm": 0.0065370709635317326,
      "learning_rate": 7.996265836446255e-05,
      "loss": 0.8447072982788086,
      "step": 50
    },
    {
      "epoch": 0.0783673469387755,
      "grad_norm": 0.005765452049672604,
      "learning_rate": 7.985070317773737e-05,
      "loss": 0.8226842880249023,
      "step": 60
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 0.004979082383215427,
      "learning_rate": 7.966434346931348e-05,
      "loss": 0.8047774314880372,
      "step": 70
    },
    {
      "epoch": 0.10448979591836735,
      "grad_norm": 0.00686669023707509,
      "learning_rate": 7.940392718800637e-05,
      "loss": 0.7929642200469971,
      "step": 80
    },
    {
      "epoch": 0.11755102040816326,
      "grad_norm": 0.006248346995562315,
      "learning_rate": 7.90699405523093e-05,
      "loss": 0.7915477275848388,
      "step": 90
    },
    {
      "epoch": 0.1306122448979592,
      "grad_norm": 0.007850440219044685,
      "learning_rate": 7.86630071425835e-05,
      "loss": 0.7851225376129151,
      "step": 100
    },
    {
      "epoch": 0.1436734693877551,
      "grad_norm": 0.007440537214279175,
      "learning_rate": 7.818388673678265e-05,
      "loss": 0.7773007869720459,
      "step": 110
    },
    {
      "epoch": 0.156734693877551,
      "grad_norm": 0.007219385821372271,
      "learning_rate": 7.763347389188538e-05,
      "loss": 0.7723363399505615,
      "step": 120
    },
    {
      "epoch": 0.16979591836734695,
      "grad_norm": 0.006354185286909342,
      "learning_rate": 7.701279627368412e-05,
      "loss": 0.7682206153869628,
      "step": 130
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 0.006955909077078104,
      "learning_rate": 7.632301273804914e-05,
      "loss": 0.7699796676635742,
      "step": 140
    },
    {
      "epoch": 0.19591836734693877,
      "grad_norm": 0.008277718909084797,
      "learning_rate": 7.556541116724981e-05,
      "loss": 0.764019775390625,
      "step": 150
    },
    {
      "epoch": 0.2089795918367347,
      "grad_norm": 0.007425008807331324,
      "learning_rate": 7.474140606537311e-05,
      "loss": 0.7628626823425293,
      "step": 160
    },
    {
      "epoch": 0.2220408163265306,
      "grad_norm": 0.008092896081507206,
      "learning_rate": 7.38525359173288e-05,
      "loss": 0.7607949256896973,
      "step": 170
    },
    {
      "epoch": 0.23510204081632652,
      "grad_norm": 0.011249990202486515,
      "learning_rate": 7.290046031637228e-05,
      "loss": 0.757351303100586,
      "step": 180
    },
    {
      "epoch": 0.24816326530612245,
      "grad_norm": 0.009156743064522743,
      "learning_rate": 7.188695686550836e-05,
      "loss": 0.7565219879150391,
      "step": 190
    },
    {
      "epoch": 0.2612244897959184,
      "grad_norm": 0.008516875095665455,
      "learning_rate": 7.081391785856087e-05,
      "loss": 0.7473669052124023,
      "step": 200
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 0.008919311687350273,
      "learning_rate": 6.96833467471056e-05,
      "loss": 0.7444419860839844,
      "step": 210
    },
    {
      "epoch": 0.2873469387755102,
      "grad_norm": 0.007335508707910776,
      "learning_rate": 6.84973543998622e-05,
      "loss": 0.7573845386505127,
      "step": 220
    },
    {
      "epoch": 0.3004081632653061,
      "grad_norm": 0.007334326393902302,
      "learning_rate": 6.725815516152973e-05,
      "loss": 0.7524682998657226,
      "step": 230
    },
    {
      "epoch": 0.313469387755102,
      "grad_norm": 0.006889250595122576,
      "learning_rate": 6.596806271842398e-05,
      "loss": 0.7463503837585449,
      "step": 240
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.007522549480199814,
      "learning_rate": 6.462948577863593e-05,
      "loss": 0.7468090057373047,
      "step": 250
    },
    {
      "epoch": 0.3395918367346939,
      "grad_norm": 0.00689704529941082,
      "learning_rate": 6.324492357477686e-05,
      "loss": 0.745818042755127,
      "step": 260
    },
    {
      "epoch": 0.3526530612244898,
      "grad_norm": 0.007402004674077034,
      "learning_rate": 6.18169611977065e-05,
      "loss": 0.737040901184082,
      "step": 270
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 0.006718257907778025,
      "learning_rate": 6.034826476995715e-05,
      "loss": 0.7412730693817139,
      "step": 280
    },
    {
      "epoch": 0.3787755102040816,
      "grad_norm": 0.006786980666220188,
      "learning_rate": 5.8841576467864825e-05,
      "loss": 0.7408377170562744,
      "step": 290
    },
    {
      "epoch": 0.39183673469387753,
      "grad_norm": 0.006618338171392679,
      "learning_rate": 5.7299709401701805e-05,
      "loss": 0.7430388927459717,
      "step": 300
    },
    {
      "epoch": 0.4048979591836735,
      "grad_norm": 0.007314841262996197,
      "learning_rate": 5.572554236336965e-05,
      "loss": 0.7401338577270508,
      "step": 310
    },
    {
      "epoch": 0.4179591836734694,
      "grad_norm": 0.0067168474197387695,
      "learning_rate": 5.4122014451459385e-05,
      "loss": 0.7423385143280029,
      "step": 320
    },
    {
      "epoch": 0.4310204081632653,
      "grad_norm": 0.007062443997710943,
      "learning_rate": 5.2492119583714064e-05,
      "loss": 0.7407833099365234,
      "step": 330
    },
    {
      "epoch": 0.4440816326530612,
      "grad_norm": 0.009489820338785648,
      "learning_rate": 5.083890090713949e-05,
      "loss": 0.7376296997070313,
      "step": 340
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.006291185040026903,
      "learning_rate": 4.916544511619984e-05,
      "loss": 0.7393476963043213,
      "step": 350
    },
    {
      "epoch": 0.47020408163265304,
      "grad_norm": 0.007340357638895512,
      "learning_rate": 4.747487668970681e-05,
      "loss": 0.7434526443481445,
      "step": 360
    },
    {
      "epoch": 0.483265306122449,
      "grad_norm": 0.007148618344217539,
      "learning_rate": 4.5770352057162046e-05,
      "loss": 0.7274169445037841,
      "step": 370
    },
    {
      "epoch": 0.4963265306122449,
      "grad_norm": 0.007421489339321852,
      "learning_rate": 4.405505370544521e-05,
      "loss": 0.7373303413391114,
      "step": 380
    },
    {
      "epoch": 0.5093877551020408,
      "grad_norm": 0.006447239778935909,
      "learning_rate": 4.233218423685071e-05,
      "loss": 0.7334803581237793,
      "step": 390
    },
    {
      "epoch": 0.5224489795918368,
      "grad_norm": 0.007035430055111647,
      "learning_rate": 4.060496038956728e-05,
      "loss": 0.7342597961425781,
      "step": 400
    },
    {
      "epoch": 0.5355102040816326,
      "grad_norm": 0.006574620492756367,
      "learning_rate": 3.887660703176474e-05,
      "loss": 0.7356997966766358,
      "step": 410
    },
    {
      "epoch": 0.5485714285714286,
      "grad_norm": 0.0066298553720116615,
      "learning_rate": 3.7150351140501457e-05,
      "loss": 0.7381177425384522,
      "step": 420
    },
    {
      "epoch": 0.5616326530612245,
      "grad_norm": 0.007492161355912685,
      "learning_rate": 3.542941577669424e-05,
      "loss": 0.7291494369506836,
      "step": 430
    },
    {
      "epoch": 0.5746938775510204,
      "grad_norm": 0.006217462942004204,
      "learning_rate": 3.3717014067400025e-05,
      "loss": 0.7233750343322753,
      "step": 440
    },
    {
      "epoch": 0.5877551020408164,
      "grad_norm": 0.006911132019013166,
      "learning_rate": 3.201634320664491e-05,
      "loss": 0.7269360542297363,
      "step": 450
    },
    {
      "epoch": 0.6008163265306122,
      "grad_norm": 0.00729888491332531,
      "learning_rate": 3.0330578486001478e-05,
      "loss": 0.7219826698303222,
      "step": 460
    },
    {
      "epoch": 0.6138775510204082,
      "grad_norm": 0.007913697510957718,
      "learning_rate": 2.8662867366059758e-05,
      "loss": 0.7285231590270996,
      "step": 470
    },
    {
      "epoch": 0.626938775510204,
      "grad_norm": 0.006929247174412012,
      "learning_rate": 2.7016323599860833e-05,
      "loss": 0.7285576820373535,
      "step": 480
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.006759402342140675,
      "learning_rate": 2.5394021419265458e-05,
      "loss": 0.7239264965057373,
      "step": 490
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 0.006527756340801716,
      "learning_rate": 2.379898979511156e-05,
      "loss": 0.731016731262207,
      "step": 500
    },
    {
      "epoch": 0.6661224489795918,
      "grad_norm": 0.006792586762458086,
      "learning_rate": 2.2234206781878127e-05,
      "loss": 0.7236400604248047,
      "step": 510
    },
    {
      "epoch": 0.6791836734693878,
      "grad_norm": 0.006418135017156601,
      "learning_rate": 2.0702593957413973e-05,
      "loss": 0.7233975887298584,
      "step": 520
    },
    {
      "epoch": 0.6922448979591836,
      "grad_norm": 0.006609582342207432,
      "learning_rate": 1.9207010968112856e-05,
      "loss": 0.7252939224243165,
      "step": 530
    },
    {
      "epoch": 0.7053061224489796,
      "grad_norm": 0.006350552197545767,
      "learning_rate": 1.7750250189719885e-05,
      "loss": 0.7322314739227295,
      "step": 540
    },
    {
      "epoch": 0.7183673469387755,
      "grad_norm": 0.006282226648181677,
      "learning_rate": 1.633503151373769e-05,
      "loss": 0.718090009689331,
      "step": 550
    },
    {
      "epoch": 0.7314285714285714,
      "grad_norm": 0.006717463489621878,
      "learning_rate": 1.4963997269166472e-05,
      "loss": 0.7251626491546631,
      "step": 560
    },
    {
      "epoch": 0.7444897959183674,
      "grad_norm": 0.006243122275918722,
      "learning_rate": 1.363970728905975e-05,
      "loss": 0.7236129760742187,
      "step": 570
    },
    {
      "epoch": 0.7575510204081632,
      "grad_norm": 0.005929226521402597,
      "learning_rate": 1.2364634131106663e-05,
      "loss": 0.7275202751159668,
      "step": 580
    },
    {
      "epoch": 0.7706122448979592,
      "grad_norm": 0.006825726944953203,
      "learning_rate": 1.11411584611646e-05,
      "loss": 0.7266074657440186,
      "step": 590
    },
    {
      "epoch": 0.7836734693877551,
      "grad_norm": 0.006338095758110285,
      "learning_rate": 9.971564608361387e-06,
      "loss": 0.7227339744567871,
      "step": 600
    },
    {
      "epoch": 0.796734693877551,
      "grad_norm": 0.006189221516251564,
      "learning_rate": 8.858036300065912e-06,
      "loss": 0.7260101318359375,
      "step": 610
    },
    {
      "epoch": 0.809795918367347,
      "grad_norm": 0.006516415625810623,
      "learning_rate": 7.802652584690627e-06,
      "loss": 0.721678638458252,
      "step": 620
    },
    {
      "epoch": 0.8228571428571428,
      "grad_norm": 0.006069981027394533,
      "learning_rate": 6.807383949938131e-06,
      "loss": 0.7275302886962891,
      "step": 630
    },
    {
      "epoch": 0.8359183673469388,
      "grad_norm": 0.006245093885809183,
      "learning_rate": 5.874088643739453e-06,
      "loss": 0.7232262134552002,
      "step": 640
    },
    {
      "epoch": 0.8489795918367347,
      "grad_norm": 0.0058577232994139194,
      "learning_rate": 5.0045092047532385e-06,
      "loss": 0.7290368556976319,
      "step": 650
    },
    {
      "epoch": 0.8620408163265306,
      "grad_norm": 0.005565746687352657,
      "learning_rate": 4.200269208903569e-06,
      "loss": 0.7283772945404052,
      "step": 660
    },
    {
      "epoch": 0.8751020408163265,
      "grad_norm": 0.006886645220220089,
      "learning_rate": 3.4628702380309266e-06,
      "loss": 0.7242953300476074,
      "step": 670
    },
    {
      "epoch": 0.8881632653061224,
      "grad_norm": 0.005979357752948999,
      "learning_rate": 2.793689076316111e-06,
      "loss": 0.7234395503997803,
      "step": 680
    },
    {
      "epoch": 0.9012244897959184,
      "grad_norm": 0.005459806881844997,
      "learning_rate": 2.193975139711575e-06,
      "loss": 0.7297232151031494,
      "step": 690
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.00546460272744298,
      "learning_rate": 1.6648481431797137e-06,
      "loss": 0.7135615348815918,
      "step": 700
    },
    {
      "epoch": 0.9273469387755102,
      "grad_norm": 0.005548370536416769,
      "learning_rate": 1.2072960100933862e-06,
      "loss": 0.7257327079772949,
      "step": 710
    },
    {
      "epoch": 0.9404081632653061,
      "grad_norm": 0.005945554003119469,
      "learning_rate": 8.221730277022488e-07,
      "loss": 0.7289669036865234,
      "step": 720
    },
    {
      "epoch": 0.953469387755102,
      "grad_norm": 0.005690570455044508,
      "learning_rate": 5.101982521085847e-07,
      "loss": 0.7285196781158447,
      "step": 730
    },
    {
      "epoch": 0.966530612244898,
      "grad_norm": 0.005644120275974274,
      "learning_rate": 2.719541657307456e-07,
      "loss": 0.7271464347839356,
      "step": 740
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 0.005760515108704567,
      "learning_rate": 1.0788558976085662e-07,
      "loss": 0.726295280456543,
      "step": 750
    },
    {
      "epoch": 0.9926530612244898,
      "grad_norm": 0.006554395891726017,
      "learning_rate": 1.8298853647267245e-08,
      "loss": 0.7278533458709717,
      "step": 760
    },
    {
      "epoch": 1.0,
      "step": 766,
      "total_flos": 7.613569370341507e+18,
      "train_loss": 0.7527124293479223,
      "train_runtime": 22851.6673,
      "train_samples_per_second": 2.144,
      "train_steps_per_second": 0.034
    }
  ],
  "logging_steps": 10,
  "max_steps": 766,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.613569370341507e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}