{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 1015,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03466204506065858,
      "grad_norm": 1.530611515045166,
      "learning_rate": 0.0002,
      "loss": 3.0151,
      "step": 5
    },
    {
      "epoch": 0.06932409012131716,
      "grad_norm": 1.7004058361053467,
      "learning_rate": 0.0002,
      "loss": 2.0235,
      "step": 10
    },
    {
      "epoch": 0.10398613518197573,
      "grad_norm": 1.933908462524414,
      "learning_rate": 0.0002,
      "loss": 1.1225,
      "step": 15
    },
    {
      "epoch": 0.1386481802426343,
      "grad_norm": 0.9951248168945312,
      "learning_rate": 0.0002,
      "loss": 0.5422,
      "step": 20
    },
    {
      "epoch": 0.1733102253032929,
      "grad_norm": 6.152623176574707,
      "learning_rate": 0.0002,
      "loss": 1.5639,
      "step": 25
    },
    {
      "epoch": 0.20797227036395147,
      "grad_norm": 8.008278846740723,
      "learning_rate": 0.0002,
      "loss": 2.6486,
      "step": 30
    },
    {
      "epoch": 0.24263431542461006,
      "grad_norm": 4.960943222045898,
      "learning_rate": 0.0002,
      "loss": 2.6059,
      "step": 35
    },
    {
      "epoch": 0.2772963604852686,
      "grad_norm": 4.607645511627197,
      "learning_rate": 0.0002,
      "loss": 1.6898,
      "step": 40
    },
    {
      "epoch": 0.3119584055459272,
      "grad_norm": 0.8448249101638794,
      "learning_rate": 0.0002,
      "loss": 0.799,
      "step": 45
    },
    {
      "epoch": 0.3466204506065858,
      "grad_norm": 0.46238261461257935,
      "learning_rate": 0.0002,
      "loss": 0.5374,
      "step": 50
    },
    {
      "epoch": 0.38128249566724437,
      "grad_norm": 0.3575257956981659,
      "learning_rate": 0.0002,
      "loss": 0.4247,
      "step": 55
    },
    {
      "epoch": 0.41594454072790293,
      "grad_norm": 2.5151493549346924,
      "learning_rate": 0.0002,
      "loss": 0.7472,
      "step": 60
    },
    {
      "epoch": 0.4506065857885615,
      "grad_norm": 17.38052749633789,
      "learning_rate": 0.0002,
      "loss": 1.8466,
      "step": 65
    },
    {
      "epoch": 0.4852686308492201,
      "grad_norm": 15.523968696594238,
      "learning_rate": 0.0002,
      "loss": 2.1105,
      "step": 70
    },
    {
      "epoch": 0.5199306759098787,
      "grad_norm": 1.0907574892044067,
      "learning_rate": 0.0002,
      "loss": 1.1052,
      "step": 75
    },
    {
      "epoch": 0.5545927209705372,
      "grad_norm": 0.5225581526756287,
      "learning_rate": 0.0002,
      "loss": 0.5663,
      "step": 80
    },
    {
      "epoch": 0.5892547660311959,
      "grad_norm": 0.3306778073310852,
      "learning_rate": 0.0002,
      "loss": 0.4648,
      "step": 85
    },
    {
      "epoch": 0.6239168110918544,
      "grad_norm": 0.33595138788223267,
      "learning_rate": 0.0002,
      "loss": 0.3762,
      "step": 90
    },
    {
      "epoch": 0.658578856152513,
      "grad_norm": 1.978458285331726,
      "learning_rate": 0.0002,
      "loss": 0.9162,
      "step": 95
    },
    {
      "epoch": 0.6932409012131716,
      "grad_norm": 1.1226632595062256,
      "learning_rate": 0.0002,
      "loss": 1.5477,
      "step": 100
    },
    {
      "epoch": 0.7279029462738301,
      "grad_norm": 22.263992309570312,
      "learning_rate": 0.0002,
      "loss": 1.8063,
      "step": 105
    },
    {
      "epoch": 0.7625649913344887,
      "grad_norm": 1.3690563440322876,
      "learning_rate": 0.0002,
      "loss": 1.3102,
      "step": 110
    },
    {
      "epoch": 0.7972270363951474,
      "grad_norm": 0.5651267766952515,
      "learning_rate": 0.0002,
      "loss": 0.553,
      "step": 115
    },
    {
      "epoch": 0.8318890814558059,
      "grad_norm": 0.3272489011287689,
      "learning_rate": 0.0002,
      "loss": 0.4813,
      "step": 120
    },
    {
      "epoch": 0.8665511265164645,
      "grad_norm": 0.30475500226020813,
      "learning_rate": 0.0002,
      "loss": 0.3746,
      "step": 125
    },
    {
      "epoch": 0.901213171577123,
      "grad_norm": 0.2812097370624542,
      "learning_rate": 0.0002,
      "loss": 0.284,
      "step": 130
    },
    {
      "epoch": 0.9358752166377816,
      "grad_norm": 1.159839391708374,
      "learning_rate": 0.0002,
      "loss": 1.5179,
      "step": 135
    },
    {
      "epoch": 0.9705372616984402,
      "grad_norm": 4.740174770355225,
      "learning_rate": 0.0002,
      "loss": 1.549,
      "step": 140
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.613008499145508,
      "learning_rate": 0.0002,
      "loss": 1.3938,
      "step": 145
    },
    {
      "epoch": 1.0346620450606585,
      "grad_norm": 0.31811827421188354,
      "learning_rate": 0.0002,
      "loss": 0.5353,
      "step": 150
    },
    {
      "epoch": 1.0693240901213172,
      "grad_norm": 0.42897579073905945,
      "learning_rate": 0.0002,
      "loss": 0.4452,
      "step": 155
    },
    {
      "epoch": 1.1039861351819757,
      "grad_norm": 0.28854838013648987,
      "learning_rate": 0.0002,
      "loss": 0.3563,
      "step": 160
    },
    {
      "epoch": 1.1386481802426343,
      "grad_norm": 0.32319992780685425,
      "learning_rate": 0.0002,
      "loss": 0.2697,
      "step": 165
    },
    {
      "epoch": 1.173310225303293,
      "grad_norm": 1.0144641399383545,
      "learning_rate": 0.0002,
      "loss": 1.3199,
      "step": 170
    },
    {
      "epoch": 1.2079722703639515,
      "grad_norm": 2.1387648582458496,
      "learning_rate": 0.0002,
      "loss": 1.1948,
      "step": 175
    },
    {
      "epoch": 1.24263431542461,
      "grad_norm": 5.240429401397705,
      "learning_rate": 0.0002,
      "loss": 1.2138,
      "step": 180
    },
    {
      "epoch": 1.2772963604852685,
      "grad_norm": 0.5809195637702942,
      "learning_rate": 0.0002,
      "loss": 0.7417,
      "step": 185
    },
    {
      "epoch": 1.3119584055459272,
      "grad_norm": 0.3426031768321991,
      "learning_rate": 0.0002,
      "loss": 0.4541,
      "step": 190
    },
    {
      "epoch": 1.3466204506065858,
      "grad_norm": 0.34089571237564087,
      "learning_rate": 0.0002,
      "loss": 0.3709,
      "step": 195
    },
    {
      "epoch": 1.3812824956672443,
      "grad_norm": 0.2676282823085785,
      "learning_rate": 0.0002,
      "loss": 0.2981,
      "step": 200
    },
    {
      "epoch": 1.415944540727903,
      "grad_norm": 1.8662705421447754,
      "learning_rate": 0.0002,
      "loss": 0.8353,
      "step": 205
    },
    {
      "epoch": 1.4506065857885615,
      "grad_norm": 3.2310688495635986,
      "learning_rate": 0.0002,
      "loss": 1.2188,
      "step": 210
    },
    {
      "epoch": 1.48526863084922,
      "grad_norm": 2.255415916442871,
      "learning_rate": 0.0002,
      "loss": 1.1677,
      "step": 215
    },
    {
      "epoch": 1.5199306759098787,
      "grad_norm": 0.5544691681861877,
      "learning_rate": 0.0002,
      "loss": 0.799,
      "step": 220
    },
    {
      "epoch": 1.5545927209705372,
      "grad_norm": 0.4003375172615051,
      "learning_rate": 0.0002,
      "loss": 0.4786,
      "step": 225
    },
    {
      "epoch": 1.5892547660311958,
      "grad_norm": 0.3774619698524475,
      "learning_rate": 0.0002,
      "loss": 0.4233,
      "step": 230
    },
    {
      "epoch": 1.6239168110918545,
      "grad_norm": 0.352490097284317,
      "learning_rate": 0.0002,
      "loss": 0.3332,
      "step": 235
    },
    {
      "epoch": 1.658578856152513,
      "grad_norm": 0.2637154459953308,
      "learning_rate": 0.0002,
      "loss": 0.2438,
      "step": 240
    },
    {
      "epoch": 1.6932409012131715,
      "grad_norm": 1.3437107801437378,
      "learning_rate": 0.0002,
      "loss": 1.4351,
      "step": 245
    },
    {
      "epoch": 1.7279029462738302,
      "grad_norm": 2.647561550140381,
      "learning_rate": 0.0002,
      "loss": 1.0698,
      "step": 250
    },
    {
      "epoch": 1.7625649913344887,
      "grad_norm": 0.6839751601219177,
      "learning_rate": 0.0002,
      "loss": 0.7411,
      "step": 255
    },
    {
      "epoch": 1.7972270363951472,
      "grad_norm": 0.4790812134742737,
      "learning_rate": 0.0002,
      "loss": 0.5009,
      "step": 260
    },
    {
      "epoch": 1.831889081455806,
      "grad_norm": 0.36322328448295593,
      "learning_rate": 0.0002,
      "loss": 0.4014,
      "step": 265
    },
    {
      "epoch": 1.8665511265164645,
      "grad_norm": 0.31694507598876953,
      "learning_rate": 0.0002,
      "loss": 0.3441,
      "step": 270
    },
    {
      "epoch": 1.901213171577123,
      "grad_norm": 0.24292677640914917,
      "learning_rate": 0.0002,
      "loss": 0.2619,
      "step": 275
    },
    {
      "epoch": 1.9358752166377817,
      "grad_norm": 1.133062720298767,
      "learning_rate": 0.0002,
      "loss": 1.1564,
      "step": 280
    },
    {
      "epoch": 1.9705372616984402,
      "grad_norm": 10.754274368286133,
      "learning_rate": 0.0002,
      "loss": 1.436,
      "step": 285
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6346553564071655,
      "learning_rate": 0.0002,
      "loss": 1.3215,
      "step": 290
    },
    {
      "epoch": 2.0346620450606587,
      "grad_norm": 0.7156389355659485,
      "learning_rate": 0.0002,
      "loss": 0.551,
      "step": 295
    },
    {
      "epoch": 2.069324090121317,
      "grad_norm": 0.3842258155345917,
      "learning_rate": 0.0002,
      "loss": 0.3783,
      "step": 300
    },
    {
      "epoch": 2.1039861351819757,
      "grad_norm": 0.35967278480529785,
      "learning_rate": 0.0002,
      "loss": 0.3124,
      "step": 305
    },
    {
      "epoch": 2.1386481802426345,
      "grad_norm": 0.296977162361145,
      "learning_rate": 0.0002,
      "loss": 0.2367,
      "step": 310
    },
    {
      "epoch": 2.1733102253032928,
      "grad_norm": 1.6834601163864136,
      "learning_rate": 0.0002,
      "loss": 0.7685,
      "step": 315
    },
    {
      "epoch": 2.2079722703639515,
      "grad_norm": 5.758884906768799,
      "learning_rate": 0.0002,
      "loss": 1.0063,
      "step": 320
    },
    {
      "epoch": 2.2426343154246102,
      "grad_norm": 15.24948501586914,
      "learning_rate": 0.0002,
      "loss": 1.231,
      "step": 325
    },
    {
      "epoch": 2.2772963604852685,
      "grad_norm": 0.599730372428894,
      "learning_rate": 0.0002,
      "loss": 0.6392,
      "step": 330
    },
    {
      "epoch": 2.3119584055459272,
      "grad_norm": 0.5307044982910156,
      "learning_rate": 0.0002,
      "loss": 0.3804,
      "step": 335
    },
    {
      "epoch": 2.346620450606586,
      "grad_norm": 0.33558061718940735,
      "learning_rate": 0.0002,
      "loss": 0.3282,
      "step": 340
    },
    {
      "epoch": 2.3812824956672443,
      "grad_norm": 0.2716732919216156,
      "learning_rate": 0.0002,
      "loss": 0.2429,
      "step": 345
    },
    {
      "epoch": 2.415944540727903,
      "grad_norm": 2.454636812210083,
      "learning_rate": 0.0002,
      "loss": 0.5396,
      "step": 350
    },
    {
      "epoch": 2.4506065857885613,
      "grad_norm": 13.286089897155762,
      "learning_rate": 0.0002,
      "loss": 1.0545,
      "step": 355
    },
    {
      "epoch": 2.48526863084922,
      "grad_norm": 12.619502067565918,
      "learning_rate": 0.0002,
      "loss": 1.1547,
      "step": 360
    },
    {
      "epoch": 2.5199306759098787,
      "grad_norm": 0.6347368359565735,
      "learning_rate": 0.0002,
      "loss": 0.7136,
      "step": 365
    },
    {
      "epoch": 2.554592720970537,
      "grad_norm": 0.44485101103782654,
      "learning_rate": 0.0002,
      "loss": 0.3994,
      "step": 370
    },
    {
      "epoch": 2.5892547660311958,
      "grad_norm": 0.36494728922843933,
      "learning_rate": 0.0002,
      "loss": 0.3107,
      "step": 375
    },
    {
      "epoch": 2.6239168110918545,
      "grad_norm": 0.322171688079834,
      "learning_rate": 0.0002,
      "loss": 0.2753,
      "step": 380
    },
    {
      "epoch": 2.6585788561525128,
      "grad_norm": 0.9659174084663391,
      "learning_rate": 0.0002,
      "loss": 0.2948,
      "step": 385
    },
    {
      "epoch": 2.6932409012131715,
      "grad_norm": 0.9371129870414734,
      "learning_rate": 0.0002,
      "loss": 1.0286,
      "step": 390
    },
    {
      "epoch": 2.7279029462738302,
      "grad_norm": 3.4619617462158203,
      "learning_rate": 0.0002,
      "loss": 1.0745,
      "step": 395
    },
    {
      "epoch": 2.7625649913344885,
      "grad_norm": 0.6884852051734924,
      "learning_rate": 0.0002,
      "loss": 0.7637,
      "step": 400
    },
    {
      "epoch": 2.7972270363951472,
      "grad_norm": 0.4440446197986603,
      "learning_rate": 0.0002,
      "loss": 0.4331,
      "step": 405
    },
    {
      "epoch": 2.831889081455806,
      "grad_norm": 0.37561893463134766,
      "learning_rate": 0.0002,
      "loss": 0.3667,
      "step": 410
    },
    {
      "epoch": 2.8665511265164643,
      "grad_norm": 0.320077121257782,
      "learning_rate": 0.0002,
      "loss": 0.2769,
      "step": 415
    },
    {
      "epoch": 2.901213171577123,
      "grad_norm": 1.4914495944976807,
      "learning_rate": 0.0002,
      "loss": 0.4493,
      "step": 420
    },
    {
      "epoch": 2.9358752166377817,
      "grad_norm": 1.164036750793457,
      "learning_rate": 0.0002,
      "loss": 1.1276,
      "step": 425
    },
    {
      "epoch": 2.97053726169844,
      "grad_norm": 5.013108253479004,
      "learning_rate": 0.0002,
      "loss": 1.0841,
      "step": 430
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.2247564792633057,
      "learning_rate": 0.0002,
      "loss": 0.7636,
      "step": 435
    },
    {
      "epoch": 3.0346620450606587,
      "grad_norm": 0.3730102479457855,
      "learning_rate": 0.0002,
      "loss": 0.4291,
      "step": 440
    },
    {
      "epoch": 3.069324090121317,
      "grad_norm": 0.36571791768074036,
      "learning_rate": 0.0002,
      "loss": 0.3155,
      "step": 445
    },
    {
      "epoch": 3.1039861351819757,
      "grad_norm": 0.34427550435066223,
      "learning_rate": 0.0002,
      "loss": 0.2297,
      "step": 450
    },
    {
      "epoch": 3.1386481802426345,
      "grad_norm": 0.3725241422653198,
      "learning_rate": 0.0002,
      "loss": 0.173,
      "step": 455
    },
    {
      "epoch": 3.1733102253032928,
      "grad_norm": 0.9735671877861023,
      "learning_rate": 0.0002,
      "loss": 0.8876,
      "step": 460
    },
    {
      "epoch": 3.2079722703639515,
      "grad_norm": 3.0348145961761475,
      "learning_rate": 0.0002,
      "loss": 0.7825,
      "step": 465
    },
    {
      "epoch": 3.2426343154246102,
      "grad_norm": 1.4603136777877808,
      "learning_rate": 0.0002,
      "loss": 0.8017,
      "step": 470
    },
    {
      "epoch": 3.2772963604852685,
      "grad_norm": 0.6849704384803772,
      "learning_rate": 0.0002,
      "loss": 0.6029,
      "step": 475
    },
    {
      "epoch": 3.3119584055459272,
      "grad_norm": 0.45950087904930115,
      "learning_rate": 0.0002,
      "loss": 0.3388,
      "step": 480
    },
    {
      "epoch": 3.346620450606586,
      "grad_norm": 0.3234940469264984,
      "learning_rate": 0.0002,
      "loss": 0.2635,
      "step": 485
    },
    {
      "epoch": 3.3812824956672443,
      "grad_norm": 0.3088044822216034,
      "learning_rate": 0.0002,
      "loss": 0.1867,
      "step": 490
    },
    {
      "epoch": 3.415944540727903,
      "grad_norm": 0.36887720227241516,
      "learning_rate": 0.0002,
      "loss": 0.1653,
      "step": 495
    },
    {
      "epoch": 3.4506065857885613,
      "grad_norm": 1.041858196258545,
      "learning_rate": 0.0002,
      "loss": 0.9041,
      "step": 500
    },
    {
      "epoch": 3.48526863084922,
      "grad_norm": 1.4774988889694214,
      "learning_rate": 0.0002,
      "loss": 0.9789,
      "step": 505
    },
    {
      "epoch": 3.5199306759098787,
      "grad_norm": 0.6804758310317993,
      "learning_rate": 0.0002,
      "loss": 0.5891,
      "step": 510
    },
    {
      "epoch": 3.554592720970537,
      "grad_norm": 0.43344879150390625,
      "learning_rate": 0.0002,
      "loss": 0.3632,
      "step": 515
    },
    {
      "epoch": 3.5892547660311958,
      "grad_norm": 0.4160469174385071,
      "learning_rate": 0.0002,
      "loss": 0.2734,
      "step": 520
    },
    {
      "epoch": 3.6239168110918545,
      "grad_norm": 0.35103052854537964,
      "learning_rate": 0.0002,
      "loss": 0.2215,
      "step": 525
    },
    {
      "epoch": 3.6585788561525128,
      "grad_norm": 1.083409309387207,
      "learning_rate": 0.0002,
      "loss": 0.2623,
      "step": 530
    },
    {
      "epoch": 3.6932409012131715,
      "grad_norm": 1.2548085451126099,
      "learning_rate": 0.0002,
      "loss": 0.9395,
      "step": 535
    },
    {
      "epoch": 3.7279029462738302,
      "grad_norm": 2.565399169921875,
      "learning_rate": 0.0002,
      "loss": 0.9097,
      "step": 540
    },
    {
      "epoch": 3.7625649913344885,
      "grad_norm": 0.6658923625946045,
      "learning_rate": 0.0002,
      "loss": 0.739,
      "step": 545
    },
    {
      "epoch": 3.7972270363951472,
      "grad_norm": 0.4989807605743408,
      "learning_rate": 0.0002,
      "loss": 0.396,
      "step": 550
    },
    {
      "epoch": 3.831889081455806,
      "grad_norm": 0.39474496245384216,
      "learning_rate": 0.0002,
      "loss": 0.2809,
      "step": 555
    },
    {
      "epoch": 3.8665511265164643,
      "grad_norm": 0.38600996136665344,
      "learning_rate": 0.0002,
      "loss": 0.2254,
      "step": 560
    },
    {
      "epoch": 3.901213171577123,
      "grad_norm": 0.3662823736667633,
      "learning_rate": 0.0002,
      "loss": 0.167,
      "step": 565
    },
    {
      "epoch": 3.9358752166377817,
      "grad_norm": 1.349672794342041,
      "learning_rate": 0.0002,
      "loss": 1.1593,
      "step": 570
    },
    {
      "epoch": 3.97053726169844,
      "grad_norm": 2.3923165798187256,
      "learning_rate": 0.0002,
      "loss": 0.8778,
      "step": 575
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7578555345535278,
      "learning_rate": 0.0002,
      "loss": 0.6897,
      "step": 580
    },
    {
      "epoch": 4.034662045060658,
      "grad_norm": 0.5052911043167114,
      "learning_rate": 0.0002,
      "loss": 0.3913,
      "step": 585
    },
    {
      "epoch": 4.0693240901213175,
      "grad_norm": 0.5212499499320984,
      "learning_rate": 0.0002,
      "loss": 0.2326,
      "step": 590
    },
    {
      "epoch": 4.103986135181976,
      "grad_norm": 0.452105313539505,
      "learning_rate": 0.0002,
      "loss": 0.1846,
      "step": 595
    },
    {
      "epoch": 4.138648180242634,
      "grad_norm": 0.4193221926689148,
      "learning_rate": 0.0002,
      "loss": 0.1359,
      "step": 600
    },
    {
      "epoch": 4.173310225303293,
      "grad_norm": 2.3956053256988525,
      "learning_rate": 0.0002,
      "loss": 0.3795,
      "step": 605
    },
    {
      "epoch": 4.2079722703639515,
      "grad_norm": 1.946535348892212,
      "learning_rate": 0.0002,
      "loss": 0.579,
      "step": 610
    },
    {
      "epoch": 4.24263431542461,
      "grad_norm": 1.874873161315918,
      "learning_rate": 0.0002,
      "loss": 0.7528,
      "step": 615
    },
    {
      "epoch": 4.277296360485269,
      "grad_norm": 0.6922146081924438,
      "learning_rate": 0.0002,
      "loss": 0.4398,
      "step": 620
    },
    {
      "epoch": 4.311958405545927,
      "grad_norm": 0.5228244662284851,
      "learning_rate": 0.0002,
      "loss": 0.2615,
      "step": 625
    },
    {
      "epoch": 4.3466204506065855,
      "grad_norm": 0.34687915444374084,
      "learning_rate": 0.0002,
      "loss": 0.191,
      "step": 630
    },
    {
      "epoch": 4.381282495667245,
      "grad_norm": 0.4160069525241852,
      "learning_rate": 0.0002,
      "loss": 0.1434,
      "step": 635
    },
    {
      "epoch": 4.415944540727903,
      "grad_norm": 1.468666434288025,
      "learning_rate": 0.0002,
      "loss": 0.61,
      "step": 640
    },
    {
      "epoch": 4.450606585788561,
      "grad_norm": 3.174201488494873,
      "learning_rate": 0.0002,
      "loss": 0.5773,
      "step": 645
    },
    {
      "epoch": 4.4852686308492205,
      "grad_norm": 1.8258005380630493,
      "learning_rate": 0.0002,
      "loss": 0.7495,
      "step": 650
    },
    {
      "epoch": 4.519930675909879,
      "grad_norm": 0.8468143343925476,
      "learning_rate": 0.0002,
      "loss": 0.5441,
      "step": 655
    },
    {
      "epoch": 4.554592720970537,
      "grad_norm": 0.5467656254768372,
      "learning_rate": 0.0002,
      "loss": 0.2906,
      "step": 660
    },
    {
      "epoch": 4.589254766031196,
      "grad_norm": 0.396992564201355,
      "learning_rate": 0.0002,
      "loss": 0.2186,
      "step": 665
    },
    {
      "epoch": 4.6239168110918545,
      "grad_norm": 0.31931889057159424,
      "learning_rate": 0.0002,
      "loss": 0.1629,
      "step": 670
    },
    {
      "epoch": 4.658578856152513,
      "grad_norm": 1.755745530128479,
      "learning_rate": 0.0002,
      "loss": 0.2292,
      "step": 675
    },
    {
      "epoch": 4.693240901213172,
      "grad_norm": 0.9869062900543213,
      "learning_rate": 0.0002,
      "loss": 0.6716,
      "step": 680
    },
    {
      "epoch": 4.72790294627383,
      "grad_norm": 1.5987203121185303,
      "learning_rate": 0.0002,
      "loss": 0.8182,
      "step": 685
    },
    {
      "epoch": 4.7625649913344885,
      "grad_norm": 0.870819091796875,
      "learning_rate": 0.0002,
      "loss": 0.5902,
      "step": 690
    },
    {
      "epoch": 4.797227036395148,
      "grad_norm": 0.5098839402198792,
      "learning_rate": 0.0002,
      "loss": 0.3224,
      "step": 695
    },
    {
      "epoch": 4.831889081455806,
      "grad_norm": 0.5435961484909058,
      "learning_rate": 0.0002,
      "loss": 0.2182,
      "step": 700
    },
    {
      "epoch": 4.866551126516464,
      "grad_norm": 0.33275553584098816,
      "learning_rate": 0.0002,
      "loss": 0.1595,
      "step": 705
    },
    {
      "epoch": 4.9012131715771226,
      "grad_norm": 1.8109265565872192,
      "learning_rate": 0.0002,
      "loss": 0.1985,
      "step": 710
    },
    {
      "epoch": 4.935875216637782,
      "grad_norm": 1.149431824684143,
      "learning_rate": 0.0002,
      "loss": 0.8148,
      "step": 715
    },
    {
      "epoch": 4.97053726169844,
      "grad_norm": 1.4355350732803345,
      "learning_rate": 0.0002,
      "loss": 0.6675,
      "step": 720
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.76149845123291,
      "learning_rate": 0.0002,
      "loss": 0.5541,
      "step": 725
    },
    {
      "epoch": 5.034662045060658,
      "grad_norm": 0.6026546359062195,
      "learning_rate": 0.0002,
      "loss": 0.3515,
      "step": 730
    },
    {
      "epoch": 5.0693240901213175,
      "grad_norm": 0.37150222063064575,
      "learning_rate": 0.0002,
      "loss": 0.1661,
      "step": 735
    },
    {
      "epoch": 5.103986135181976,
      "grad_norm": 0.31225013732910156,
      "learning_rate": 0.0002,
      "loss": 0.1243,
      "step": 740
    },
    {
      "epoch": 5.138648180242634,
      "grad_norm": 0.4382600784301758,
      "learning_rate": 0.0002,
      "loss": 0.1004,
      "step": 745
    },
    {
      "epoch": 5.173310225303293,
      "grad_norm": 2.0306389331817627,
      "learning_rate": 0.0002,
      "loss": 0.3743,
      "step": 750
    },
    {
      "epoch": 5.2079722703639515,
      "grad_norm": 1.6935468912124634,
      "learning_rate": 0.0002,
      "loss": 0.4202,
      "step": 755
    },
    {
      "epoch": 5.24263431542461,
      "grad_norm": 1.4990637302398682,
      "learning_rate": 0.0002,
      "loss": 0.5533,
      "step": 760
    },
    {
      "epoch": 5.277296360485269,
      "grad_norm": 0.6687419414520264,
      "learning_rate": 0.0002,
      "loss": 0.3429,
      "step": 765
    },
    {
      "epoch": 5.311958405545927,
      "grad_norm": 0.5400169491767883,
      "learning_rate": 0.0002,
      "loss": 0.1759,
      "step": 770
    },
    {
      "epoch": 5.3466204506065855,
      "grad_norm": 0.39679139852523804,
      "learning_rate": 0.0002,
      "loss": 0.1395,
      "step": 775
    },
    {
      "epoch": 5.381282495667245,
      "grad_norm": 0.33043885231018066,
      "learning_rate": 0.0002,
      "loss": 0.1004,
      "step": 780
    },
    {
      "epoch": 5.415944540727903,
      "grad_norm": 3.1912200450897217,
      "learning_rate": 0.0002,
      "loss": 0.305,
      "step": 785
    },
    {
      "epoch": 5.450606585788561,
      "grad_norm": 1.2743686437606812,
      "learning_rate": 0.0002,
      "loss": 0.4876,
      "step": 790
    },
    {
      "epoch": 5.4852686308492205,
      "grad_norm": 2.9798948764801025,
      "learning_rate": 0.0002,
      "loss": 0.7476,
      "step": 795
    },
    {
      "epoch": 5.519930675909879,
      "grad_norm": 0.7342365384101868,
      "learning_rate": 0.0002,
      "loss": 0.463,
      "step": 800
    },
    {
      "epoch": 5.554592720970537,
      "grad_norm": 0.5035507678985596,
      "learning_rate": 0.0002,
      "loss": 0.2116,
      "step": 805
    },
    {
      "epoch": 5.589254766031196,
      "grad_norm": 0.4394471347332001,
      "learning_rate": 0.0002,
      "loss": 0.1568,
      "step": 810
    },
    {
      "epoch": 5.6239168110918545,
      "grad_norm": 0.383515328168869,
      "learning_rate": 0.0002,
      "loss": 0.1035,
      "step": 815
    },
    {
      "epoch": 5.658578856152513,
      "grad_norm": 2.142784357070923,
      "learning_rate": 0.0002,
      "loss": 0.3458,
      "step": 820
    },
    {
      "epoch": 5.693240901213172,
      "grad_norm": 1.2484018802642822,
      "learning_rate": 0.0002,
      "loss": 0.3576,
      "step": 825
    },
    {
      "epoch": 5.72790294627383,
      "grad_norm": 2.6863198280334473,
      "learning_rate": 0.0002,
      "loss": 0.5996,
      "step": 830
    },
    {
      "epoch": 5.7625649913344885,
      "grad_norm": 1.098381757736206,
      "learning_rate": 0.0002,
      "loss": 0.4993,
      "step": 835
    },
    {
      "epoch": 5.797227036395148,
      "grad_norm": 0.5609210133552551,
      "learning_rate": 0.0002,
      "loss": 0.2608,
      "step": 840
    },
    {
      "epoch": 5.831889081455806,
      "grad_norm": 0.5123816132545471,
      "learning_rate": 0.0002,
      "loss": 0.1799,
      "step": 845
    },
    {
      "epoch": 5.866551126516464,
      "grad_norm": 0.46399134397506714,
      "learning_rate": 0.0002,
      "loss": 0.1254,
      "step": 850
    },
    {
      "epoch": 5.9012131715771226,
      "grad_norm": 0.5089249014854431,
      "learning_rate": 0.0002,
      "loss": 0.0934,
      "step": 855
    },
    {
      "epoch": 5.935875216637782,
      "grad_norm": 1.3031930923461914,
      "learning_rate": 0.0002,
      "loss": 0.6664,
      "step": 860
    },
    {
      "epoch": 5.97053726169844,
      "grad_norm": 2.294696569442749,
      "learning_rate": 0.0002,
      "loss": 0.6034,
      "step": 865
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.738062620162964,
      "learning_rate": 0.0002,
      "loss": 0.587,
      "step": 870
    },
    {
      "epoch": 6.034662045060658,
      "grad_norm": 0.6086808443069458,
      "learning_rate": 0.0002,
      "loss": 0.252,
      "step": 875
    },
    {
      "epoch": 6.0693240901213175,
      "grad_norm": 0.4935630261898041,
      "learning_rate": 0.0002,
      "loss": 0.1223,
      "step": 880
    },
    {
      "epoch": 6.103986135181976,
      "grad_norm": 0.43656599521636963,
      "learning_rate": 0.0002,
      "loss": 0.0882,
      "step": 885
    },
    {
      "epoch": 6.138648180242634,
      "grad_norm": 0.2987945079803467,
      "learning_rate": 0.0002,
      "loss": 0.0629,
      "step": 890
    },
    {
      "epoch": 6.173310225303293,
      "grad_norm": 1.7174897193908691,
      "learning_rate": 0.0002,
      "loss": 0.4102,
      "step": 895
    },
    {
      "epoch": 6.2079722703639515,
      "grad_norm": 2.4946401119232178,
      "learning_rate": 0.0002,
      "loss": 0.2899,
      "step": 900
    },
    {
      "epoch": 6.24263431542461,
      "grad_norm": 2.8931374549865723,
      "learning_rate": 0.0002,
      "loss": 0.4676,
      "step": 905
    },
    {
      "epoch": 6.277296360485269,
      "grad_norm": 0.8096083998680115,
      "learning_rate": 0.0002,
      "loss": 0.3168,
      "step": 910
    },
    {
      "epoch": 6.311958405545927,
      "grad_norm": 0.4966631531715393,
      "learning_rate": 0.0002,
      "loss": 0.1399,
      "step": 915
    },
    {
      "epoch": 6.3466204506065855,
      "grad_norm": 0.46740466356277466,
      "learning_rate": 0.0002,
      "loss": 0.1037,
      "step": 920
    },
    {
      "epoch": 6.381282495667245,
      "grad_norm": 0.3550221920013428,
      "learning_rate": 0.0002,
      "loss": 0.0682,
      "step": 925
    },
    {
      "epoch": 6.415944540727903,
      "grad_norm": 1.7010166645050049,
      "learning_rate": 0.0002,
      "loss": 0.401,
      "step": 930
    },
    {
      "epoch": 6.450606585788561,
      "grad_norm": 1.4712696075439453,
      "learning_rate": 0.0002,
      "loss": 0.2843,
      "step": 935
    },
    {
      "epoch": 6.4852686308492205,
      "grad_norm": 1.702062964439392,
      "learning_rate": 0.0002,
      "loss": 0.5166,
      "step": 940
    },
    {
      "epoch": 6.519930675909879,
      "grad_norm": 0.6730090379714966,
      "learning_rate": 0.0002,
      "loss": 0.3467,
      "step": 945
    },
    {
      "epoch": 6.554592720970537,
      "grad_norm": 0.6367856860160828,
      "learning_rate": 0.0002,
      "loss": 0.1564,
      "step": 950
    },
    {
      "epoch": 6.589254766031196,
      "grad_norm": 0.5671469569206238,
      "learning_rate": 0.0002,
      "loss": 0.1267,
      "step": 955
    },
    {
      "epoch": 6.6239168110918545,
      "grad_norm": 0.29594796895980835,
      "learning_rate": 0.0002,
      "loss": 0.0927,
      "step": 960
    },
    {
      "epoch": 6.658578856152513,
      "grad_norm": 0.6945505738258362,
      "learning_rate": 0.0002,
      "loss": 0.0982,
      "step": 965
    },
    {
      "epoch": 6.693240901213172,
      "grad_norm": 1.2007991075515747,
      "learning_rate": 0.0002,
      "loss": 0.4829,
      "step": 970
    },
    {
      "epoch": 6.72790294627383,
      "grad_norm": 4.258643627166748,
      "learning_rate": 0.0002,
      "loss": 0.5014,
      "step": 975
    },
    {
      "epoch": 6.7625649913344885,
      "grad_norm": 1.2368519306182861,
      "learning_rate": 0.0002,
      "loss": 0.4639,
      "step": 980
    },
    {
      "epoch": 6.797227036395148,
      "grad_norm": 0.5854914784431458,
      "learning_rate": 0.0002,
      "loss": 0.1885,
      "step": 985
    },
    {
      "epoch": 6.831889081455806,
      "grad_norm": 0.433727890253067,
      "learning_rate": 0.0002,
      "loss": 0.1182,
      "step": 990
    },
    {
      "epoch": 6.866551126516464,
      "grad_norm": 0.37968766689300537,
      "learning_rate": 0.0002,
      "loss": 0.0907,
      "step": 995
    },
    {
      "epoch": 6.9012131715771226,
      "grad_norm": 0.49255871772766113,
      "learning_rate": 0.0002,
      "loss": 0.0748,
      "step": 1000
    },
    {
      "epoch": 6.935875216637782,
      "grad_norm": 0.8562117218971252,
      "learning_rate": 0.0002,
      "loss": 0.301,
      "step": 1005
    },
    {
      "epoch": 6.97053726169844,
      "grad_norm": 2.18452787399292,
      "learning_rate": 0.0002,
      "loss": 0.5265,
      "step": 1010
    },
    {
      "epoch": 7.0,
      "grad_norm": 5.248262405395508,
      "learning_rate": 0.0002,
      "loss": 0.4677,
      "step": 1015
    }
  ],
  "logging_steps": 5,
  "max_steps": 1440,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 2.366970120384307e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}