{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 248,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004032258064516129,
      "grad_norm": 23.183565139770508,
      "learning_rate": 0.0,
      "loss": 1.0275,
      "step": 1
    },
    {
      "epoch": 0.008064516129032258,
      "grad_norm": 23.37139320373535,
      "learning_rate": 6.666666666666668e-06,
      "loss": 1.0547,
      "step": 2
    },
    {
      "epoch": 0.012096774193548387,
      "grad_norm": 22.907167434692383,
      "learning_rate": 1.0566416671474378e-05,
      "loss": 1.0348,
      "step": 3
    },
    {
      "epoch": 0.016129032258064516,
      "grad_norm": 15.111400604248047,
      "learning_rate": 1.3333333333333337e-05,
      "loss": 0.6538,
      "step": 4
    },
    {
      "epoch": 0.020161290322580645,
      "grad_norm": 6.891965389251709,
      "learning_rate": 1.5479520632582417e-05,
      "loss": 0.253,
      "step": 5
    },
    {
      "epoch": 0.024193548387096774,
      "grad_norm": 5.94376802444458,
      "learning_rate": 1.7233083338141044e-05,
      "loss": 0.3932,
      "step": 6
    },
    {
      "epoch": 0.028225806451612902,
      "grad_norm": 2.6044232845306396,
      "learning_rate": 1.8715699480384028e-05,
      "loss": 0.2468,
      "step": 7
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 5.8222126960754395,
      "learning_rate": 2e-05,
      "loss": 0.3847,
      "step": 8
    },
    {
      "epoch": 0.036290322580645164,
      "grad_norm": 2.5366413593292236,
      "learning_rate": 2e-05,
      "loss": 0.306,
      "step": 9
    },
    {
      "epoch": 0.04032258064516129,
      "grad_norm": 1.6535553932189941,
      "learning_rate": 2e-05,
      "loss": 0.2243,
      "step": 10
    },
    {
      "epoch": 0.04435483870967742,
      "grad_norm": 1.9359959363937378,
      "learning_rate": 2e-05,
      "loss": 0.2214,
      "step": 11
    },
    {
      "epoch": 0.04838709677419355,
      "grad_norm": 2.255415201187134,
      "learning_rate": 2e-05,
      "loss": 0.2351,
      "step": 12
    },
    {
      "epoch": 0.05241935483870968,
      "grad_norm": 1.2205442190170288,
      "learning_rate": 2e-05,
      "loss": 0.1992,
      "step": 13
    },
    {
      "epoch": 0.056451612903225805,
      "grad_norm": 2.05025053024292,
      "learning_rate": 2e-05,
      "loss": 0.2232,
      "step": 14
    },
    {
      "epoch": 0.06048387096774194,
      "grad_norm": 1.5063331127166748,
      "learning_rate": 2e-05,
      "loss": 0.2107,
      "step": 15
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 1.1306530237197876,
      "learning_rate": 2e-05,
      "loss": 0.2015,
      "step": 16
    },
    {
      "epoch": 0.06854838709677419,
      "grad_norm": 0.8307346701622009,
      "learning_rate": 2e-05,
      "loss": 0.191,
      "step": 17
    },
    {
      "epoch": 0.07258064516129033,
      "grad_norm": 0.6416309475898743,
      "learning_rate": 2e-05,
      "loss": 0.184,
      "step": 18
    },
    {
      "epoch": 0.07661290322580645,
      "grad_norm": 1.3595116138458252,
      "learning_rate": 2e-05,
      "loss": 0.2,
      "step": 19
    },
    {
      "epoch": 0.08064516129032258,
      "grad_norm": 0.6382694840431213,
      "learning_rate": 2e-05,
      "loss": 0.1793,
      "step": 20
    },
    {
      "epoch": 0.0846774193548387,
      "grad_norm": 1.1086512804031372,
      "learning_rate": 2e-05,
      "loss": 0.1925,
      "step": 21
    },
    {
      "epoch": 0.08870967741935484,
      "grad_norm": 0.6290364861488342,
      "learning_rate": 2e-05,
      "loss": 0.1828,
      "step": 22
    },
    {
      "epoch": 0.09274193548387097,
      "grad_norm": 1.621184229850769,
      "learning_rate": 2e-05,
      "loss": 0.1849,
      "step": 23
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 1.1934734582901,
      "learning_rate": 2e-05,
      "loss": 0.1978,
      "step": 24
    },
    {
      "epoch": 0.10080645161290322,
      "grad_norm": 0.5095123648643494,
      "learning_rate": 2e-05,
      "loss": 0.1823,
      "step": 25
    },
    {
      "epoch": 0.10483870967741936,
      "grad_norm": 0.9218118786811829,
      "learning_rate": 2e-05,
      "loss": 0.191,
      "step": 26
    },
    {
      "epoch": 0.10887096774193548,
      "grad_norm": 0.7978827357292175,
      "learning_rate": 2e-05,
      "loss": 0.1766,
      "step": 27
    },
    {
      "epoch": 0.11290322580645161,
      "grad_norm": 0.8179630637168884,
      "learning_rate": 2e-05,
      "loss": 0.1868,
      "step": 28
    },
    {
      "epoch": 0.11693548387096774,
      "grad_norm": 0.5699785351753235,
      "learning_rate": 2e-05,
      "loss": 0.1869,
      "step": 29
    },
    {
      "epoch": 0.12096774193548387,
      "grad_norm": 0.7835913300514221,
      "learning_rate": 2e-05,
      "loss": 0.1973,
      "step": 30
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.5692117810249329,
      "learning_rate": 2e-05,
      "loss": 0.1759,
      "step": 31
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 0.803184449672699,
      "learning_rate": 2e-05,
      "loss": 0.1907,
      "step": 32
    },
    {
      "epoch": 0.13306451612903225,
      "grad_norm": 0.5545604228973389,
      "learning_rate": 2e-05,
      "loss": 0.1676,
      "step": 33
    },
    {
      "epoch": 0.13709677419354838,
      "grad_norm": 0.3685874342918396,
      "learning_rate": 2e-05,
      "loss": 0.1766,
      "step": 34
    },
    {
      "epoch": 0.14112903225806453,
      "grad_norm": 0.6002175807952881,
      "learning_rate": 2e-05,
      "loss": 0.1836,
      "step": 35
    },
    {
      "epoch": 0.14516129032258066,
      "grad_norm": 0.5726589560508728,
      "learning_rate": 2e-05,
      "loss": 0.1757,
      "step": 36
    },
    {
      "epoch": 0.14919354838709678,
      "grad_norm": 0.5990753769874573,
      "learning_rate": 2e-05,
      "loss": 0.1814,
      "step": 37
    },
    {
      "epoch": 0.1532258064516129,
      "grad_norm": 0.5180577039718628,
      "learning_rate": 2e-05,
      "loss": 0.1725,
      "step": 38
    },
    {
      "epoch": 0.15725806451612903,
      "grad_norm": 0.6645565629005432,
      "learning_rate": 2e-05,
      "loss": 0.1856,
      "step": 39
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 0.7106342911720276,
      "learning_rate": 2e-05,
      "loss": 0.1679,
      "step": 40
    },
    {
      "epoch": 0.16532258064516128,
      "grad_norm": 0.8131007552146912,
      "learning_rate": 2e-05,
      "loss": 0.1806,
      "step": 41
    },
    {
      "epoch": 0.1693548387096774,
      "grad_norm": 0.8143223524093628,
      "learning_rate": 2e-05,
      "loss": 0.1689,
      "step": 42
    },
    {
      "epoch": 0.17338709677419356,
      "grad_norm": 0.6998667120933533,
      "learning_rate": 2e-05,
      "loss": 0.1681,
      "step": 43
    },
    {
      "epoch": 0.1774193548387097,
      "grad_norm": 0.9026826620101929,
      "learning_rate": 2e-05,
      "loss": 0.1597,
      "step": 44
    },
    {
      "epoch": 0.1814516129032258,
      "grad_norm": 1.212770700454712,
      "learning_rate": 2e-05,
      "loss": 0.1707,
      "step": 45
    },
    {
      "epoch": 0.18548387096774194,
      "grad_norm": 0.8376269936561584,
      "learning_rate": 2e-05,
      "loss": 0.1552,
      "step": 46
    },
    {
      "epoch": 0.18951612903225806,
      "grad_norm": 0.9025837182998657,
      "learning_rate": 2e-05,
      "loss": 0.1633,
      "step": 47
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 0.9542744159698486,
      "learning_rate": 2e-05,
      "loss": 0.1749,
      "step": 48
    },
    {
      "epoch": 0.1975806451612903,
      "grad_norm": 0.7638697624206543,
      "learning_rate": 2e-05,
      "loss": 0.158,
      "step": 49
    },
    {
      "epoch": 0.20161290322580644,
      "grad_norm": 0.5949487090110779,
      "learning_rate": 2e-05,
      "loss": 0.1487,
      "step": 50
    },
    {
      "epoch": 0.2056451612903226,
      "grad_norm": 1.0373241901397705,
      "learning_rate": 2e-05,
      "loss": 0.1519,
      "step": 51
    },
    {
      "epoch": 0.20967741935483872,
      "grad_norm": 0.5316594243049622,
      "learning_rate": 2e-05,
      "loss": 0.1364,
      "step": 52
    },
    {
      "epoch": 0.21370967741935484,
      "grad_norm": 0.624768078327179,
      "learning_rate": 2e-05,
      "loss": 0.1449,
      "step": 53
    },
    {
      "epoch": 0.21774193548387097,
      "grad_norm": 0.7126561403274536,
      "learning_rate": 2e-05,
      "loss": 0.1426,
      "step": 54
    },
    {
      "epoch": 0.2217741935483871,
      "grad_norm": 1.0926051139831543,
      "learning_rate": 2e-05,
      "loss": 0.142,
      "step": 55
    },
    {
      "epoch": 0.22580645161290322,
      "grad_norm": 1.873496651649475,
      "learning_rate": 2e-05,
      "loss": 0.1578,
      "step": 56
    },
    {
      "epoch": 0.22983870967741934,
      "grad_norm": 0.8202502727508545,
      "learning_rate": 2e-05,
      "loss": 0.1462,
      "step": 57
    },
    {
      "epoch": 0.23387096774193547,
      "grad_norm": 0.6349180936813354,
      "learning_rate": 2e-05,
      "loss": 0.1326,
      "step": 58
    },
    {
      "epoch": 0.23790322580645162,
      "grad_norm": 1.0204631090164185,
      "learning_rate": 2e-05,
      "loss": 0.1385,
      "step": 59
    },
    {
      "epoch": 0.24193548387096775,
      "grad_norm": 0.8092764616012573,
      "learning_rate": 2e-05,
      "loss": 0.1341,
      "step": 60
    },
    {
      "epoch": 0.24596774193548387,
      "grad_norm": 1.0302892923355103,
      "learning_rate": 2e-05,
      "loss": 0.144,
      "step": 61
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.2825901508331299,
      "learning_rate": 2e-05,
      "loss": 0.1391,
      "step": 62
    },
    {
      "epoch": 0.2540322580645161,
      "grad_norm": 0.873502790927887,
      "learning_rate": 2e-05,
      "loss": 0.1331,
      "step": 63
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.8886832594871521,
      "learning_rate": 2e-05,
      "loss": 0.1248,
      "step": 64
    },
    {
      "epoch": 0.2620967741935484,
      "grad_norm": 0.7013624906539917,
      "learning_rate": 2e-05,
      "loss": 0.1164,
      "step": 65
    },
    {
      "epoch": 0.2661290322580645,
      "grad_norm": 0.7485561966896057,
      "learning_rate": 2e-05,
      "loss": 0.118,
      "step": 66
    },
    {
      "epoch": 0.2701612903225806,
      "grad_norm": 0.7874916791915894,
      "learning_rate": 2e-05,
      "loss": 0.1116,
      "step": 67
    },
    {
      "epoch": 0.27419354838709675,
      "grad_norm": 0.8042868375778198,
      "learning_rate": 2e-05,
      "loss": 0.1215,
      "step": 68
    },
    {
      "epoch": 0.2782258064516129,
      "grad_norm": 0.604430615901947,
      "learning_rate": 2e-05,
      "loss": 0.1109,
      "step": 69
    },
    {
      "epoch": 0.28225806451612906,
      "grad_norm": 0.976264476776123,
      "learning_rate": 2e-05,
      "loss": 0.124,
      "step": 70
    },
    {
      "epoch": 0.2862903225806452,
      "grad_norm": 1.0005311965942383,
      "learning_rate": 2e-05,
      "loss": 0.1112,
      "step": 71
    },
    {
      "epoch": 0.2903225806451613,
      "grad_norm": 0.6228518486022949,
      "learning_rate": 2e-05,
      "loss": 0.1049,
      "step": 72
    },
    {
      "epoch": 0.29435483870967744,
      "grad_norm": 0.7674490809440613,
      "learning_rate": 2e-05,
      "loss": 0.1091,
      "step": 73
    },
    {
      "epoch": 0.29838709677419356,
      "grad_norm": 1.027273416519165,
      "learning_rate": 2e-05,
      "loss": 0.1147,
      "step": 74
    },
    {
      "epoch": 0.3024193548387097,
      "grad_norm": 0.6840062737464905,
      "learning_rate": 2e-05,
      "loss": 0.0962,
      "step": 75
    },
    {
      "epoch": 0.3064516129032258,
      "grad_norm": 0.5666499137878418,
      "learning_rate": 2e-05,
      "loss": 0.0956,
      "step": 76
    },
    {
      "epoch": 0.31048387096774194,
      "grad_norm": 0.594052791595459,
      "learning_rate": 2e-05,
      "loss": 0.0968,
      "step": 77
    },
    {
      "epoch": 0.31451612903225806,
      "grad_norm": 0.7595533132553101,
      "learning_rate": 2e-05,
      "loss": 0.0927,
      "step": 78
    },
    {
      "epoch": 0.3185483870967742,
      "grad_norm": 0.7487107515335083,
      "learning_rate": 2e-05,
      "loss": 0.1027,
      "step": 79
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 0.5936404466629028,
      "learning_rate": 2e-05,
      "loss": 0.0884,
      "step": 80
    },
    {
      "epoch": 0.32661290322580644,
      "grad_norm": 0.4667339622974396,
      "learning_rate": 2e-05,
      "loss": 0.0946,
      "step": 81
    },
    {
      "epoch": 0.33064516129032256,
      "grad_norm": 0.8685793280601501,
      "learning_rate": 2e-05,
      "loss": 0.1011,
      "step": 82
    },
    {
      "epoch": 0.3346774193548387,
      "grad_norm": 0.7018740177154541,
      "learning_rate": 2e-05,
      "loss": 0.0872,
      "step": 83
    },
    {
      "epoch": 0.3387096774193548,
      "grad_norm": 1.0336928367614746,
      "learning_rate": 2e-05,
      "loss": 0.1042,
      "step": 84
    },
    {
      "epoch": 0.34274193548387094,
      "grad_norm": 0.6793813705444336,
      "learning_rate": 2e-05,
      "loss": 0.0924,
      "step": 85
    },
    {
      "epoch": 0.3467741935483871,
      "grad_norm": 1.0464022159576416,
      "learning_rate": 2e-05,
      "loss": 0.0955,
      "step": 86
    },
    {
      "epoch": 0.35080645161290325,
      "grad_norm": 0.7015179991722107,
      "learning_rate": 2e-05,
      "loss": 0.0928,
      "step": 87
    },
    {
      "epoch": 0.3548387096774194,
      "grad_norm": 0.7370674014091492,
      "learning_rate": 2e-05,
      "loss": 0.0895,
      "step": 88
    },
    {
      "epoch": 0.3588709677419355,
      "grad_norm": 0.5556283593177795,
      "learning_rate": 2e-05,
      "loss": 0.0895,
      "step": 89
    },
    {
      "epoch": 0.3629032258064516,
      "grad_norm": 0.6646509766578674,
      "learning_rate": 2e-05,
      "loss": 0.0871,
      "step": 90
    },
    {
      "epoch": 0.36693548387096775,
      "grad_norm": 0.7947157025337219,
      "learning_rate": 2e-05,
      "loss": 0.0939,
      "step": 91
    },
    {
      "epoch": 0.3709677419354839,
      "grad_norm": 0.6044544577598572,
      "learning_rate": 2e-05,
      "loss": 0.0857,
      "step": 92
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.7086596488952637,
      "learning_rate": 2e-05,
      "loss": 0.0919,
      "step": 93
    },
    {
      "epoch": 0.3790322580645161,
      "grad_norm": 0.6559664011001587,
      "learning_rate": 2e-05,
      "loss": 0.0856,
      "step": 94
    },
    {
      "epoch": 0.38306451612903225,
      "grad_norm": 0.784209132194519,
      "learning_rate": 2e-05,
      "loss": 0.0836,
      "step": 95
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 0.5902017951011658,
      "learning_rate": 2e-05,
      "loss": 0.0747,
      "step": 96
    },
    {
      "epoch": 0.3911290322580645,
      "grad_norm": 0.697828471660614,
      "learning_rate": 2e-05,
      "loss": 0.0776,
      "step": 97
    },
    {
      "epoch": 0.3951612903225806,
      "grad_norm": 0.5101798176765442,
      "learning_rate": 2e-05,
      "loss": 0.0777,
      "step": 98
    },
    {
      "epoch": 0.39919354838709675,
      "grad_norm": 0.8497079610824585,
      "learning_rate": 2e-05,
      "loss": 0.0832,
      "step": 99
    },
    {
      "epoch": 0.4032258064516129,
      "grad_norm": 0.5198425054550171,
      "learning_rate": 2e-05,
      "loss": 0.0786,
      "step": 100
    },
    {
      "epoch": 0.40725806451612906,
      "grad_norm": 0.6342234015464783,
      "learning_rate": 2e-05,
      "loss": 0.0801,
      "step": 101
    },
    {
      "epoch": 0.4112903225806452,
      "grad_norm": 0.4612491726875305,
      "learning_rate": 2e-05,
      "loss": 0.0805,
      "step": 102
    },
    {
      "epoch": 0.4153225806451613,
      "grad_norm": 0.8742281198501587,
      "learning_rate": 2e-05,
      "loss": 0.0882,
      "step": 103
    },
    {
      "epoch": 0.41935483870967744,
      "grad_norm": 0.3069051206111908,
      "learning_rate": 2e-05,
      "loss": 0.0762,
      "step": 104
    },
    {
      "epoch": 0.42338709677419356,
      "grad_norm": 0.7006452083587646,
      "learning_rate": 2e-05,
      "loss": 0.0744,
      "step": 105
    },
    {
      "epoch": 0.4274193548387097,
      "grad_norm": 0.514578640460968,
      "learning_rate": 2e-05,
      "loss": 0.0827,
      "step": 106
    },
    {
      "epoch": 0.4314516129032258,
      "grad_norm": 1.0400453805923462,
      "learning_rate": 2e-05,
      "loss": 0.0819,
      "step": 107
    },
    {
      "epoch": 0.43548387096774194,
      "grad_norm": 0.7127644419670105,
      "learning_rate": 2e-05,
      "loss": 0.083,
      "step": 108
    },
    {
      "epoch": 0.43951612903225806,
      "grad_norm": 0.617011308670044,
      "learning_rate": 2e-05,
      "loss": 0.0705,
      "step": 109
    },
    {
      "epoch": 0.4435483870967742,
      "grad_norm": 0.5836071968078613,
      "learning_rate": 2e-05,
      "loss": 0.0777,
      "step": 110
    },
    {
      "epoch": 0.4475806451612903,
      "grad_norm": 0.6622437238693237,
      "learning_rate": 2e-05,
      "loss": 0.0747,
      "step": 111
    },
    {
      "epoch": 0.45161290322580644,
      "grad_norm": 0.7056003212928772,
      "learning_rate": 2e-05,
      "loss": 0.0715,
      "step": 112
    },
    {
      "epoch": 0.45564516129032256,
      "grad_norm": 0.6626383662223816,
      "learning_rate": 2e-05,
      "loss": 0.0776,
      "step": 113
    },
    {
      "epoch": 0.4596774193548387,
      "grad_norm": 0.7465190291404724,
      "learning_rate": 2e-05,
      "loss": 0.0856,
      "step": 114
    },
    {
      "epoch": 0.4637096774193548,
      "grad_norm": 0.5531803369522095,
      "learning_rate": 2e-05,
      "loss": 0.0679,
      "step": 115
    },
    {
      "epoch": 0.46774193548387094,
      "grad_norm": 0.4788318872451782,
      "learning_rate": 2e-05,
      "loss": 0.0648,
      "step": 116
    },
    {
      "epoch": 0.4717741935483871,
      "grad_norm": 0.6184081435203552,
      "learning_rate": 2e-05,
      "loss": 0.0801,
      "step": 117
    },
    {
      "epoch": 0.47580645161290325,
      "grad_norm": 0.6424548029899597,
      "learning_rate": 2e-05,
      "loss": 0.0789,
      "step": 118
    },
    {
      "epoch": 0.4798387096774194,
      "grad_norm": 0.7118510007858276,
      "learning_rate": 2e-05,
      "loss": 0.0735,
      "step": 119
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 0.4841958284378052,
      "learning_rate": 2e-05,
      "loss": 0.061,
      "step": 120
    },
    {
      "epoch": 0.4879032258064516,
      "grad_norm": 0.8846139311790466,
      "learning_rate": 2e-05,
      "loss": 0.0747,
      "step": 121
    },
    {
      "epoch": 0.49193548387096775,
      "grad_norm": 0.5449007153511047,
      "learning_rate": 2e-05,
      "loss": 0.0711,
      "step": 122
    },
    {
      "epoch": 0.4959677419354839,
      "grad_norm": 0.767926037311554,
      "learning_rate": 2e-05,
      "loss": 0.0736,
      "step": 123
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.5696377158164978,
      "learning_rate": 2e-05,
      "loss": 0.0671,
      "step": 124
    },
    {
      "epoch": 0.5040322580645161,
      "grad_norm": 0.6430863738059998,
      "learning_rate": 2e-05,
      "loss": 0.0679,
      "step": 125
    },
    {
      "epoch": 0.5080645161290323,
      "grad_norm": 0.7779257893562317,
      "learning_rate": 2e-05,
      "loss": 0.0713,
      "step": 126
    },
    {
      "epoch": 0.5120967741935484,
      "grad_norm": 0.7092922329902649,
      "learning_rate": 2e-05,
      "loss": 0.0765,
      "step": 127
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.5975173711776733,
      "learning_rate": 2e-05,
      "loss": 0.066,
      "step": 128
    },
    {
      "epoch": 0.5201612903225806,
      "grad_norm": 0.5376009941101074,
      "learning_rate": 2e-05,
      "loss": 0.0642,
      "step": 129
    },
    {
      "epoch": 0.5241935483870968,
      "grad_norm": 0.4406221807003021,
      "learning_rate": 2e-05,
      "loss": 0.0594,
      "step": 130
    },
    {
      "epoch": 0.5282258064516129,
      "grad_norm": 0.530074954032898,
      "learning_rate": 2e-05,
      "loss": 0.0731,
      "step": 131
    },
    {
      "epoch": 0.532258064516129,
      "grad_norm": 0.5786536335945129,
      "learning_rate": 2e-05,
      "loss": 0.06,
      "step": 132
    },
    {
      "epoch": 0.5362903225806451,
      "grad_norm": 0.5356053113937378,
      "learning_rate": 2e-05,
      "loss": 0.0659,
      "step": 133
    },
    {
      "epoch": 0.5403225806451613,
      "grad_norm": 0.3962647318840027,
      "learning_rate": 2e-05,
      "loss": 0.0618,
      "step": 134
    },
    {
      "epoch": 0.5443548387096774,
      "grad_norm": 0.3608771860599518,
      "learning_rate": 2e-05,
      "loss": 0.0643,
      "step": 135
    },
    {
      "epoch": 0.5483870967741935,
      "grad_norm": 0.5634734034538269,
      "learning_rate": 2e-05,
      "loss": 0.0615,
      "step": 136
    },
    {
      "epoch": 0.5524193548387096,
      "grad_norm": 0.5571008324623108,
      "learning_rate": 2e-05,
      "loss": 0.0663,
      "step": 137
    },
    {
      "epoch": 0.5564516129032258,
      "grad_norm": 0.5018740296363831,
      "learning_rate": 2e-05,
      "loss": 0.0613,
      "step": 138
    },
    {
      "epoch": 0.5604838709677419,
      "grad_norm": 0.664557933807373,
      "learning_rate": 2e-05,
      "loss": 0.067,
      "step": 139
    },
    {
      "epoch": 0.5645161290322581,
      "grad_norm": 0.6537980437278748,
      "learning_rate": 2e-05,
      "loss": 0.0593,
      "step": 140
    },
    {
      "epoch": 0.5685483870967742,
      "grad_norm": 0.8715218901634216,
      "learning_rate": 2e-05,
      "loss": 0.0693,
      "step": 141
    },
    {
      "epoch": 0.5725806451612904,
      "grad_norm": 0.5582900047302246,
      "learning_rate": 2e-05,
      "loss": 0.0605,
      "step": 142
    },
    {
      "epoch": 0.5766129032258065,
      "grad_norm": 0.4657461941242218,
      "learning_rate": 2e-05,
      "loss": 0.0594,
      "step": 143
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 0.5373775959014893,
      "learning_rate": 2e-05,
      "loss": 0.07,
      "step": 144
    },
    {
      "epoch": 0.5846774193548387,
      "grad_norm": 0.4283169209957123,
      "learning_rate": 2e-05,
      "loss": 0.0536,
      "step": 145
    },
    {
      "epoch": 0.5887096774193549,
      "grad_norm": 0.6403968930244446,
      "learning_rate": 2e-05,
      "loss": 0.0667,
      "step": 146
    },
    {
      "epoch": 0.592741935483871,
      "grad_norm": 0.32464203238487244,
      "learning_rate": 2e-05,
      "loss": 0.0548,
      "step": 147
    },
    {
      "epoch": 0.5967741935483871,
      "grad_norm": 0.648133397102356,
      "learning_rate": 2e-05,
      "loss": 0.0612,
      "step": 148
    },
    {
      "epoch": 0.6008064516129032,
      "grad_norm": 0.47770267724990845,
      "learning_rate": 2e-05,
      "loss": 0.0544,
      "step": 149
    },
    {
      "epoch": 0.6048387096774194,
      "grad_norm": 0.9105427861213684,
      "learning_rate": 2e-05,
      "loss": 0.0684,
      "step": 150
    },
    {
      "epoch": 0.6088709677419355,
      "grad_norm": 0.6342010498046875,
      "learning_rate": 2e-05,
      "loss": 0.0601,
      "step": 151
    },
    {
      "epoch": 0.6129032258064516,
      "grad_norm": 0.8317110538482666,
      "learning_rate": 2e-05,
      "loss": 0.0584,
      "step": 152
    },
    {
      "epoch": 0.6169354838709677,
      "grad_norm": 0.57545405626297,
      "learning_rate": 2e-05,
      "loss": 0.059,
      "step": 153
    },
    {
      "epoch": 0.6209677419354839,
      "grad_norm": 0.46788084506988525,
      "learning_rate": 2e-05,
      "loss": 0.0552,
      "step": 154
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.5528416633605957,
      "learning_rate": 2e-05,
      "loss": 0.0579,
      "step": 155
    },
    {
      "epoch": 0.6290322580645161,
      "grad_norm": 0.45801204442977905,
      "learning_rate": 2e-05,
      "loss": 0.0539,
      "step": 156
    },
    {
      "epoch": 0.6330645161290323,
      "grad_norm": 0.47493261098861694,
      "learning_rate": 2e-05,
      "loss": 0.0585,
      "step": 157
    },
    {
      "epoch": 0.6370967741935484,
      "grad_norm": 0.46749451756477356,
      "learning_rate": 2e-05,
      "loss": 0.0537,
      "step": 158
    },
    {
      "epoch": 0.6411290322580645,
      "grad_norm": 0.5712094306945801,
      "learning_rate": 2e-05,
      "loss": 0.0636,
      "step": 159
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.474437952041626,
      "learning_rate": 2e-05,
      "loss": 0.0539,
      "step": 160
    },
    {
      "epoch": 0.6491935483870968,
      "grad_norm": 0.5955020785331726,
      "learning_rate": 2e-05,
      "loss": 0.0686,
      "step": 161
    },
    {
      "epoch": 0.6532258064516129,
      "grad_norm": 0.5444841980934143,
      "learning_rate": 2e-05,
      "loss": 0.0514,
      "step": 162
    },
    {
      "epoch": 0.657258064516129,
      "grad_norm": 0.585702657699585,
      "learning_rate": 2e-05,
      "loss": 0.057,
      "step": 163
    },
    {
      "epoch": 0.6612903225806451,
      "grad_norm": 0.6098143458366394,
      "learning_rate": 2e-05,
      "loss": 0.0624,
      "step": 164
    },
    {
      "epoch": 0.6653225806451613,
      "grad_norm": 0.5105492472648621,
      "learning_rate": 2e-05,
      "loss": 0.0524,
      "step": 165
    },
    {
      "epoch": 0.6693548387096774,
      "grad_norm": 0.3543269634246826,
      "learning_rate": 2e-05,
      "loss": 0.0427,
      "step": 166
    },
    {
      "epoch": 0.6733870967741935,
      "grad_norm": 0.40186411142349243,
      "learning_rate": 2e-05,
      "loss": 0.0513,
      "step": 167
    },
    {
      "epoch": 0.6774193548387096,
      "grad_norm": 0.4863409101963043,
      "learning_rate": 2e-05,
      "loss": 0.0615,
      "step": 168
    },
    {
      "epoch": 0.6814516129032258,
      "grad_norm": 0.35418546199798584,
      "learning_rate": 2e-05,
      "loss": 0.0534,
      "step": 169
    },
    {
      "epoch": 0.6854838709677419,
      "grad_norm": 0.4265013039112091,
      "learning_rate": 2e-05,
      "loss": 0.0424,
      "step": 170
    },
    {
      "epoch": 0.6895161290322581,
      "grad_norm": 0.4792309105396271,
      "learning_rate": 2e-05,
      "loss": 0.0534,
      "step": 171
    },
    {
      "epoch": 0.6935483870967742,
      "grad_norm": 0.9275990724563599,
      "learning_rate": 2e-05,
      "loss": 0.0605,
      "step": 172
    },
    {
      "epoch": 0.6975806451612904,
      "grad_norm": 0.5802022218704224,
      "learning_rate": 2e-05,
      "loss": 0.0541,
      "step": 173
    },
    {
      "epoch": 0.7016129032258065,
      "grad_norm": 0.8620706796646118,
      "learning_rate": 2e-05,
      "loss": 0.0617,
      "step": 174
    },
    {
      "epoch": 0.7056451612903226,
      "grad_norm": 0.6036432981491089,
      "learning_rate": 2e-05,
      "loss": 0.0626,
      "step": 175
    },
    {
      "epoch": 0.7096774193548387,
      "grad_norm": 0.5247609615325928,
      "learning_rate": 2e-05,
      "loss": 0.0553,
      "step": 176
    },
    {
      "epoch": 0.7137096774193549,
      "grad_norm": 0.5166157484054565,
      "learning_rate": 2e-05,
      "loss": 0.0549,
      "step": 177
    },
    {
      "epoch": 0.717741935483871,
      "grad_norm": 0.4395121932029724,
      "learning_rate": 2e-05,
      "loss": 0.0526,
      "step": 178
    },
    {
      "epoch": 0.7217741935483871,
      "grad_norm": 0.47025758028030396,
      "learning_rate": 2e-05,
      "loss": 0.0558,
      "step": 179
    },
    {
      "epoch": 0.7258064516129032,
      "grad_norm": 0.5386791229248047,
      "learning_rate": 2e-05,
      "loss": 0.0539,
      "step": 180
    },
    {
      "epoch": 0.7298387096774194,
      "grad_norm": 0.5612148642539978,
      "learning_rate": 2e-05,
      "loss": 0.0591,
      "step": 181
    },
    {
      "epoch": 0.7338709677419355,
      "grad_norm": 0.4585655927658081,
      "learning_rate": 2e-05,
      "loss": 0.0546,
      "step": 182
    },
    {
      "epoch": 0.7379032258064516,
      "grad_norm": 0.5998373627662659,
      "learning_rate": 2e-05,
      "loss": 0.0583,
      "step": 183
    },
    {
      "epoch": 0.7419354838709677,
      "grad_norm": 0.38647782802581787,
      "learning_rate": 2e-05,
      "loss": 0.0494,
      "step": 184
    },
    {
      "epoch": 0.7459677419354839,
      "grad_norm": 0.567383348941803,
      "learning_rate": 2e-05,
      "loss": 0.0487,
      "step": 185
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.5236309766769409,
      "learning_rate": 2e-05,
      "loss": 0.0552,
      "step": 186
    },
    {
      "epoch": 0.7540322580645161,
      "grad_norm": 0.3990425765514374,
      "learning_rate": 2e-05,
      "loss": 0.0512,
      "step": 187
    },
    {
      "epoch": 0.7580645161290323,
      "grad_norm": 0.5519928336143494,
      "learning_rate": 2e-05,
      "loss": 0.0449,
      "step": 188
    },
    {
      "epoch": 0.7620967741935484,
      "grad_norm": 0.43356701731681824,
      "learning_rate": 2e-05,
      "loss": 0.0413,
      "step": 189
    },
    {
      "epoch": 0.7661290322580645,
      "grad_norm": 0.46121910214424133,
      "learning_rate": 2e-05,
      "loss": 0.0441,
      "step": 190
    },
    {
      "epoch": 0.7701612903225806,
      "grad_norm": 0.5286686420440674,
      "learning_rate": 2e-05,
      "loss": 0.0506,
      "step": 191
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.6215876340866089,
      "learning_rate": 2e-05,
      "loss": 0.0538,
      "step": 192
    },
    {
      "epoch": 0.7782258064516129,
      "grad_norm": 0.7031762003898621,
      "learning_rate": 2e-05,
      "loss": 0.0507,
      "step": 193
    },
    {
      "epoch": 0.782258064516129,
      "grad_norm": 0.4998103678226471,
      "learning_rate": 2e-05,
      "loss": 0.055,
      "step": 194
    },
    {
      "epoch": 0.7862903225806451,
      "grad_norm": 0.4593054950237274,
      "learning_rate": 2e-05,
      "loss": 0.0468,
      "step": 195
    },
    {
      "epoch": 0.7903225806451613,
      "grad_norm": 0.6475517749786377,
      "learning_rate": 2e-05,
      "loss": 0.0559,
      "step": 196
    },
    {
      "epoch": 0.7943548387096774,
      "grad_norm": 0.523537278175354,
      "learning_rate": 2e-05,
      "loss": 0.0464,
      "step": 197
    },
    {
      "epoch": 0.7983870967741935,
      "grad_norm": 0.6223071813583374,
      "learning_rate": 2e-05,
      "loss": 0.0464,
      "step": 198
    },
    {
      "epoch": 0.8024193548387096,
      "grad_norm": 0.40836507081985474,
      "learning_rate": 2e-05,
      "loss": 0.049,
      "step": 199
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 0.6119136810302734,
      "learning_rate": 2e-05,
      "loss": 0.0536,
      "step": 200
    },
    {
      "epoch": 0.8104838709677419,
      "grad_norm": 0.4265545904636383,
      "learning_rate": 2e-05,
      "loss": 0.0502,
      "step": 201
    },
    {
      "epoch": 0.8145161290322581,
      "grad_norm": 0.44581177830696106,
      "learning_rate": 2e-05,
      "loss": 0.0471,
      "step": 202
    },
    {
      "epoch": 0.8185483870967742,
      "grad_norm": 0.4306443929672241,
      "learning_rate": 2e-05,
      "loss": 0.0444,
      "step": 203
    },
    {
      "epoch": 0.8225806451612904,
      "grad_norm": 0.402327299118042,
      "learning_rate": 2e-05,
      "loss": 0.0415,
      "step": 204
    },
    {
      "epoch": 0.8266129032258065,
      "grad_norm": 0.4216252863407135,
      "learning_rate": 2e-05,
      "loss": 0.0465,
      "step": 205
    },
    {
      "epoch": 0.8306451612903226,
      "grad_norm": 0.3738255202770233,
      "learning_rate": 2e-05,
      "loss": 0.0415,
      "step": 206
    },
    {
      "epoch": 0.8346774193548387,
      "grad_norm": 0.5387892723083496,
      "learning_rate": 2e-05,
      "loss": 0.0543,
      "step": 207
    },
    {
      "epoch": 0.8387096774193549,
      "grad_norm": 0.5584475994110107,
      "learning_rate": 2e-05,
      "loss": 0.0457,
      "step": 208
    },
    {
      "epoch": 0.842741935483871,
      "grad_norm": 0.5456405878067017,
      "learning_rate": 2e-05,
      "loss": 0.048,
      "step": 209
    },
    {
      "epoch": 0.8467741935483871,
      "grad_norm": 0.5054622888565063,
      "learning_rate": 2e-05,
      "loss": 0.0476,
      "step": 210
    },
    {
      "epoch": 0.8508064516129032,
      "grad_norm": 0.41379377245903015,
      "learning_rate": 2e-05,
      "loss": 0.0436,
      "step": 211
    },
    {
      "epoch": 0.8548387096774194,
      "grad_norm": 0.3779892921447754,
      "learning_rate": 2e-05,
      "loss": 0.0478,
      "step": 212
    },
    {
      "epoch": 0.8588709677419355,
      "grad_norm": 0.4135122001171112,
      "learning_rate": 2e-05,
      "loss": 0.0422,
      "step": 213
    },
    {
      "epoch": 0.8629032258064516,
      "grad_norm": 0.5435640215873718,
      "learning_rate": 2e-05,
      "loss": 0.0484,
      "step": 214
    },
    {
      "epoch": 0.8669354838709677,
      "grad_norm": 0.5836952924728394,
      "learning_rate": 2e-05,
      "loss": 0.0493,
      "step": 215
    },
    {
      "epoch": 0.8709677419354839,
      "grad_norm": 0.4919867515563965,
      "learning_rate": 2e-05,
      "loss": 0.0503,
      "step": 216
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.4889490008354187,
      "learning_rate": 2e-05,
      "loss": 0.0475,
      "step": 217
    },
    {
      "epoch": 0.8790322580645161,
      "grad_norm": 0.4471587538719177,
      "learning_rate": 2e-05,
      "loss": 0.0381,
      "step": 218
    },
    {
      "epoch": 0.8830645161290323,
      "grad_norm": 0.40294429659843445,
      "learning_rate": 2e-05,
      "loss": 0.0438,
      "step": 219
    },
    {
      "epoch": 0.8870967741935484,
      "grad_norm": 0.46678218245506287,
      "learning_rate": 2e-05,
      "loss": 0.0442,
      "step": 220
    },
    {
      "epoch": 0.8911290322580645,
      "grad_norm": 0.622652530670166,
      "learning_rate": 2e-05,
      "loss": 0.0412,
      "step": 221
    },
    {
      "epoch": 0.8951612903225806,
      "grad_norm": 0.41154831647872925,
      "learning_rate": 2e-05,
      "loss": 0.0451,
      "step": 222
    },
    {
      "epoch": 0.8991935483870968,
      "grad_norm": 0.36561766266822815,
      "learning_rate": 2e-05,
      "loss": 0.0453,
      "step": 223
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 0.619911789894104,
      "learning_rate": 2e-05,
      "loss": 0.0481,
      "step": 224
    },
    {
      "epoch": 0.907258064516129,
      "grad_norm": 0.543843686580658,
      "learning_rate": 2e-05,
      "loss": 0.043,
      "step": 225
    },
    {
      "epoch": 0.9112903225806451,
      "grad_norm": 0.546393871307373,
      "learning_rate": 2e-05,
      "loss": 0.0435,
      "step": 226
    },
    {
      "epoch": 0.9153225806451613,
      "grad_norm": 0.3940606713294983,
      "learning_rate": 2e-05,
      "loss": 0.0406,
      "step": 227
    },
    {
      "epoch": 0.9193548387096774,
      "grad_norm": 0.31918397545814514,
      "learning_rate": 2e-05,
      "loss": 0.0384,
      "step": 228
    },
    {
      "epoch": 0.9233870967741935,
      "grad_norm": 0.35918116569519043,
      "learning_rate": 2e-05,
      "loss": 0.0366,
      "step": 229
    },
    {
      "epoch": 0.9274193548387096,
      "grad_norm": 0.39295467734336853,
      "learning_rate": 2e-05,
      "loss": 0.0395,
      "step": 230
    },
    {
      "epoch": 0.9314516129032258,
      "grad_norm": 0.34643733501434326,
      "learning_rate": 2e-05,
      "loss": 0.0405,
      "step": 231
    },
    {
      "epoch": 0.9354838709677419,
      "grad_norm": 0.3488601744174957,
      "learning_rate": 2e-05,
      "loss": 0.0435,
      "step": 232
    },
    {
      "epoch": 0.9395161290322581,
      "grad_norm": 0.4448557496070862,
      "learning_rate": 2e-05,
      "loss": 0.0459,
      "step": 233
    },
    {
      "epoch": 0.9435483870967742,
      "grad_norm": 0.4407562017440796,
      "learning_rate": 2e-05,
      "loss": 0.0447,
      "step": 234
    },
    {
      "epoch": 0.9475806451612904,
      "grad_norm": 0.5757035613059998,
      "learning_rate": 2e-05,
      "loss": 0.0458,
      "step": 235
    },
    {
      "epoch": 0.9516129032258065,
      "grad_norm": 0.29268836975097656,
      "learning_rate": 2e-05,
      "loss": 0.0441,
      "step": 236
    },
    {
      "epoch": 0.9556451612903226,
      "grad_norm": 0.39647752046585083,
      "learning_rate": 2e-05,
      "loss": 0.0382,
      "step": 237
    },
    {
      "epoch": 0.9596774193548387,
      "grad_norm": 0.4112660884857178,
      "learning_rate": 2e-05,
      "loss": 0.0382,
      "step": 238
    },
    {
      "epoch": 0.9637096774193549,
      "grad_norm": 0.4475345313549042,
      "learning_rate": 2e-05,
      "loss": 0.0458,
      "step": 239
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 0.26978054642677307,
      "learning_rate": 2e-05,
      "loss": 0.0419,
      "step": 240
    },
    {
      "epoch": 0.9717741935483871,
      "grad_norm": 0.4117030203342438,
      "learning_rate": 2e-05,
      "loss": 0.043,
      "step": 241
    },
    {
      "epoch": 0.9758064516129032,
      "grad_norm": 0.28733769059181213,
      "learning_rate": 2e-05,
      "loss": 0.0387,
      "step": 242
    },
    {
      "epoch": 0.9798387096774194,
      "grad_norm": 0.32847997546195984,
      "learning_rate": 2e-05,
      "loss": 0.0407,
      "step": 243
    },
    {
      "epoch": 0.9838709677419355,
      "grad_norm": 0.4303770661354065,
      "learning_rate": 2e-05,
      "loss": 0.0417,
      "step": 244
    },
    {
      "epoch": 0.9879032258064516,
      "grad_norm": 0.36009445786476135,
      "learning_rate": 2e-05,
      "loss": 0.0391,
      "step": 245
    },
    {
      "epoch": 0.9919354838709677,
      "grad_norm": 0.46317991614341736,
      "learning_rate": 2e-05,
      "loss": 0.0477,
      "step": 246
    },
    {
      "epoch": 0.9959677419354839,
      "grad_norm": 0.48081448674201965,
      "learning_rate": 2e-05,
      "loss": 0.035,
      "step": 247
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3577556908130646,
      "learning_rate": 2e-05,
      "loss": 0.0435,
      "step": 248
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 248,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 284755222462464.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}