{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1846153846153846,
  "eval_steps": 500,
  "global_step": 180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.0638142824172974,
      "learning_rate": 0.0,
      "loss": 1.0777,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.9542151689529419,
      "learning_rate": 9.56e-05,
      "loss": 1.1025,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.0668847560882568,
      "learning_rate": 0.0001912,
      "loss": 1.0405,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.0646922588348389,
      "learning_rate": 0.0002868,
      "loss": 0.9056,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6475369334220886,
      "learning_rate": 0.0003824,
      "loss": 0.8513,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.653504490852356,
      "learning_rate": 0.000478,
      "loss": 0.9432,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5652804374694824,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.8951,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.38114824891090393,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8546,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.3202402591705322,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.9013,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.3632391095161438,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.7981,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.38180795311927795,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8034,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.44034814834594727,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.8194,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5649089217185974,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.7964,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.4905894994735718,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.7767,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5945530533790588,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.7485,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.47223448753356934,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.7412,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.4855833053588867,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.7992,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.420284628868103,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7427,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.517633855342865,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.7918,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.434706449508667,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.7891,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3698730766773224,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.7076,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3561922609806061,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.7893,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3815233111381531,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7999,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.38611900806427,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.7928,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.29186370968818665,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.724,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3245350420475006,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7503,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3803184926509857,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7455,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3178353011608124,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.7207,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.4353942573070526,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.8268,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3097940981388092,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.6621,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3318345546722412,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.7092,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.31531524658203125,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.7668,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3566637933254242,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.7545,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.36444291472435,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.8064,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3560720980167389,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.7774,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3715183734893799,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.7131,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.2921788692474365,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.8009,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.29083380103111267,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.7223,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3140243887901306,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.7196,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3676493465900421,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.7143,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3598462641239166,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.7474,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3195889890193939,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.7229,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.30827897787094116,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.7428,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.38703453540802,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.7169,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.28942254185676575,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.7456,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.35373979806900024,
      "learning_rate": 0.0004356053215077605,
      "loss": 0.7703,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3619854748249054,
      "learning_rate": 0.00043454545454545455,
      "loss": 0.6991,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.3936954438686371,
      "learning_rate": 0.0004334855875831486,
      "loss": 0.7505,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.31419533491134644,
      "learning_rate": 0.0004324257206208426,
      "loss": 0.7218,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.31622064113616943,
      "learning_rate": 0.0004313658536585366,
      "loss": 0.7133,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.31881847977638245,
      "learning_rate": 0.00043030598669623066,
      "loss": 0.7015,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.29825660586357117,
      "learning_rate": 0.0004292461197339246,
      "loss": 0.7513,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.28996437788009644,
      "learning_rate": 0.00042818625277161863,
      "loss": 0.7417,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.317898690700531,
      "learning_rate": 0.00042712638580931267,
      "loss": 0.7547,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.35207676887512207,
      "learning_rate": 0.00042606651884700666,
      "loss": 0.8215,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.2996538579463959,
      "learning_rate": 0.0004250066518847007,
      "loss": 0.7897,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.35331282019615173,
      "learning_rate": 0.00042394678492239474,
      "loss": 0.7466,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.30339422821998596,
      "learning_rate": 0.00042288691796008867,
      "loss": 0.7079,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.35229793190956116,
      "learning_rate": 0.0004218270509977827,
      "loss": 0.7322,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3471188545227051,
      "learning_rate": 0.00042076718403547675,
      "loss": 0.6908,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.384351521730423,
      "learning_rate": 0.00041970731707317074,
      "loss": 0.6937,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.34261906147003174,
      "learning_rate": 0.0004186474501108648,
      "loss": 0.694,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.36659127473831177,
      "learning_rate": 0.0004175875831485588,
      "loss": 0.7186,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3876580595970154,
      "learning_rate": 0.00041652771618625275,
      "loss": 0.7474,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3435872495174408,
      "learning_rate": 0.0004154678492239468,
      "loss": 0.7313,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.2954373061656952,
      "learning_rate": 0.00041440798226164083,
      "loss": 0.6693,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2931239604949951,
      "learning_rate": 0.0004133481152993348,
      "loss": 0.7175,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.37997666001319885,
      "learning_rate": 0.00041228824833702886,
      "loss": 0.704,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3305527865886688,
      "learning_rate": 0.00041122838137472285,
      "loss": 0.7234,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.33284375071525574,
      "learning_rate": 0.00041016851441241683,
      "loss": 0.6931,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.32701659202575684,
      "learning_rate": 0.00040910864745011087,
      "loss": 0.7191,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.32257601618766785,
      "learning_rate": 0.00040804878048780486,
      "loss": 0.6495,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.34117209911346436,
      "learning_rate": 0.0004069889135254989,
      "loss": 0.7386,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.41902703046798706,
      "learning_rate": 0.00040592904656319294,
      "loss": 0.7807,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3014705181121826,
      "learning_rate": 0.0004048691796008869,
      "loss": 0.6529,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.34272533655166626,
      "learning_rate": 0.00040380931263858097,
      "loss": 0.7318,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3316797614097595,
      "learning_rate": 0.00040274944567627495,
      "loss": 0.6452,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.290902704000473,
      "learning_rate": 0.00040168957871396894,
      "loss": 0.742,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.34589096903800964,
      "learning_rate": 0.000400629711751663,
      "loss": 0.7207,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.35719630122184753,
      "learning_rate": 0.000399569844789357,
      "loss": 0.7156,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.36912935972213745,
      "learning_rate": 0.000398509977827051,
      "loss": 0.7168,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3709248900413513,
      "learning_rate": 0.00039745011086474505,
      "loss": 0.7413,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3554258942604065,
      "learning_rate": 0.00039639024390243904,
      "loss": 0.7422,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.2682874798774719,
      "learning_rate": 0.000395330376940133,
      "loss": 0.6487,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.275944322347641,
      "learning_rate": 0.00039427050997782706,
      "loss": 0.7031,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3202199935913086,
      "learning_rate": 0.0003932106430155211,
      "loss": 0.6992,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3686879575252533,
      "learning_rate": 0.0003921507760532151,
      "loss": 0.7499,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.303440660238266,
      "learning_rate": 0.00039109090909090913,
      "loss": 0.7126,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3335700035095215,
      "learning_rate": 0.0003900310421286031,
      "loss": 0.782,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.33381161093711853,
      "learning_rate": 0.0003889711751662971,
      "loss": 0.6969,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.30890610814094543,
      "learning_rate": 0.00038791130820399114,
      "loss": 0.7082,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3305893540382385,
      "learning_rate": 0.0003868514412416852,
      "loss": 0.7532,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.29973316192626953,
      "learning_rate": 0.00038579157427937917,
      "loss": 0.6992,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.2805730402469635,
      "learning_rate": 0.0003847317073170732,
      "loss": 0.7513,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.29244521260261536,
      "learning_rate": 0.0003836718403547672,
      "loss": 0.7227,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.2936287224292755,
      "learning_rate": 0.0003826119733924612,
      "loss": 0.7598,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.30633246898651123,
      "learning_rate": 0.0003815521064301552,
      "loss": 0.6596,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.3642038404941559,
      "learning_rate": 0.00038049223946784927,
      "loss": 0.7832,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.3244490921497345,
      "learning_rate": 0.00037943237250554325,
      "loss": 0.6916,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3080962896347046,
      "learning_rate": 0.0003783725055432373,
      "loss": 0.6874,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.340778648853302,
      "learning_rate": 0.0003773126385809313,
      "loss": 0.8066,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.3969302177429199,
      "learning_rate": 0.00037625277161862527,
      "loss": 0.726,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.30715158581733704,
      "learning_rate": 0.0003751929046563193,
      "loss": 0.7383,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.38129615783691406,
      "learning_rate": 0.00037413303769401335,
      "loss": 0.7091,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.33120641112327576,
      "learning_rate": 0.00037307317073170733,
      "loss": 0.7248,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.3293302059173584,
      "learning_rate": 0.0003720133037694014,
      "loss": 0.5786,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.32738253474235535,
      "learning_rate": 0.00037095343680709536,
      "loss": 0.7797,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.31135183572769165,
      "learning_rate": 0.00036989356984478935,
      "loss": 0.6484,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.40488898754119873,
      "learning_rate": 0.0003688337028824834,
      "loss": 0.7333,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.33448660373687744,
      "learning_rate": 0.0003677738359201774,
      "loss": 0.7262,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.38866227865219116,
      "learning_rate": 0.0003667139689578714,
      "loss": 0.6933,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.3379201591014862,
      "learning_rate": 0.00036565410199556546,
      "loss": 0.6609,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.33066609501838684,
      "learning_rate": 0.0003645942350332594,
      "loss": 0.725,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.2952742278575897,
      "learning_rate": 0.00036353436807095343,
      "loss": 0.6916,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3941051661968231,
      "learning_rate": 0.00036247450110864747,
      "loss": 0.7429,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3148791491985321,
      "learning_rate": 0.00036141463414634146,
      "loss": 0.7121,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3531208336353302,
      "learning_rate": 0.0003603547671840355,
      "loss": 0.7297,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3178044855594635,
      "learning_rate": 0.00035929490022172954,
      "loss": 0.7168,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.30421027541160583,
      "learning_rate": 0.00035823503325942347,
      "loss": 0.7223,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3736768364906311,
      "learning_rate": 0.0003571751662971175,
      "loss": 0.6606,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.3562946617603302,
      "learning_rate": 0.00035611529933481155,
      "loss": 0.7329,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.3355368375778198,
      "learning_rate": 0.00035505543237250554,
      "loss": 0.6589,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3533897399902344,
      "learning_rate": 0.0003539955654101996,
      "loss": 0.6781,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.31134122610092163,
      "learning_rate": 0.0003529356984478936,
      "loss": 0.6875,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3257146179676056,
      "learning_rate": 0.00035187583148558755,
      "loss": 0.693,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.355998694896698,
      "learning_rate": 0.0003508159645232816,
      "loss": 0.7246,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.30442821979522705,
      "learning_rate": 0.00034975609756097563,
      "loss": 0.7177,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.2803910970687866,
      "learning_rate": 0.0003486962305986696,
      "loss": 0.7422,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3258972465991974,
      "learning_rate": 0.00034763636363636366,
      "loss": 0.7031,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.382231205701828,
      "learning_rate": 0.0003465764966740577,
      "loss": 0.7223,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3049597144126892,
      "learning_rate": 0.00034551662971175163,
      "loss": 0.7557,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.34174099564552307,
      "learning_rate": 0.00034445676274944567,
      "loss": 0.729,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.348481684923172,
      "learning_rate": 0.0003433968957871397,
      "loss": 0.7002,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.28441721200942993,
      "learning_rate": 0.0003423370288248337,
      "loss": 0.7053,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3341362178325653,
      "learning_rate": 0.00034127716186252774,
      "loss": 0.7317,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.3288741409778595,
      "learning_rate": 0.0003402172949002218,
      "loss": 0.7089,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3161088526248932,
      "learning_rate": 0.00033915742793791577,
      "loss": 0.6842,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3017628788948059,
      "learning_rate": 0.00033809756097560975,
      "loss": 0.6552,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.2661060690879822,
      "learning_rate": 0.0003370376940133038,
      "loss": 0.7478,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.31222012639045715,
      "learning_rate": 0.0003359778270509978,
      "loss": 0.7552,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.43476974964141846,
      "learning_rate": 0.0003349179600886918,
      "loss": 0.758,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.3367742598056793,
      "learning_rate": 0.00033385809312638586,
      "loss": 0.7794,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3539772927761078,
      "learning_rate": 0.00033279822616407985,
      "loss": 0.7972,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.28672459721565247,
      "learning_rate": 0.00033173835920177384,
      "loss": 0.7016,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.28496575355529785,
      "learning_rate": 0.0003306784922394679,
      "loss": 0.7164,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.2734069228172302,
      "learning_rate": 0.00032961862527716186,
      "loss": 0.8092,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.26828694343566895,
      "learning_rate": 0.0003285587583148559,
      "loss": 0.7474,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.32626521587371826,
      "learning_rate": 0.00032749889135254994,
      "loss": 0.7146,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3634294271469116,
      "learning_rate": 0.00032643902439024393,
      "loss": 0.7179,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.30671507120132446,
      "learning_rate": 0.0003253791574279379,
      "loss": 0.7103,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.3247479498386383,
      "learning_rate": 0.0003243192904656319,
      "loss": 0.7221,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.42680439352989197,
      "learning_rate": 0.00032325942350332594,
      "loss": 0.7161,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.36276939511299133,
      "learning_rate": 0.00032219955654102,
      "loss": 0.7322,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3108954131603241,
      "learning_rate": 0.00032113968957871397,
      "loss": 0.673,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3481237292289734,
      "learning_rate": 0.000320079822616408,
      "loss": 0.6863,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.4196075201034546,
      "learning_rate": 0.000319019955654102,
      "loss": 0.6962,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.3725369870662689,
      "learning_rate": 0.000317960088691796,
      "loss": 0.6477,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3431801497936249,
      "learning_rate": 0.00031690022172949,
      "loss": 0.7138,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.352556973695755,
      "learning_rate": 0.00031584035476718407,
      "loss": 0.696,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3816937208175659,
      "learning_rate": 0.00031478048780487805,
      "loss": 0.6795,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.3353464901447296,
      "learning_rate": 0.0003137206208425721,
      "loss": 0.6945,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.3413096070289612,
      "learning_rate": 0.0003126607538802661,
      "loss": 0.6986,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.39247822761535645,
      "learning_rate": 0.00031160088691796007,
      "loss": 0.6975,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.37605905532836914,
      "learning_rate": 0.0003105410199556541,
      "loss": 0.6648,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3390028476715088,
      "learning_rate": 0.00030948115299334815,
      "loss": 0.6513,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3718453049659729,
      "learning_rate": 0.00030842128603104213,
      "loss": 0.6919,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.2975955307483673,
      "learning_rate": 0.0003073614190687362,
      "loss": 0.6299,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.34555625915527344,
      "learning_rate": 0.00030630155210643016,
      "loss": 0.7005,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.32412344217300415,
      "learning_rate": 0.00030524168514412415,
      "loss": 0.6203,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.3432216942310333,
      "learning_rate": 0.0003041818181818182,
      "loss": 0.606,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3454482853412628,
      "learning_rate": 0.00030312195121951223,
      "loss": 0.6129,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.44866660237312317,
      "learning_rate": 0.0003020620842572062,
      "loss": 0.6854,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.4065716564655304,
      "learning_rate": 0.00030100221729490026,
      "loss": 0.7183,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.35473760962486267,
      "learning_rate": 0.00029994235033259424,
      "loss": 0.5937,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.4422287940979004,
      "learning_rate": 0.00029888248337028823,
      "loss": 0.6083,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3578943908214569,
      "learning_rate": 0.00029782261640798227,
      "loss": 0.6769,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.3340145945549011,
      "learning_rate": 0.0002967627494456763,
      "loss": 0.644,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.33603644371032715,
      "learning_rate": 0.0002957028824833703,
      "loss": 0.645,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.3559483289718628,
      "learning_rate": 0.00029464301552106434,
      "loss": 0.6179,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.38981226086616516,
      "learning_rate": 0.0002935831485587583,
      "loss": 0.6229,
      "step": 180
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.20362936627118e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}