{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.567032967032967,
  "eval_steps": 500,
  "global_step": 390,
  "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
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.48952823877334595,
      "learning_rate": 0.0002925232815964523,
      "loss": 0.7109,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.36474210023880005,
      "learning_rate": 0.00029146341463414635,
      "loss": 0.6027,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.34098976850509644,
      "learning_rate": 0.0002904035476718404,
      "loss": 0.7102,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.34124574065208435,
      "learning_rate": 0.0002893436807095344,
      "loss": 0.6423,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.3932075500488281,
      "learning_rate": 0.0002882838137472284,
      "loss": 0.6671,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.33542463183403015,
      "learning_rate": 0.0002872239467849224,
      "loss": 0.6803,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3534783124923706,
      "learning_rate": 0.0002861640798226164,
      "loss": 0.6576,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.40464842319488525,
      "learning_rate": 0.00028510421286031043,
      "loss": 0.6706,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.40317490696907043,
      "learning_rate": 0.0002840443458980045,
      "loss": 0.7072,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.4195561707019806,
      "learning_rate": 0.00028298447893569846,
      "loss": 0.6661,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.38662609457969666,
      "learning_rate": 0.0002819246119733925,
      "loss": 0.6754,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.3110015094280243,
      "learning_rate": 0.00028086474501108643,
      "loss": 0.6553,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.3761013150215149,
      "learning_rate": 0.0002798048780487805,
      "loss": 0.7035,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.38549262285232544,
      "learning_rate": 0.0002787450110864745,
      "loss": 0.7035,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.33969804644584656,
      "learning_rate": 0.0002776851441241685,
      "loss": 0.5982,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.38856765627861023,
      "learning_rate": 0.00027662527716186254,
      "loss": 0.6633,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.40017169713974,
      "learning_rate": 0.0002755654101995566,
      "loss": 0.5817,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4068447947502136,
      "learning_rate": 0.0002745055432372505,
      "loss": 0.7324,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.40120214223861694,
      "learning_rate": 0.00027344567627494455,
      "loss": 0.6351,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.3413095772266388,
      "learning_rate": 0.0002723858093126386,
      "loss": 0.6304,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.4990409016609192,
      "learning_rate": 0.0002713259423503326,
      "loss": 0.7766,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.42951729893684387,
      "learning_rate": 0.0002702660753880266,
      "loss": 0.6906,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.3540504276752472,
      "learning_rate": 0.00026920620842572066,
      "loss": 0.6968,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.48668473958969116,
      "learning_rate": 0.00026814634146341465,
      "loss": 0.6692,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.37050965428352356,
      "learning_rate": 0.00026708647450110864,
      "loss": 0.6669,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.39586934447288513,
      "learning_rate": 0.0002660266075388027,
      "loss": 0.6758,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.40397927165031433,
      "learning_rate": 0.00026496674057649666,
      "loss": 0.6899,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.37612348794937134,
      "learning_rate": 0.0002639068736141907,
      "loss": 0.6707,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.3504735231399536,
      "learning_rate": 0.00026284700665188474,
      "loss": 0.6767,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.35173776745796204,
      "learning_rate": 0.00026178713968957873,
      "loss": 0.5735,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.40999504923820496,
      "learning_rate": 0.0002607272727272727,
      "loss": 0.6273,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.35834893584251404,
      "learning_rate": 0.00025966740576496676,
      "loss": 0.598,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.3837548792362213,
      "learning_rate": 0.00025860753880266074,
      "loss": 0.6965,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.34808504581451416,
      "learning_rate": 0.0002575476718403548,
      "loss": 0.595,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.35062023997306824,
      "learning_rate": 0.0002564878048780488,
      "loss": 0.6515,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.33710214495658875,
      "learning_rate": 0.0002554279379157428,
      "loss": 0.6686,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.37949880957603455,
      "learning_rate": 0.0002543680709534368,
      "loss": 0.6156,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.3699743449687958,
      "learning_rate": 0.00025330820399113084,
      "loss": 0.6601,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.3863787353038788,
      "learning_rate": 0.0002522483370288248,
      "loss": 0.6775,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.3577323853969574,
      "learning_rate": 0.00025118847006651887,
      "loss": 0.6428,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.35522976517677307,
      "learning_rate": 0.0002501286031042129,
      "loss": 0.7113,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.2958388030529022,
      "learning_rate": 0.0002490687361419069,
      "loss": 0.5894,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.39004430174827576,
      "learning_rate": 0.0002480088691796009,
      "loss": 0.7323,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.3532419204711914,
      "learning_rate": 0.0002469490022172949,
      "loss": 0.7053,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.38058528304100037,
      "learning_rate": 0.0002458891352549889,
      "loss": 0.5879,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.3630821704864502,
      "learning_rate": 0.00024482926829268295,
      "loss": 0.6575,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.336331844329834,
      "learning_rate": 0.00024376940133037696,
      "loss": 0.5471,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.417603462934494,
      "learning_rate": 0.00024270953436807097,
      "loss": 0.7068,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.4159291982650757,
      "learning_rate": 0.00024164966740576496,
      "loss": 0.7434,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.38124197721481323,
      "learning_rate": 0.00024058980044345897,
      "loss": 0.651,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.35591304302215576,
      "learning_rate": 0.000239529933481153,
      "loss": 0.6499,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.3156837522983551,
      "learning_rate": 0.00023847006651884703,
      "loss": 0.6625,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.35423845052719116,
      "learning_rate": 0.00023741019955654104,
      "loss": 0.6815,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.3334770202636719,
      "learning_rate": 0.00023635033259423503,
      "loss": 0.6598,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.36000946164131165,
      "learning_rate": 0.00023529046563192907,
      "loss": 0.6857,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.3560355007648468,
      "learning_rate": 0.00023423059866962308,
      "loss": 0.6333,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.33485350012779236,
      "learning_rate": 0.00023317073170731707,
      "loss": 0.6805,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.3382507860660553,
      "learning_rate": 0.0002321108647450111,
      "loss": 0.5923,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.37855657935142517,
      "learning_rate": 0.00023105099778270512,
      "loss": 0.6704,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.38713422417640686,
      "learning_rate": 0.0002299911308203991,
      "loss": 0.65,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.4157232344150543,
      "learning_rate": 0.00022893126385809315,
      "loss": 0.6736,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.36155664920806885,
      "learning_rate": 0.00022787139689578716,
      "loss": 0.667,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.3499765396118164,
      "learning_rate": 0.00022681152993348115,
      "loss": 0.7014,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.41679126024246216,
      "learning_rate": 0.00022575166297117516,
      "loss": 0.6368,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.3487682044506073,
      "learning_rate": 0.0002246917960088692,
      "loss": 0.6537,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.40102338790893555,
      "learning_rate": 0.0002236319290465632,
      "loss": 0.6403,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.3773156702518463,
      "learning_rate": 0.0002225720620842572,
      "loss": 0.6263,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.35781264305114746,
      "learning_rate": 0.00022151219512195125,
      "loss": 0.7296,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.38307562470436096,
      "learning_rate": 0.00022045232815964523,
      "loss": 0.5955,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.4169180393218994,
      "learning_rate": 0.00021939246119733925,
      "loss": 0.619,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.4185219705104828,
      "learning_rate": 0.0002183325942350333,
      "loss": 0.7264,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.37964341044425964,
      "learning_rate": 0.00021727272727272727,
      "loss": 0.6893,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.3570690155029297,
      "learning_rate": 0.0002162128603104213,
      "loss": 0.6997,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.37315163016319275,
      "learning_rate": 0.00021515299334811533,
      "loss": 0.6197,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.43261992931365967,
      "learning_rate": 0.00021409312638580931,
      "loss": 0.6111,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.3639296889305115,
      "learning_rate": 0.00021303325942350333,
      "loss": 0.5749,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.37761378288269043,
      "learning_rate": 0.00021197339246119737,
      "loss": 0.7539,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.4344223141670227,
      "learning_rate": 0.00021091352549889135,
      "loss": 0.6699,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.39609697461128235,
      "learning_rate": 0.00020985365853658537,
      "loss": 0.6528,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.40705087780952454,
      "learning_rate": 0.0002087937915742794,
      "loss": 0.623,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.4111230671405792,
      "learning_rate": 0.0002077339246119734,
      "loss": 0.7173,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.38785091042518616,
      "learning_rate": 0.0002066740576496674,
      "loss": 0.6951,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.39383167028427124,
      "learning_rate": 0.00020561419068736142,
      "loss": 0.6437,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.37726521492004395,
      "learning_rate": 0.00020455432372505544,
      "loss": 0.6648,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.404821515083313,
      "learning_rate": 0.00020349445676274945,
      "loss": 0.6606,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.38121116161346436,
      "learning_rate": 0.00020243458980044346,
      "loss": 0.688,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.3439493477344513,
      "learning_rate": 0.00020137472283813748,
      "loss": 0.6788,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.3669295310974121,
      "learning_rate": 0.0002003148558758315,
      "loss": 0.5679,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.36400479078292847,
      "learning_rate": 0.0001992549889135255,
      "loss": 0.7218,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.3788094222545624,
      "learning_rate": 0.00019819512195121952,
      "loss": 0.6222,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.3777931332588196,
      "learning_rate": 0.00019713525498891353,
      "loss": 0.6646,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.3810963034629822,
      "learning_rate": 0.00019607538802660754,
      "loss": 0.6871,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.41431093215942383,
      "learning_rate": 0.00019501552106430156,
      "loss": 0.7054,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.3819563388824463,
      "learning_rate": 0.00019395565410199557,
      "loss": 0.7587,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.3508612811565399,
      "learning_rate": 0.00019289578713968959,
      "loss": 0.6415,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.38655802607536316,
      "learning_rate": 0.0001918359201773836,
      "loss": 0.6289,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.36534982919692993,
      "learning_rate": 0.0001907760532150776,
      "loss": 0.6478,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.3356361985206604,
      "learning_rate": 0.00018971618625277163,
      "loss": 0.6516,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.35123294591903687,
      "learning_rate": 0.00018865631929046564,
      "loss": 0.6406,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.3991864323616028,
      "learning_rate": 0.00018759645232815965,
      "loss": 0.6831,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.3936593532562256,
      "learning_rate": 0.00018653658536585367,
      "loss": 0.6266,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.3679262101650238,
      "learning_rate": 0.00018547671840354768,
      "loss": 0.6619,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.3894799053668976,
      "learning_rate": 0.0001844168514412417,
      "loss": 0.6749,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.41627606749534607,
      "learning_rate": 0.0001833569844789357,
      "loss": 0.6096,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.37425053119659424,
      "learning_rate": 0.0001822971175166297,
      "loss": 0.6385,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.42545342445373535,
      "learning_rate": 0.00018123725055432373,
      "loss": 0.6724,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.40074142813682556,
      "learning_rate": 0.00018017738359201775,
      "loss": 0.7184,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.3925767242908478,
      "learning_rate": 0.00017911751662971173,
      "loss": 0.7205,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.4131416380405426,
      "learning_rate": 0.00017805764966740578,
      "loss": 0.6596,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.3493328094482422,
      "learning_rate": 0.0001769977827050998,
      "loss": 0.6297,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.38077864050865173,
      "learning_rate": 0.00017593791574279378,
      "loss": 0.658,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.33103784918785095,
      "learning_rate": 0.00017487804878048782,
      "loss": 0.6637,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.3739219009876251,
      "learning_rate": 0.00017381818181818183,
      "loss": 0.654,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.36662906408309937,
      "learning_rate": 0.00017275831485587582,
      "loss": 0.6985,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.3902086615562439,
      "learning_rate": 0.00017169844789356986,
      "loss": 0.6029,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.3567931354045868,
      "learning_rate": 0.00017063858093126387,
      "loss": 0.6858,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.3652505576610565,
      "learning_rate": 0.00016957871396895788,
      "loss": 0.6156,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.39131873846054077,
      "learning_rate": 0.0001685188470066519,
      "loss": 0.6437,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.3901872932910919,
      "learning_rate": 0.0001674589800443459,
      "loss": 0.5859,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.3876962959766388,
      "learning_rate": 0.00016639911308203992,
      "loss": 0.6364,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.353511780500412,
      "learning_rate": 0.00016533924611973394,
      "loss": 0.6737,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.40350696444511414,
      "learning_rate": 0.00016427937915742795,
      "loss": 0.5841,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.3877563178539276,
      "learning_rate": 0.00016321951219512197,
      "loss": 0.6367,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4490271210670471,
      "learning_rate": 0.00016215964523281595,
      "loss": 0.609,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.36414027214050293,
      "learning_rate": 0.00016109977827051,
      "loss": 0.5645,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.38158196210861206,
      "learning_rate": 0.000160039911308204,
      "loss": 0.5581,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.36571335792541504,
      "learning_rate": 0.000158980044345898,
      "loss": 0.5919,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.38686469197273254,
      "learning_rate": 0.00015792017738359203,
      "loss": 0.4992,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.3830243945121765,
      "learning_rate": 0.00015686031042128605,
      "loss": 0.6104,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.4463445544242859,
      "learning_rate": 0.00015580044345898003,
      "loss": 0.5279,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.48589542508125305,
      "learning_rate": 0.00015474057649667407,
      "loss": 0.6084,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.5054001212120056,
      "learning_rate": 0.0001536807095343681,
      "loss": 0.5908,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.4260968565940857,
      "learning_rate": 0.00015262084257206207,
      "loss": 0.5545,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.45022574067115784,
      "learning_rate": 0.00015156097560975611,
      "loss": 0.5411,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.41795817017555237,
      "learning_rate": 0.00015050110864745013,
      "loss": 0.6025,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.43173566460609436,
      "learning_rate": 0.00014944124168514411,
      "loss": 0.5343,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.4401814937591553,
      "learning_rate": 0.00014838137472283816,
      "loss": 0.6157,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.4120434522628784,
      "learning_rate": 0.00014732150776053217,
      "loss": 0.5256,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.4425227642059326,
      "learning_rate": 0.00014626164079822616,
      "loss": 0.5616,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.5097671151161194,
      "learning_rate": 0.0001452017738359202,
      "loss": 0.6132,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.5228633284568787,
      "learning_rate": 0.0001441419068736142,
      "loss": 0.5791,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.49693989753723145,
      "learning_rate": 0.0001430820399113082,
      "loss": 0.5524,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.45052996277809143,
      "learning_rate": 0.00014202217294900224,
      "loss": 0.597,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.47330087423324585,
      "learning_rate": 0.00014096230598669625,
      "loss": 0.5449,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.4297902584075928,
      "learning_rate": 0.00013990243902439024,
      "loss": 0.4786,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.44193458557128906,
      "learning_rate": 0.00013884257206208425,
      "loss": 0.5961,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.4771270751953125,
      "learning_rate": 0.0001377827050997783,
      "loss": 0.4534,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.4830714464187622,
      "learning_rate": 0.00013672283813747228,
      "loss": 0.5515,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.49183136224746704,
      "learning_rate": 0.0001356629711751663,
      "loss": 0.5578,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.509364128112793,
      "learning_rate": 0.00013460310421286033,
      "loss": 0.5625,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.5401235818862915,
      "learning_rate": 0.00013354323725055432,
      "loss": 0.5831,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.4866209328174591,
      "learning_rate": 0.00013248337028824833,
      "loss": 0.4584,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.5264401435852051,
      "learning_rate": 0.00013142350332594237,
      "loss": 0.5875,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.4918362498283386,
      "learning_rate": 0.00013036363636363636,
      "loss": 0.4876,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.4651448726654053,
      "learning_rate": 0.00012930376940133037,
      "loss": 0.475,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.4479612708091736,
      "learning_rate": 0.0001282439024390244,
      "loss": 0.5706,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.4616782069206238,
      "learning_rate": 0.0001271840354767184,
      "loss": 0.6362,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.5072535276412964,
      "learning_rate": 0.0001261241685144124,
      "loss": 0.495,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.5395843982696533,
      "learning_rate": 0.00012506430155210645,
      "loss": 0.5876,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.4644815921783447,
      "learning_rate": 0.00012400443458980044,
      "loss": 0.574,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.46828600764274597,
      "learning_rate": 0.00012294456762749445,
      "loss": 0.5984,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.500522792339325,
      "learning_rate": 0.00012188470066518848,
      "loss": 0.5876,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.5314874649047852,
      "learning_rate": 0.00012082483370288248,
      "loss": 0.5961,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.5057728886604309,
      "learning_rate": 0.0001197649667405765,
      "loss": 0.5868,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.5343583822250366,
      "learning_rate": 0.00011870509977827052,
      "loss": 0.5573,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.48953306674957275,
      "learning_rate": 0.00011764523281596453,
      "loss": 0.5866,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.5053675770759583,
      "learning_rate": 0.00011658536585365853,
      "loss": 0.551,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.5395176410675049,
      "learning_rate": 0.00011552549889135256,
      "loss": 0.543,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.539143443107605,
      "learning_rate": 0.00011446563192904658,
      "loss": 0.5924,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.4997571110725403,
      "learning_rate": 0.00011340576496674058,
      "loss": 0.4865,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.5067327618598938,
      "learning_rate": 0.0001123458980044346,
      "loss": 0.5199,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.5650079250335693,
      "learning_rate": 0.0001112860310421286,
      "loss": 0.5955,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.543550968170166,
      "learning_rate": 0.00011022616407982262,
      "loss": 0.5807,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.567020833492279,
      "learning_rate": 0.00010916629711751664,
      "loss": 0.619,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.47536998987197876,
      "learning_rate": 0.00010810643015521064,
      "loss": 0.5422,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.5356211066246033,
      "learning_rate": 0.00010704656319290466,
      "loss": 0.6118,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.5155754685401917,
      "learning_rate": 0.00010598669623059868,
      "loss": 0.4529,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.4807490110397339,
      "learning_rate": 0.00010492682926829268,
      "loss": 0.5387,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.5635716319084167,
      "learning_rate": 0.0001038669623059867,
      "loss": 0.5875,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.4951256811618805,
      "learning_rate": 0.00010280709534368071,
      "loss": 0.5992,
      "step": 360
    },
    {
      "epoch": 2.375824175824176,
      "grad_norm": 0.4901532232761383,
      "learning_rate": 0.00010174722838137472,
      "loss": 0.5816,
      "step": 361
    },
    {
      "epoch": 2.3824175824175824,
      "grad_norm": 0.5091278553009033,
      "learning_rate": 0.00010068736141906874,
      "loss": 0.5126,
      "step": 362
    },
    {
      "epoch": 2.389010989010989,
      "grad_norm": 0.459832102060318,
      "learning_rate": 9.962749445676275e-05,
      "loss": 0.5792,
      "step": 363
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 0.5044639706611633,
      "learning_rate": 9.856762749445677e-05,
      "loss": 0.5308,
      "step": 364
    },
    {
      "epoch": 2.402197802197802,
      "grad_norm": 0.5355687737464905,
      "learning_rate": 9.750776053215078e-05,
      "loss": 0.5391,
      "step": 365
    },
    {
      "epoch": 2.4087912087912087,
      "grad_norm": 0.5197217464447021,
      "learning_rate": 9.644789356984479e-05,
      "loss": 0.5706,
      "step": 366
    },
    {
      "epoch": 2.4153846153846152,
      "grad_norm": 0.5308353900909424,
      "learning_rate": 9.53880266075388e-05,
      "loss": 0.5688,
      "step": 367
    },
    {
      "epoch": 2.421978021978022,
      "grad_norm": 0.4923224449157715,
      "learning_rate": 9.432815964523282e-05,
      "loss": 0.5851,
      "step": 368
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.5244911909103394,
      "learning_rate": 9.326829268292683e-05,
      "loss": 0.5589,
      "step": 369
    },
    {
      "epoch": 2.4351648351648354,
      "grad_norm": 0.5343697667121887,
      "learning_rate": 9.220842572062085e-05,
      "loss": 0.5658,
      "step": 370
    },
    {
      "epoch": 2.441758241758242,
      "grad_norm": 0.4676620066165924,
      "learning_rate": 9.114855875831485e-05,
      "loss": 0.5427,
      "step": 371
    },
    {
      "epoch": 2.4483516483516485,
      "grad_norm": 0.49916768074035645,
      "learning_rate": 9.008869179600887e-05,
      "loss": 0.6231,
      "step": 372
    },
    {
      "epoch": 2.454945054945055,
      "grad_norm": 0.46556830406188965,
      "learning_rate": 8.902882483370289e-05,
      "loss": 0.5648,
      "step": 373
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.522914707660675,
      "learning_rate": 8.796895787139689e-05,
      "loss": 0.55,
      "step": 374
    },
    {
      "epoch": 2.4681318681318682,
      "grad_norm": 0.49538254737854004,
      "learning_rate": 8.690909090909091e-05,
      "loss": 0.5695,
      "step": 375
    },
    {
      "epoch": 2.474725274725275,
      "grad_norm": 0.4914807677268982,
      "learning_rate": 8.584922394678493e-05,
      "loss": 0.4717,
      "step": 376
    },
    {
      "epoch": 2.4813186813186814,
      "grad_norm": 0.5074240565299988,
      "learning_rate": 8.478935698447894e-05,
      "loss": 0.4367,
      "step": 377
    },
    {
      "epoch": 2.487912087912088,
      "grad_norm": 0.4804547429084778,
      "learning_rate": 8.372949002217296e-05,
      "loss": 0.6175,
      "step": 378
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 0.5531794428825378,
      "learning_rate": 8.266962305986697e-05,
      "loss": 0.5239,
      "step": 379
    },
    {
      "epoch": 2.501098901098901,
      "grad_norm": 0.5505852103233337,
      "learning_rate": 8.160975609756098e-05,
      "loss": 0.4578,
      "step": 380
    },
    {
      "epoch": 2.5076923076923077,
      "grad_norm": 0.512364387512207,
      "learning_rate": 8.0549889135255e-05,
      "loss": 0.5019,
      "step": 381
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.6376479268074036,
      "learning_rate": 7.9490022172949e-05,
      "loss": 0.5854,
      "step": 382
    },
    {
      "epoch": 2.520879120879121,
      "grad_norm": 0.5317598581314087,
      "learning_rate": 7.843015521064302e-05,
      "loss": 0.5197,
      "step": 383
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 0.5354563593864441,
      "learning_rate": 7.737028824833704e-05,
      "loss": 0.542,
      "step": 384
    },
    {
      "epoch": 2.534065934065934,
      "grad_norm": 0.4872952997684479,
      "learning_rate": 7.631042128603104e-05,
      "loss": 0.5535,
      "step": 385
    },
    {
      "epoch": 2.5406593406593405,
      "grad_norm": 0.5370059013366699,
      "learning_rate": 7.525055432372506e-05,
      "loss": 0.5416,
      "step": 386
    },
    {
      "epoch": 2.547252747252747,
      "grad_norm": 0.5250877141952515,
      "learning_rate": 7.419068736141908e-05,
      "loss": 0.5444,
      "step": 387
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.496770441532135,
      "learning_rate": 7.313082039911308e-05,
      "loss": 0.5805,
      "step": 388
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 0.47272270917892456,
      "learning_rate": 7.20709534368071e-05,
      "loss": 0.4928,
      "step": 389
    },
    {
      "epoch": 2.567032967032967,
      "grad_norm": 0.49495187401771545,
      "learning_rate": 7.101108647450112e-05,
      "loss": 0.5498,
      "step": 390
    }
  ],
  "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": 1.777883582991237e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}