{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 230,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004347826086956522,
      "grad_norm": 209.3180389404297,
      "learning_rate": 0.0,
      "loss": 5.8188,
      "step": 1
    },
    {
      "epoch": 0.008695652173913044,
      "grad_norm": 215.69874572753906,
      "learning_rate": 4.347826086956522e-06,
      "loss": 5.9259,
      "step": 2
    },
    {
      "epoch": 0.013043478260869565,
      "grad_norm": 62.712825775146484,
      "learning_rate": 8.695652173913044e-06,
      "loss": 5.4202,
      "step": 3
    },
    {
      "epoch": 0.017391304347826087,
      "grad_norm": 85.59194946289062,
      "learning_rate": 1.3043478260869566e-05,
      "loss": 5.3079,
      "step": 4
    },
    {
      "epoch": 0.021739130434782608,
      "grad_norm": 22.901897430419922,
      "learning_rate": 1.739130434782609e-05,
      "loss": 5.0196,
      "step": 5
    },
    {
      "epoch": 0.02608695652173913,
      "grad_norm": 22.081829071044922,
      "learning_rate": 2.173913043478261e-05,
      "loss": 4.8222,
      "step": 6
    },
    {
      "epoch": 0.030434782608695653,
      "grad_norm": 11.022245407104492,
      "learning_rate": 2.608695652173913e-05,
      "loss": 4.4617,
      "step": 7
    },
    {
      "epoch": 0.034782608695652174,
      "grad_norm": 7.274469375610352,
      "learning_rate": 3.0434782608695656e-05,
      "loss": 4.335,
      "step": 8
    },
    {
      "epoch": 0.0391304347826087,
      "grad_norm": 3.8645834922790527,
      "learning_rate": 3.478260869565218e-05,
      "loss": 4.0476,
      "step": 9
    },
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 2.6724016666412354,
      "learning_rate": 3.91304347826087e-05,
      "loss": 3.8387,
      "step": 10
    },
    {
      "epoch": 0.04782608695652174,
      "grad_norm": 2.258195161819458,
      "learning_rate": 4.347826086956522e-05,
      "loss": 3.8144,
      "step": 11
    },
    {
      "epoch": 0.05217391304347826,
      "grad_norm": 1.8822625875473022,
      "learning_rate": 4.782608695652174e-05,
      "loss": 3.4008,
      "step": 12
    },
    {
      "epoch": 0.05652173913043478,
      "grad_norm": 2.047840118408203,
      "learning_rate": 5.217391304347826e-05,
      "loss": 3.2554,
      "step": 13
    },
    {
      "epoch": 0.06086956521739131,
      "grad_norm": 1.8671568632125854,
      "learning_rate": 5.652173913043478e-05,
      "loss": 3.2461,
      "step": 14
    },
    {
      "epoch": 0.06521739130434782,
      "grad_norm": 1.6069483757019043,
      "learning_rate": 6.086956521739131e-05,
      "loss": 2.9738,
      "step": 15
    },
    {
      "epoch": 0.06956521739130435,
      "grad_norm": 1.3096915483474731,
      "learning_rate": 6.521739130434783e-05,
      "loss": 2.7823,
      "step": 16
    },
    {
      "epoch": 0.07391304347826087,
      "grad_norm": 1.3594956398010254,
      "learning_rate": 6.956521739130436e-05,
      "loss": 2.6255,
      "step": 17
    },
    {
      "epoch": 0.0782608695652174,
      "grad_norm": 1.0210895538330078,
      "learning_rate": 7.391304347826086e-05,
      "loss": 2.4501,
      "step": 18
    },
    {
      "epoch": 0.08260869565217391,
      "grad_norm": 0.8942164182662964,
      "learning_rate": 7.82608695652174e-05,
      "loss": 2.2934,
      "step": 19
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.8361735343933105,
      "learning_rate": 8.260869565217392e-05,
      "loss": 2.2029,
      "step": 20
    },
    {
      "epoch": 0.09130434782608696,
      "grad_norm": 0.794482409954071,
      "learning_rate": 8.695652173913044e-05,
      "loss": 2.0223,
      "step": 21
    },
    {
      "epoch": 0.09565217391304348,
      "grad_norm": 0.7513137459754944,
      "learning_rate": 9.130434782608696e-05,
      "loss": 1.8504,
      "step": 22
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.76312655210495,
      "learning_rate": 9.565217391304348e-05,
      "loss": 1.6577,
      "step": 23
    },
    {
      "epoch": 0.10434782608695652,
      "grad_norm": 0.8560758829116821,
      "learning_rate": 0.0001,
      "loss": 1.5565,
      "step": 24
    },
    {
      "epoch": 0.10869565217391304,
      "grad_norm": 0.7479954957962036,
      "learning_rate": 0.00010434782608695653,
      "loss": 1.4364,
      "step": 25
    },
    {
      "epoch": 0.11304347826086956,
      "grad_norm": 0.5951140522956848,
      "learning_rate": 0.00010869565217391305,
      "loss": 1.2957,
      "step": 26
    },
    {
      "epoch": 0.11739130434782609,
      "grad_norm": 0.503224790096283,
      "learning_rate": 0.00011304347826086956,
      "loss": 1.1799,
      "step": 27
    },
    {
      "epoch": 0.12173913043478261,
      "grad_norm": 0.47480374574661255,
      "learning_rate": 0.0001173913043478261,
      "loss": 1.1277,
      "step": 28
    },
    {
      "epoch": 0.12608695652173912,
      "grad_norm": 0.38552260398864746,
      "learning_rate": 0.00012173913043478263,
      "loss": 1.0744,
      "step": 29
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 0.35596558451652527,
      "learning_rate": 0.00012608695652173915,
      "loss": 1.0023,
      "step": 30
    },
    {
      "epoch": 0.13478260869565217,
      "grad_norm": 0.32971665263175964,
      "learning_rate": 0.00013043478260869567,
      "loss": 0.9691,
      "step": 31
    },
    {
      "epoch": 0.1391304347826087,
      "grad_norm": 0.37770169973373413,
      "learning_rate": 0.0001347826086956522,
      "loss": 0.9116,
      "step": 32
    },
    {
      "epoch": 0.14347826086956522,
      "grad_norm": 0.22640736401081085,
      "learning_rate": 0.0001391304347826087,
      "loss": 0.8613,
      "step": 33
    },
    {
      "epoch": 0.14782608695652175,
      "grad_norm": 0.20925410091876984,
      "learning_rate": 0.0001434782608695652,
      "loss": 0.8836,
      "step": 34
    },
    {
      "epoch": 0.15217391304347827,
      "grad_norm": 0.20542123913764954,
      "learning_rate": 0.00014782608695652173,
      "loss": 0.8502,
      "step": 35
    },
    {
      "epoch": 0.1565217391304348,
      "grad_norm": 0.16715222597122192,
      "learning_rate": 0.00015217391304347827,
      "loss": 0.8292,
      "step": 36
    },
    {
      "epoch": 0.1608695652173913,
      "grad_norm": 0.1648133248090744,
      "learning_rate": 0.0001565217391304348,
      "loss": 0.8189,
      "step": 37
    },
    {
      "epoch": 0.16521739130434782,
      "grad_norm": 0.13562779128551483,
      "learning_rate": 0.00016086956521739132,
      "loss": 0.8078,
      "step": 38
    },
    {
      "epoch": 0.16956521739130434,
      "grad_norm": 0.1290610432624817,
      "learning_rate": 0.00016521739130434784,
      "loss": 0.7712,
      "step": 39
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.11024343967437744,
      "learning_rate": 0.00016956521739130436,
      "loss": 0.7448,
      "step": 40
    },
    {
      "epoch": 0.1782608695652174,
      "grad_norm": 0.12418993562459946,
      "learning_rate": 0.00017391304347826088,
      "loss": 0.7633,
      "step": 41
    },
    {
      "epoch": 0.1826086956521739,
      "grad_norm": 0.10319849103689194,
      "learning_rate": 0.0001782608695652174,
      "loss": 0.7463,
      "step": 42
    },
    {
      "epoch": 0.18695652173913044,
      "grad_norm": 0.10371455550193787,
      "learning_rate": 0.00018260869565217392,
      "loss": 0.7516,
      "step": 43
    },
    {
      "epoch": 0.19130434782608696,
      "grad_norm": 0.09219090640544891,
      "learning_rate": 0.00018695652173913045,
      "loss": 0.7265,
      "step": 44
    },
    {
      "epoch": 0.1956521739130435,
      "grad_norm": 0.09577666968107224,
      "learning_rate": 0.00019130434782608697,
      "loss": 0.7382,
      "step": 45
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.08755916357040405,
      "learning_rate": 0.0001956521739130435,
      "loss": 0.7392,
      "step": 46
    },
    {
      "epoch": 0.20434782608695654,
      "grad_norm": 0.08335893601179123,
      "learning_rate": 0.0002,
      "loss": 0.7182,
      "step": 47
    },
    {
      "epoch": 0.20869565217391303,
      "grad_norm": 0.08622466027736664,
      "learning_rate": 0.00019999712083215463,
      "loss": 0.7196,
      "step": 48
    },
    {
      "epoch": 0.21304347826086956,
      "grad_norm": 0.07222707569599152,
      "learning_rate": 0.00019998848349441062,
      "loss": 0.7014,
      "step": 49
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.07286012172698975,
      "learning_rate": 0.00019997408848413493,
      "loss": 0.6986,
      "step": 50
    },
    {
      "epoch": 0.2217391304347826,
      "grad_norm": 0.07811558246612549,
      "learning_rate": 0.00019995393663024054,
      "loss": 0.6922,
      "step": 51
    },
    {
      "epoch": 0.22608695652173913,
      "grad_norm": 0.07095416635274887,
      "learning_rate": 0.0001999280290931388,
      "loss": 0.7188,
      "step": 52
    },
    {
      "epoch": 0.23043478260869565,
      "grad_norm": 0.0705651044845581,
      "learning_rate": 0.00019989636736467278,
      "loss": 0.7135,
      "step": 53
    },
    {
      "epoch": 0.23478260869565218,
      "grad_norm": 0.0649741142988205,
      "learning_rate": 0.00019985895326803097,
      "loss": 0.6833,
      "step": 54
    },
    {
      "epoch": 0.2391304347826087,
      "grad_norm": 0.07023416459560394,
      "learning_rate": 0.00019981578895764273,
      "loss": 0.6902,
      "step": 55
    },
    {
      "epoch": 0.24347826086956523,
      "grad_norm": 0.065043605864048,
      "learning_rate": 0.00019976687691905393,
      "loss": 0.6933,
      "step": 56
    },
    {
      "epoch": 0.24782608695652175,
      "grad_norm": 0.0647321566939354,
      "learning_rate": 0.00019971221996878394,
      "loss": 0.6946,
      "step": 57
    },
    {
      "epoch": 0.25217391304347825,
      "grad_norm": 0.08214448392391205,
      "learning_rate": 0.0001996518212541634,
      "loss": 0.6789,
      "step": 58
    },
    {
      "epoch": 0.2565217391304348,
      "grad_norm": 0.06106014922261238,
      "learning_rate": 0.00019958568425315314,
      "loss": 0.6826,
      "step": 59
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.06052952632308006,
      "learning_rate": 0.0001995138127741436,
      "loss": 0.6706,
      "step": 60
    },
    {
      "epoch": 0.26521739130434785,
      "grad_norm": 0.06265316903591156,
      "learning_rate": 0.00019943621095573586,
      "loss": 0.6809,
      "step": 61
    },
    {
      "epoch": 0.26956521739130435,
      "grad_norm": 0.0603368878364563,
      "learning_rate": 0.00019935288326650312,
      "loss": 0.6728,
      "step": 62
    },
    {
      "epoch": 0.27391304347826084,
      "grad_norm": 0.06611189991235733,
      "learning_rate": 0.00019926383450473344,
      "loss": 0.6499,
      "step": 63
    },
    {
      "epoch": 0.2782608695652174,
      "grad_norm": 0.06278355419635773,
      "learning_rate": 0.00019916906979815347,
      "loss": 0.6561,
      "step": 64
    },
    {
      "epoch": 0.2826086956521739,
      "grad_norm": 0.07379094511270523,
      "learning_rate": 0.00019906859460363307,
      "loss": 0.6786,
      "step": 65
    },
    {
      "epoch": 0.28695652173913044,
      "grad_norm": 0.09574166685342789,
      "learning_rate": 0.0001989624147068713,
      "loss": 0.6625,
      "step": 66
    },
    {
      "epoch": 0.29130434782608694,
      "grad_norm": 0.08743462711572647,
      "learning_rate": 0.00019885053622206304,
      "loss": 0.648,
      "step": 67
    },
    {
      "epoch": 0.2956521739130435,
      "grad_norm": 0.08914034813642502,
      "learning_rate": 0.00019873296559154698,
      "loss": 0.6561,
      "step": 68
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.06804706901311874,
      "learning_rate": 0.0001986097095854347,
      "loss": 0.658,
      "step": 69
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.09893489629030228,
      "learning_rate": 0.00019848077530122083,
      "loss": 0.6708,
      "step": 70
    },
    {
      "epoch": 0.30869565217391304,
      "grad_norm": 0.07928409427404404,
      "learning_rate": 0.0001983461701633742,
      "loss": 0.6407,
      "step": 71
    },
    {
      "epoch": 0.3130434782608696,
      "grad_norm": 0.07455449551343918,
      "learning_rate": 0.0001982059019229106,
      "loss": 0.676,
      "step": 72
    },
    {
      "epoch": 0.3173913043478261,
      "grad_norm": 0.0770968496799469,
      "learning_rate": 0.00019805997865694614,
      "loss": 0.6639,
      "step": 73
    },
    {
      "epoch": 0.3217391304347826,
      "grad_norm": 0.06771919876337051,
      "learning_rate": 0.00019790840876823232,
      "loss": 0.6486,
      "step": 74
    },
    {
      "epoch": 0.32608695652173914,
      "grad_norm": 0.07457810640335083,
      "learning_rate": 0.0001977512009846721,
      "loss": 0.6681,
      "step": 75
    },
    {
      "epoch": 0.33043478260869563,
      "grad_norm": 0.0826922208070755,
      "learning_rate": 0.00019758836435881746,
      "loss": 0.6356,
      "step": 76
    },
    {
      "epoch": 0.3347826086956522,
      "grad_norm": 0.07923886179924011,
      "learning_rate": 0.00019741990826734794,
      "loss": 0.6682,
      "step": 77
    },
    {
      "epoch": 0.3391304347826087,
      "grad_norm": 0.11045071482658386,
      "learning_rate": 0.0001972458424105307,
      "loss": 0.6203,
      "step": 78
    },
    {
      "epoch": 0.34347826086956523,
      "grad_norm": 0.11731227487325668,
      "learning_rate": 0.00019706617681166218,
      "loss": 0.66,
      "step": 79
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.12649305164813995,
      "learning_rate": 0.00019688092181649065,
      "loss": 0.6613,
      "step": 80
    },
    {
      "epoch": 0.3521739130434783,
      "grad_norm": 0.1144268661737442,
      "learning_rate": 0.00019669008809262062,
      "loss": 0.6606,
      "step": 81
    },
    {
      "epoch": 0.3565217391304348,
      "grad_norm": 0.11361440271139145,
      "learning_rate": 0.00019649368662889855,
      "loss": 0.629,
      "step": 82
    },
    {
      "epoch": 0.36086956521739133,
      "grad_norm": 0.12539249658584595,
      "learning_rate": 0.00019629172873477995,
      "loss": 0.6676,
      "step": 83
    },
    {
      "epoch": 0.3652173913043478,
      "grad_norm": 0.11141279339790344,
      "learning_rate": 0.00019608422603967836,
      "loss": 0.6376,
      "step": 84
    },
    {
      "epoch": 0.3695652173913043,
      "grad_norm": 0.09837634861469269,
      "learning_rate": 0.00019587119049229557,
      "loss": 0.6503,
      "step": 85
    },
    {
      "epoch": 0.3739130434782609,
      "grad_norm": 0.15677575767040253,
      "learning_rate": 0.0001956526343599335,
      "loss": 0.6638,
      "step": 86
    },
    {
      "epoch": 0.3782608695652174,
      "grad_norm": 0.252825528383255,
      "learning_rate": 0.0001954285702277879,
      "loss": 0.6713,
      "step": 87
    },
    {
      "epoch": 0.3826086956521739,
      "grad_norm": 0.3602813482284546,
      "learning_rate": 0.00019519901099822372,
      "loss": 0.6596,
      "step": 88
    },
    {
      "epoch": 0.3869565217391304,
      "grad_norm": 0.3970949053764343,
      "learning_rate": 0.00019496396989003193,
      "loss": 0.6617,
      "step": 89
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.284343421459198,
      "learning_rate": 0.00019472346043766865,
      "loss": 0.6229,
      "step": 90
    },
    {
      "epoch": 0.39565217391304347,
      "grad_norm": 0.19832171499729156,
      "learning_rate": 0.00019447749649047542,
      "loss": 0.6665,
      "step": 91
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.24541743099689484,
      "learning_rate": 0.00019422609221188207,
      "loss": 0.6585,
      "step": 92
    },
    {
      "epoch": 0.4043478260869565,
      "grad_norm": 0.1915537267923355,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.6343,
      "step": 93
    },
    {
      "epoch": 0.40869565217391307,
      "grad_norm": 0.20492875576019287,
      "learning_rate": 0.00019370702087974302,
      "loss": 0.6438,
      "step": 94
    },
    {
      "epoch": 0.41304347826086957,
      "grad_norm": 0.25835996866226196,
      "learning_rate": 0.00019343938371606712,
      "loss": 0.6502,
      "step": 95
    },
    {
      "epoch": 0.41739130434782606,
      "grad_norm": 0.2585464417934418,
      "learning_rate": 0.00019316636599900946,
      "loss": 0.6393,
      "step": 96
    },
    {
      "epoch": 0.4217391304347826,
      "grad_norm": 0.2317182868719101,
      "learning_rate": 0.00019288798344984672,
      "loss": 0.6275,
      "step": 97
    },
    {
      "epoch": 0.4260869565217391,
      "grad_norm": 0.23632416129112244,
      "learning_rate": 0.00019260425209878052,
      "loss": 0.6414,
      "step": 98
    },
    {
      "epoch": 0.43043478260869567,
      "grad_norm": 0.1801244169473648,
      "learning_rate": 0.00019231518828401458,
      "loss": 0.6491,
      "step": 99
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.24871514737606049,
      "learning_rate": 0.00019202080865081368,
      "loss": 0.6581,
      "step": 100
    },
    {
      "epoch": 0.4391304347826087,
      "grad_norm": 0.26276353001594543,
      "learning_rate": 0.00019172113015054532,
      "loss": 0.644,
      "step": 101
    },
    {
      "epoch": 0.4434782608695652,
      "grad_norm": 0.19743724167346954,
      "learning_rate": 0.0001914161700397035,
      "loss": 0.6519,
      "step": 102
    },
    {
      "epoch": 0.44782608695652176,
      "grad_norm": 0.31385916471481323,
      "learning_rate": 0.00019110594587891519,
      "loss": 0.6462,
      "step": 103
    },
    {
      "epoch": 0.45217391304347826,
      "grad_norm": 0.2689647674560547,
      "learning_rate": 0.0001907904755319289,
      "loss": 0.6517,
      "step": 104
    },
    {
      "epoch": 0.45652173913043476,
      "grad_norm": 0.17245543003082275,
      "learning_rate": 0.00019046977716458626,
      "loss": 0.6245,
      "step": 105
    },
    {
      "epoch": 0.4608695652173913,
      "grad_norm": 0.4380849003791809,
      "learning_rate": 0.00019014386924377582,
      "loss": 0.6519,
      "step": 106
    },
    {
      "epoch": 0.4652173913043478,
      "grad_norm": 0.305043488740921,
      "learning_rate": 0.0001898127705363696,
      "loss": 0.6606,
      "step": 107
    },
    {
      "epoch": 0.46956521739130436,
      "grad_norm": 0.20340269804000854,
      "learning_rate": 0.0001894765001081428,
      "loss": 0.6359,
      "step": 108
    },
    {
      "epoch": 0.47391304347826085,
      "grad_norm": 0.15703125298023224,
      "learning_rate": 0.0001891350773226754,
      "loss": 0.6461,
      "step": 109
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.16932646930217743,
      "learning_rate": 0.0001887885218402375,
      "loss": 0.6413,
      "step": 110
    },
    {
      "epoch": 0.4826086956521739,
      "grad_norm": 0.1790553480386734,
      "learning_rate": 0.00018843685361665723,
      "loss": 0.6378,
      "step": 111
    },
    {
      "epoch": 0.48695652173913045,
      "grad_norm": 0.24903282523155212,
      "learning_rate": 0.00018808009290217136,
      "loss": 0.6308,
      "step": 112
    },
    {
      "epoch": 0.49130434782608695,
      "grad_norm": 0.20529182255268097,
      "learning_rate": 0.00018771826024025946,
      "loss": 0.6315,
      "step": 113
    },
    {
      "epoch": 0.4956521739130435,
      "grad_norm": 0.18206629157066345,
      "learning_rate": 0.00018735137646646078,
      "loss": 0.6409,
      "step": 114
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.22906547784805298,
      "learning_rate": 0.00018697946270717467,
      "loss": 0.6522,
      "step": 115
    },
    {
      "epoch": 0.5043478260869565,
      "grad_norm": 0.23560722172260284,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.6424,
      "step": 116
    },
    {
      "epoch": 0.508695652173913,
      "grad_norm": 0.3479248881340027,
      "learning_rate": 0.00018622063118472134,
      "loss": 0.6591,
      "step": 117
    },
    {
      "epoch": 0.5130434782608696,
      "grad_norm": 0.48405924439430237,
      "learning_rate": 0.00018583375711762052,
      "loss": 0.6312,
      "step": 118
    },
    {
      "epoch": 0.5173913043478261,
      "grad_norm": 0.6660999655723572,
      "learning_rate": 0.00018544194045464886,
      "loss": 0.6492,
      "step": 119
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.6070662140846252,
      "learning_rate": 0.0001850452037579251,
      "loss": 0.631,
      "step": 120
    },
    {
      "epoch": 0.5260869565217391,
      "grad_norm": 0.2432556301355362,
      "learning_rate": 0.00018464356987288013,
      "loss": 0.6192,
      "step": 121
    },
    {
      "epoch": 0.5304347826086957,
      "grad_norm": 0.4718700647354126,
      "learning_rate": 0.00018423706192694116,
      "loss": 0.6385,
      "step": 122
    },
    {
      "epoch": 0.5347826086956522,
      "grad_norm": 0.41220200061798096,
      "learning_rate": 0.00018382570332820043,
      "loss": 0.6362,
      "step": 123
    },
    {
      "epoch": 0.5391304347826087,
      "grad_norm": 0.24313992261886597,
      "learning_rate": 0.00018340951776406694,
      "loss": 0.659,
      "step": 124
    },
    {
      "epoch": 0.5434782608695652,
      "grad_norm": 0.42307668924331665,
      "learning_rate": 0.00018298852919990252,
      "loss": 0.6484,
      "step": 125
    },
    {
      "epoch": 0.5478260869565217,
      "grad_norm": 0.2858572006225586,
      "learning_rate": 0.00018256276187764197,
      "loss": 0.6437,
      "step": 126
    },
    {
      "epoch": 0.5521739130434783,
      "grad_norm": 0.2318851351737976,
      "learning_rate": 0.0001821322403143969,
      "loss": 0.6191,
      "step": 127
    },
    {
      "epoch": 0.5565217391304348,
      "grad_norm": 0.3861188292503357,
      "learning_rate": 0.0001816969893010442,
      "loss": 0.639,
      "step": 128
    },
    {
      "epoch": 0.5608695652173913,
      "grad_norm": 0.2969801127910614,
      "learning_rate": 0.0001812570339007983,
      "loss": 0.6624,
      "step": 129
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.29341548681259155,
      "learning_rate": 0.00018081239944776805,
      "loss": 0.639,
      "step": 130
    },
    {
      "epoch": 0.5695652173913044,
      "grad_norm": 0.43678849935531616,
      "learning_rate": 0.00018036311154549784,
      "loss": 0.6384,
      "step": 131
    },
    {
      "epoch": 0.5739130434782609,
      "grad_norm": 0.5248069167137146,
      "learning_rate": 0.00017990919606549328,
      "loss": 0.6451,
      "step": 132
    },
    {
      "epoch": 0.5782608695652174,
      "grad_norm": 0.5387030243873596,
      "learning_rate": 0.00017945067914573146,
      "loss": 0.6198,
      "step": 133
    },
    {
      "epoch": 0.5826086956521739,
      "grad_norm": 0.55666184425354,
      "learning_rate": 0.00017898758718915586,
      "loss": 0.6391,
      "step": 134
    },
    {
      "epoch": 0.5869565217391305,
      "grad_norm": 0.4839560389518738,
      "learning_rate": 0.0001785199468621559,
      "loss": 0.6411,
      "step": 135
    },
    {
      "epoch": 0.591304347826087,
      "grad_norm": 0.5173195004463196,
      "learning_rate": 0.00017804778509303138,
      "loss": 0.6318,
      "step": 136
    },
    {
      "epoch": 0.5956521739130435,
      "grad_norm": 0.341448038816452,
      "learning_rate": 0.000177571129070442,
      "loss": 0.6427,
      "step": 137
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.2654604911804199,
      "learning_rate": 0.00017709000624184162,
      "loss": 0.616,
      "step": 138
    },
    {
      "epoch": 0.6043478260869565,
      "grad_norm": 0.4000408351421356,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.611,
      "step": 139
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.2812383770942688,
      "learning_rate": 0.00017611447124089649,
      "loss": 0.6508,
      "step": 140
    },
    {
      "epoch": 0.6130434782608696,
      "grad_norm": 0.30483949184417725,
      "learning_rate": 0.00017562011524313185,
      "loss": 0.6628,
      "step": 141
    },
    {
      "epoch": 0.6173913043478261,
      "grad_norm": 0.4457907974720001,
      "learning_rate": 0.0001751214047852818,
      "loss": 0.6274,
      "step": 142
    },
    {
      "epoch": 0.6217391304347826,
      "grad_norm": 0.38395488262176514,
      "learning_rate": 0.00017461836858476856,
      "loss": 0.6528,
      "step": 143
    },
    {
      "epoch": 0.6260869565217392,
      "grad_norm": 0.573344886302948,
      "learning_rate": 0.00017411103560810526,
      "loss": 0.6504,
      "step": 144
    },
    {
      "epoch": 0.6304347826086957,
      "grad_norm": 0.5133661031723022,
      "learning_rate": 0.00017359943506922774,
      "loss": 0.6334,
      "step": 145
    },
    {
      "epoch": 0.6347826086956522,
      "grad_norm": 0.2995568513870239,
      "learning_rate": 0.00017308359642781242,
      "loss": 0.6328,
      "step": 146
    },
    {
      "epoch": 0.6391304347826087,
      "grad_norm": 0.5677820444107056,
      "learning_rate": 0.0001725635493875799,
      "loss": 0.639,
      "step": 147
    },
    {
      "epoch": 0.6434782608695652,
      "grad_norm": 0.4751092791557312,
      "learning_rate": 0.00017203932389458454,
      "loss": 0.6229,
      "step": 148
    },
    {
      "epoch": 0.6478260869565218,
      "grad_norm": 0.4374710023403168,
      "learning_rate": 0.00017151095013548994,
      "loss": 0.6377,
      "step": 149
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.4172927439212799,
      "learning_rate": 0.0001709784585358309,
      "loss": 0.6277,
      "step": 150
    },
    {
      "epoch": 0.6565217391304348,
      "grad_norm": 0.3994798958301544,
      "learning_rate": 0.00017044187975826124,
      "loss": 0.637,
      "step": 151
    },
    {
      "epoch": 0.6608695652173913,
      "grad_norm": 0.34366917610168457,
      "learning_rate": 0.00016990124470078822,
      "loss": 0.6556,
      "step": 152
    },
    {
      "epoch": 0.6652173913043479,
      "grad_norm": 0.533347487449646,
      "learning_rate": 0.0001693565844949933,
      "loss": 0.6073,
      "step": 153
    },
    {
      "epoch": 0.6695652173913044,
      "grad_norm": 0.4292946457862854,
      "learning_rate": 0.0001688079305042395,
      "loss": 0.6548,
      "step": 154
    },
    {
      "epoch": 0.6739130434782609,
      "grad_norm": 0.2770076394081116,
      "learning_rate": 0.00016825531432186543,
      "loss": 0.6014,
      "step": 155
    },
    {
      "epoch": 0.6782608695652174,
      "grad_norm": 0.377838134765625,
      "learning_rate": 0.0001676987677693659,
      "loss": 0.6406,
      "step": 156
    },
    {
      "epoch": 0.6826086956521739,
      "grad_norm": 0.421268492937088,
      "learning_rate": 0.0001671383228945597,
      "loss": 0.6288,
      "step": 157
    },
    {
      "epoch": 0.6869565217391305,
      "grad_norm": 0.4219221770763397,
      "learning_rate": 0.00016657401196974405,
      "loss": 0.647,
      "step": 158
    },
    {
      "epoch": 0.691304347826087,
      "grad_norm": 0.3563760221004486,
      "learning_rate": 0.00016600586748983641,
      "loss": 0.6307,
      "step": 159
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.39387866854667664,
      "learning_rate": 0.00016543392217050314,
      "loss": 0.631,
      "step": 160
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.36268243193626404,
      "learning_rate": 0.0001648582089462756,
      "loss": 0.6429,
      "step": 161
    },
    {
      "epoch": 0.7043478260869566,
      "grad_norm": 0.3702019155025482,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.6338,
      "step": 162
    },
    {
      "epoch": 0.7086956521739131,
      "grad_norm": 0.44408297538757324,
      "learning_rate": 0.00016369561160419784,
      "loss": 0.6416,
      "step": 163
    },
    {
      "epoch": 0.7130434782608696,
      "grad_norm": 0.5986080765724182,
      "learning_rate": 0.00016310879443260528,
      "loss": 0.6187,
      "step": 164
    },
    {
      "epoch": 0.717391304347826,
      "grad_norm": 0.7963016629219055,
      "learning_rate": 0.0001625183432447789,
      "loss": 0.6365,
      "step": 165
    },
    {
      "epoch": 0.7217391304347827,
      "grad_norm": 1.2156025171279907,
      "learning_rate": 0.0001619242920408802,
      "loss": 0.6625,
      "step": 166
    },
    {
      "epoch": 0.7260869565217392,
      "grad_norm": 0.7924716472625732,
      "learning_rate": 0.00016132667502837165,
      "loss": 0.6276,
      "step": 167
    },
    {
      "epoch": 0.7304347826086957,
      "grad_norm": 0.29551273584365845,
      "learning_rate": 0.00016072552662004696,
      "loss": 0.6159,
      "step": 168
    },
    {
      "epoch": 0.7347826086956522,
      "grad_norm": 0.7566269040107727,
      "learning_rate": 0.00016012088143204953,
      "loss": 0.6485,
      "step": 169
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 1.001354455947876,
      "learning_rate": 0.00015951277428187898,
      "loss": 0.6323,
      "step": 170
    },
    {
      "epoch": 0.7434782608695653,
      "grad_norm": 0.9103027582168579,
      "learning_rate": 0.00015890124018638638,
      "loss": 0.6255,
      "step": 171
    },
    {
      "epoch": 0.7478260869565218,
      "grad_norm": 0.3885137736797333,
      "learning_rate": 0.00015828631435975784,
      "loss": 0.6323,
      "step": 172
    },
    {
      "epoch": 0.7521739130434782,
      "grad_norm": 0.6141281723976135,
      "learning_rate": 0.00015766803221148673,
      "loss": 0.6504,
      "step": 173
    },
    {
      "epoch": 0.7565217391304347,
      "grad_norm": 0.8024821281433105,
      "learning_rate": 0.0001570464293443346,
      "loss": 0.641,
      "step": 174
    },
    {
      "epoch": 0.7608695652173914,
      "grad_norm": 0.43333736062049866,
      "learning_rate": 0.00015642154155228122,
      "loss": 0.627,
      "step": 175
    },
    {
      "epoch": 0.7652173913043478,
      "grad_norm": 0.649389922618866,
      "learning_rate": 0.00015579340481846336,
      "loss": 0.6483,
      "step": 176
    },
    {
      "epoch": 0.7695652173913043,
      "grad_norm": 1.0359424352645874,
      "learning_rate": 0.00015516205531310273,
      "loss": 0.6332,
      "step": 177
    },
    {
      "epoch": 0.7739130434782608,
      "grad_norm": 0.7209396362304688,
      "learning_rate": 0.00015452752939142328,
      "loss": 0.6524,
      "step": 178
    },
    {
      "epoch": 0.7782608695652173,
      "grad_norm": 0.6178513169288635,
      "learning_rate": 0.00015388986359155758,
      "loss": 0.645,
      "step": 179
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.9886595606803894,
      "learning_rate": 0.00015324909463244296,
      "loss": 0.6642,
      "step": 180
    },
    {
      "epoch": 0.7869565217391304,
      "grad_norm": 0.7466373443603516,
      "learning_rate": 0.00015260525941170712,
      "loss": 0.6315,
      "step": 181
    },
    {
      "epoch": 0.7913043478260869,
      "grad_norm": 0.5552679896354675,
      "learning_rate": 0.00015195839500354335,
      "loss": 0.6207,
      "step": 182
    },
    {
      "epoch": 0.7956521739130434,
      "grad_norm": 0.5576688647270203,
      "learning_rate": 0.0001513085386565758,
      "loss": 0.6421,
      "step": 183
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.4000707268714905,
      "learning_rate": 0.00015065572779171432,
      "loss": 0.6398,
      "step": 184
    },
    {
      "epoch": 0.8043478260869565,
      "grad_norm": 0.4978863298892975,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.6456,
      "step": 185
    },
    {
      "epoch": 0.808695652173913,
      "grad_norm": 0.4530424177646637,
      "learning_rate": 0.00014934139304044033,
      "loss": 0.6453,
      "step": 186
    },
    {
      "epoch": 0.8130434782608695,
      "grad_norm": 0.29163071513175964,
      "learning_rate": 0.00014867994483783485,
      "loss": 0.6558,
      "step": 187
    },
    {
      "epoch": 0.8173913043478261,
      "grad_norm": 0.33445900678634644,
      "learning_rate": 0.00014801569348059157,
      "loss": 0.6291,
      "step": 188
    },
    {
      "epoch": 0.8217391304347826,
      "grad_norm": 0.3891032934188843,
      "learning_rate": 0.0001473486772185334,
      "loss": 0.6458,
      "step": 189
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.4320944845676422,
      "learning_rate": 0.00014667893446069588,
      "loss": 0.6275,
      "step": 190
    },
    {
      "epoch": 0.8304347826086956,
      "grad_norm": 0.3652418553829193,
      "learning_rate": 0.00014600650377311522,
      "loss": 0.6434,
      "step": 191
    },
    {
      "epoch": 0.8347826086956521,
      "grad_norm": 0.2939096689224243,
      "learning_rate": 0.00014533142387660773,
      "loss": 0.6462,
      "step": 192
    },
    {
      "epoch": 0.8391304347826087,
      "grad_norm": 0.36094796657562256,
      "learning_rate": 0.00014465373364454001,
      "loss": 0.6259,
      "step": 193
    },
    {
      "epoch": 0.8434782608695652,
      "grad_norm": 0.503746747970581,
      "learning_rate": 0.00014397347210059057,
      "loss": 0.6565,
      "step": 194
    },
    {
      "epoch": 0.8478260869565217,
      "grad_norm": 0.501377522945404,
      "learning_rate": 0.00014329067841650274,
      "loss": 0.6358,
      "step": 195
    },
    {
      "epoch": 0.8521739130434782,
      "grad_norm": 0.40720251202583313,
      "learning_rate": 0.00014260539190982886,
      "loss": 0.636,
      "step": 196
    },
    {
      "epoch": 0.8565217391304348,
      "grad_norm": 0.3170947730541229,
      "learning_rate": 0.00014191765204166643,
      "loss": 0.6343,
      "step": 197
    },
    {
      "epoch": 0.8608695652173913,
      "grad_norm": 0.43554455041885376,
      "learning_rate": 0.00014122749841438575,
      "loss": 0.6319,
      "step": 198
    },
    {
      "epoch": 0.8652173913043478,
      "grad_norm": 0.5128415822982788,
      "learning_rate": 0.00014053497076934948,
      "loss": 0.6326,
      "step": 199
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.44992515444755554,
      "learning_rate": 0.00013984010898462416,
      "loss": 0.6343,
      "step": 200
    },
    {
      "epoch": 0.8739130434782608,
      "grad_norm": 0.506968080997467,
      "learning_rate": 0.00013914295307268396,
      "loss": 0.6472,
      "step": 201
    },
    {
      "epoch": 0.8782608695652174,
      "grad_norm": 0.6257392764091492,
      "learning_rate": 0.0001384435431781065,
      "loss": 0.6535,
      "step": 202
    },
    {
      "epoch": 0.8826086956521739,
      "grad_norm": 0.9480230808258057,
      "learning_rate": 0.00013774191957526143,
      "loss": 0.6628,
      "step": 203
    },
    {
      "epoch": 0.8869565217391304,
      "grad_norm": 1.2171893119812012,
      "learning_rate": 0.00013703812266599113,
      "loss": 0.6585,
      "step": 204
    },
    {
      "epoch": 0.8913043478260869,
      "grad_norm": 0.3134421110153198,
      "learning_rate": 0.00013633219297728416,
      "loss": 0.6629,
      "step": 205
    },
    {
      "epoch": 0.8956521739130435,
      "grad_norm": 1.003349781036377,
      "learning_rate": 0.00013562417115894172,
      "loss": 0.6516,
      "step": 206
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.246419906616211,
      "learning_rate": 0.00013491409798123687,
      "loss": 0.6418,
      "step": 207
    },
    {
      "epoch": 0.9043478260869565,
      "grad_norm": 0.46948862075805664,
      "learning_rate": 0.00013420201433256689,
      "loss": 0.6441,
      "step": 208
    },
    {
      "epoch": 0.908695652173913,
      "grad_norm": 1.628340244293213,
      "learning_rate": 0.00013348796121709862,
      "loss": 0.6661,
      "step": 209
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.4027623236179352,
      "learning_rate": 0.0001327719797524075,
      "loss": 0.6342,
      "step": 210
    },
    {
      "epoch": 0.9173913043478261,
      "grad_norm": 1.3196384906768799,
      "learning_rate": 0.00013205411116710972,
      "loss": 0.6724,
      "step": 211
    },
    {
      "epoch": 0.9217391304347826,
      "grad_norm": 0.561631977558136,
      "learning_rate": 0.00013133439679848823,
      "loss": 0.6541,
      "step": 212
    },
    {
      "epoch": 0.9260869565217391,
      "grad_norm": 0.7715569734573364,
      "learning_rate": 0.00013061287809011242,
      "loss": 0.6419,
      "step": 213
    },
    {
      "epoch": 0.9304347826086956,
      "grad_norm": 0.8591257333755493,
      "learning_rate": 0.0001298895965894516,
      "loss": 0.6197,
      "step": 214
    },
    {
      "epoch": 0.9347826086956522,
      "grad_norm": 0.4229847192764282,
      "learning_rate": 0.0001291645939454825,
      "loss": 0.6472,
      "step": 215
    },
    {
      "epoch": 0.9391304347826087,
      "grad_norm": 0.7943733930587769,
      "learning_rate": 0.0001284379119062912,
      "loss": 0.6576,
      "step": 216
    },
    {
      "epoch": 0.9434782608695652,
      "grad_norm": 0.7454273104667664,
      "learning_rate": 0.0001277095923166689,
      "loss": 0.6245,
      "step": 217
    },
    {
      "epoch": 0.9478260869565217,
      "grad_norm": 0.4976602792739868,
      "learning_rate": 0.00012697967711570242,
      "loss": 0.644,
      "step": 218
    },
    {
      "epoch": 0.9521739130434783,
      "grad_norm": 0.6845293641090393,
      "learning_rate": 0.00012624820833435937,
      "loss": 0.6412,
      "step": 219
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.7265484929084778,
      "learning_rate": 0.0001255152280930676,
      "loss": 0.6438,
      "step": 220
    },
    {
      "epoch": 0.9608695652173913,
      "grad_norm": 0.4346272647380829,
      "learning_rate": 0.00012478077859929,
      "loss": 0.6116,
      "step": 221
    },
    {
      "epoch": 0.9652173913043478,
      "grad_norm": 0.5768253803253174,
      "learning_rate": 0.00012404490214509386,
      "loss": 0.6242,
      "step": 222
    },
    {
      "epoch": 0.9695652173913043,
      "grad_norm": 0.688556969165802,
      "learning_rate": 0.00012330764110471566,
      "loss": 0.6546,
      "step": 223
    },
    {
      "epoch": 0.9739130434782609,
      "grad_norm": 0.6147114634513855,
      "learning_rate": 0.00012256903793212107,
      "loss": 0.6286,
      "step": 224
    },
    {
      "epoch": 0.9782608695652174,
      "grad_norm": 0.6598117351531982,
      "learning_rate": 0.00012182913515856015,
      "loss": 0.65,
      "step": 225
    },
    {
      "epoch": 0.9826086956521739,
      "grad_norm": 0.6232290863990784,
      "learning_rate": 0.00012108797539011847,
      "loss": 0.6465,
      "step": 226
    },
    {
      "epoch": 0.9869565217391304,
      "grad_norm": 0.3764599561691284,
      "learning_rate": 0.0001203456013052634,
      "loss": 0.6397,
      "step": 227
    },
    {
      "epoch": 0.991304347826087,
      "grad_norm": 0.4177006781101227,
      "learning_rate": 0.00011960205565238684,
      "loss": 0.6324,
      "step": 228
    },
    {
      "epoch": 0.9956521739130435,
      "grad_norm": 0.6632861495018005,
      "learning_rate": 0.00011885738124734358,
      "loss": 0.6394,
      "step": 229
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8406037092208862,
      "learning_rate": 0.00011811162097098558,
      "loss": 0.6563,
      "step": 230
    }
  ],
  "logging_steps": 1,
  "max_steps": 460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.970864260913562e+18,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}