{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8901098901098901,
  "eval_steps": 500,
  "global_step": 135,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.195170283317566,
      "learning_rate": 0.0,
      "loss": 1.0821,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.0331945419311523,
      "learning_rate": 9.56e-05,
      "loss": 1.0763,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.1415084600448608,
      "learning_rate": 0.0001912,
      "loss": 1.0495,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.063579797744751,
      "learning_rate": 0.0002868,
      "loss": 0.956,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6625626087188721,
      "learning_rate": 0.0003824,
      "loss": 0.8477,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.6782878637313843,
      "learning_rate": 0.000478,
      "loss": 1.0343,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.6161335110664368,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.9727,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.41984498500823975,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8698,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.3116914927959442,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8446,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.29025012254714966,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.7877,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.39959046244621277,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8688,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5689778923988342,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.8847,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.40798476338386536,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.7254,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.6968982219696045,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.8179,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5194700360298157,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.7156,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.43927809596061707,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.8273,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.3979283571243286,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.7288,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4314859211444855,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7677,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3548160791397095,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.6472,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.38769328594207764,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.6578,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3017254173755646,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.7163,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.33315712213516235,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.6951,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3334329426288605,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7464,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.301981121301651,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.667,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3768517076969147,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.6719,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3810518980026245,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7687,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.4689561128616333,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7114,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3895481824874878,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.7328,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.44972071051597595,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.708,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.39502742886543274,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.7672,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.5479147434234619,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.7583,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.33382317423820496,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.7369,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.49583446979522705,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.8174,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3855836093425751,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.7935,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.45332643389701843,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.7593,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3067397475242615,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.6878,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3372962474822998,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.7705,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.40445494651794434,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.7849,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3279916048049927,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.715,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.31464719772338867,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.7322,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.27914178371429443,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.6922,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.27055102586746216,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.7071,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.30358147621154785,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.7257,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3098717927932739,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.6871,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.32566770911216736,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.7264,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3617362082004547,
      "learning_rate": 0.0004356053215077605,
      "loss": 0.6902,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.43403375148773193,
      "learning_rate": 0.00043454545454545455,
      "loss": 0.7037,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.33475279808044434,
      "learning_rate": 0.0004334855875831486,
      "loss": 0.7261,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.34020453691482544,
      "learning_rate": 0.0004324257206208426,
      "loss": 0.6361,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.29145631194114685,
      "learning_rate": 0.0004313658536585366,
      "loss": 0.6797,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.35258740186691284,
      "learning_rate": 0.00043030598669623066,
      "loss": 0.6811,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.31551578640937805,
      "learning_rate": 0.0004292461197339246,
      "loss": 0.6662,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.40033137798309326,
      "learning_rate": 0.00042818625277161863,
      "loss": 0.7066,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.34928882122039795,
      "learning_rate": 0.00042712638580931267,
      "loss": 0.6704,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3890458345413208,
      "learning_rate": 0.00042606651884700666,
      "loss": 0.7074,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.34585464000701904,
      "learning_rate": 0.0004250066518847007,
      "loss": 0.7147,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2896708548069,
      "learning_rate": 0.00042394678492239474,
      "loss": 0.7679,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3353179395198822,
      "learning_rate": 0.00042288691796008867,
      "loss": 0.6415,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.32367175817489624,
      "learning_rate": 0.0004218270509977827,
      "loss": 0.7697,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.32652848958969116,
      "learning_rate": 0.00042076718403547675,
      "loss": 0.6835,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2857896089553833,
      "learning_rate": 0.00041970731707317074,
      "loss": 0.7343,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.35556867718696594,
      "learning_rate": 0.0004186474501108648,
      "loss": 0.6726,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3160596191883087,
      "learning_rate": 0.0004175875831485588,
      "loss": 0.7143,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3572760224342346,
      "learning_rate": 0.00041652771618625275,
      "loss": 0.7587,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.2954725921154022,
      "learning_rate": 0.0004154678492239468,
      "loss": 0.6812,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3745565116405487,
      "learning_rate": 0.00041440798226164083,
      "loss": 0.7258,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.3284990191459656,
      "learning_rate": 0.0004133481152993348,
      "loss": 0.7153,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.30010706186294556,
      "learning_rate": 0.00041228824833702886,
      "loss": 0.6984,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.2915664613246918,
      "learning_rate": 0.00041122838137472285,
      "loss": 0.7052,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.29902124404907227,
      "learning_rate": 0.00041016851441241683,
      "loss": 0.6934,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3071542978286743,
      "learning_rate": 0.00040910864745011087,
      "loss": 0.708,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.27577969431877136,
      "learning_rate": 0.00040804878048780486,
      "loss": 0.7428,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.2982359826564789,
      "learning_rate": 0.0004069889135254989,
      "loss": 0.7779,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.30666181445121765,
      "learning_rate": 0.00040592904656319294,
      "loss": 0.7067,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.2994212508201599,
      "learning_rate": 0.0004048691796008869,
      "loss": 0.6904,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.2912769317626953,
      "learning_rate": 0.00040380931263858097,
      "loss": 0.7374,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.26267528533935547,
      "learning_rate": 0.00040274944567627495,
      "loss": 0.7415,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3228910565376282,
      "learning_rate": 0.00040168957871396894,
      "loss": 0.6345,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3353758752346039,
      "learning_rate": 0.000400629711751663,
      "loss": 0.6988,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.34910428524017334,
      "learning_rate": 0.000399569844789357,
      "loss": 0.6955,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.35183653235435486,
      "learning_rate": 0.000398509977827051,
      "loss": 0.668,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.2986193001270294,
      "learning_rate": 0.00039745011086474505,
      "loss": 0.7467,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3669707775115967,
      "learning_rate": 0.00039639024390243904,
      "loss": 0.7143,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3397374749183655,
      "learning_rate": 0.000395330376940133,
      "loss": 0.6948,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.36349624395370483,
      "learning_rate": 0.00039427050997782706,
      "loss": 0.6381,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3161599934101105,
      "learning_rate": 0.0003932106430155211,
      "loss": 0.7035,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.34338268637657166,
      "learning_rate": 0.0003921507760532151,
      "loss": 0.6079,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3725844621658325,
      "learning_rate": 0.00039109090909090913,
      "loss": 0.6842,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3499543368816376,
      "learning_rate": 0.0003900310421286031,
      "loss": 0.6663,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.27967825531959534,
      "learning_rate": 0.0003889711751662971,
      "loss": 0.7043,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.42830947041511536,
      "learning_rate": 0.00038791130820399114,
      "loss": 0.6066,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.2985455095767975,
      "learning_rate": 0.0003868514412416852,
      "loss": 0.7876,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.31391894817352295,
      "learning_rate": 0.00038579157427937917,
      "loss": 0.7133,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3369094133377075,
      "learning_rate": 0.0003847317073170732,
      "loss": 0.6965,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.35192903876304626,
      "learning_rate": 0.0003836718403547672,
      "loss": 0.738,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.30551454424858093,
      "learning_rate": 0.0003826119733924612,
      "loss": 0.6792,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.2987115681171417,
      "learning_rate": 0.0003815521064301552,
      "loss": 0.684,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.2904681861400604,
      "learning_rate": 0.00038049223946784927,
      "loss": 0.7354,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.3646203279495239,
      "learning_rate": 0.00037943237250554325,
      "loss": 0.7511,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.27354785799980164,
      "learning_rate": 0.0003783725055432373,
      "loss": 0.6868,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3103290796279907,
      "learning_rate": 0.0003773126385809313,
      "loss": 0.6935,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.33116936683654785,
      "learning_rate": 0.00037625277161862527,
      "loss": 0.7088,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.31001362204551697,
      "learning_rate": 0.0003751929046563193,
      "loss": 0.7556,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.34533751010894775,
      "learning_rate": 0.00037413303769401335,
      "loss": 0.6535,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3335258364677429,
      "learning_rate": 0.00037307317073170733,
      "loss": 0.7302,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.2870931923389435,
      "learning_rate": 0.0003720133037694014,
      "loss": 0.6758,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.3254625201225281,
      "learning_rate": 0.00037095343680709536,
      "loss": 0.7593,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.30663806200027466,
      "learning_rate": 0.00036989356984478935,
      "loss": 0.7143,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.2793548107147217,
      "learning_rate": 0.0003688337028824834,
      "loss": 0.7234,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.31374335289001465,
      "learning_rate": 0.0003677738359201774,
      "loss": 0.7025,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3022034764289856,
      "learning_rate": 0.0003667139689578714,
      "loss": 0.6732,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.3161036968231201,
      "learning_rate": 0.00036565410199556546,
      "loss": 0.7136,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.30554062128067017,
      "learning_rate": 0.0003645942350332594,
      "loss": 0.6756,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.29600027203559875,
      "learning_rate": 0.00036353436807095343,
      "loss": 0.7567,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.29495969414711,
      "learning_rate": 0.00036247450110864747,
      "loss": 0.6993,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.36187559366226196,
      "learning_rate": 0.00036141463414634146,
      "loss": 0.7093,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.2875276505947113,
      "learning_rate": 0.0003603547671840355,
      "loss": 0.6432,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3426610827445984,
      "learning_rate": 0.00035929490022172954,
      "loss": 0.6835,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3620908558368683,
      "learning_rate": 0.00035823503325942347,
      "loss": 0.756,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.2915194630622864,
      "learning_rate": 0.0003571751662971175,
      "loss": 0.6883,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.32311534881591797,
      "learning_rate": 0.00035611529933481155,
      "loss": 0.727,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.3259125053882599,
      "learning_rate": 0.00035505543237250554,
      "loss": 0.6523,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.33542436361312866,
      "learning_rate": 0.0003539955654101996,
      "loss": 0.6245,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.4077654480934143,
      "learning_rate": 0.0003529356984478936,
      "loss": 0.7295,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.35173124074935913,
      "learning_rate": 0.00035187583148558755,
      "loss": 0.7189,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.3285554349422455,
      "learning_rate": 0.0003508159645232816,
      "loss": 0.7179,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.3704049289226532,
      "learning_rate": 0.00034975609756097563,
      "loss": 0.7213,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.30321356654167175,
      "learning_rate": 0.0003486962305986696,
      "loss": 0.701,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.25718748569488525,
      "learning_rate": 0.00034763636363636366,
      "loss": 0.7196,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.38271740078926086,
      "learning_rate": 0.0003465764966740577,
      "loss": 0.7567,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3291567862033844,
      "learning_rate": 0.00034551662971175163,
      "loss": 0.7078,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.3053141236305237,
      "learning_rate": 0.00034445676274944567,
      "loss": 0.6136,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.300508052110672,
      "learning_rate": 0.0003433968957871397,
      "loss": 0.7905,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3538469970226288,
      "learning_rate": 0.0003423370288248337,
      "loss": 0.6981,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.285239040851593,
      "learning_rate": 0.00034127716186252774,
      "loss": 0.7405,
      "step": 135
    }
  ],
  "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": 6.19594756725289e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}