{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.2703296703296703,
  "eval_steps": 500,
  "global_step": 345,
  "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
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.39319372177124023,
      "learning_rate": 0.0003402172949002218,
      "loss": 0.7222,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.381517231464386,
      "learning_rate": 0.00033915742793791577,
      "loss": 0.712,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3278730511665344,
      "learning_rate": 0.00033809756097560975,
      "loss": 0.6998,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.3165235221385956,
      "learning_rate": 0.0003370376940133038,
      "loss": 0.7314,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.34131768345832825,
      "learning_rate": 0.0003359778270509978,
      "loss": 0.696,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3008774518966675,
      "learning_rate": 0.0003349179600886918,
      "loss": 0.6536,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.3007766306400299,
      "learning_rate": 0.00033385809312638586,
      "loss": 0.6952,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3253723680973053,
      "learning_rate": 0.00033279822616407985,
      "loss": 0.7443,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.31287214159965515,
      "learning_rate": 0.00033173835920177384,
      "loss": 0.7231,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.31145626306533813,
      "learning_rate": 0.0003306784922394679,
      "loss": 0.6726,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.3471812307834625,
      "learning_rate": 0.00032961862527716186,
      "loss": 0.685,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.33790674805641174,
      "learning_rate": 0.0003285587583148559,
      "loss": 0.6287,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.29381513595581055,
      "learning_rate": 0.00032749889135254994,
      "loss": 0.7269,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.33163395524024963,
      "learning_rate": 0.00032643902439024393,
      "loss": 0.6688,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.28233274817466736,
      "learning_rate": 0.0003253791574279379,
      "loss": 0.7459,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.2697957456111908,
      "learning_rate": 0.0003243192904656319,
      "loss": 0.7204,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3910374939441681,
      "learning_rate": 0.00032325942350332594,
      "loss": 0.7153,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.31035199761390686,
      "learning_rate": 0.00032219955654102,
      "loss": 0.6372,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.35336118936538696,
      "learning_rate": 0.00032113968957871397,
      "loss": 0.6743,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.34364980459213257,
      "learning_rate": 0.000320079822616408,
      "loss": 0.6599,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.43252575397491455,
      "learning_rate": 0.000319019955654102,
      "loss": 0.7043,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.3506278991699219,
      "learning_rate": 0.000317960088691796,
      "loss": 0.6128,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.2789537012577057,
      "learning_rate": 0.00031690022172949,
      "loss": 0.5281,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.35527005791664124,
      "learning_rate": 0.00031584035476718407,
      "loss": 0.6422,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.31511110067367554,
      "learning_rate": 0.00031478048780487805,
      "loss": 0.5686,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.3340548574924469,
      "learning_rate": 0.0003137206208425721,
      "loss": 0.6509,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.32808569073677063,
      "learning_rate": 0.0003126607538802661,
      "loss": 0.6608,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.33119022846221924,
      "learning_rate": 0.00031160088691796007,
      "loss": 0.6298,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.3775770664215088,
      "learning_rate": 0.0003105410199556541,
      "loss": 0.656,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.30977287888526917,
      "learning_rate": 0.00030948115299334815,
      "loss": 0.6113,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.37175706028938293,
      "learning_rate": 0.00030842128603104213,
      "loss": 0.7013,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.351672887802124,
      "learning_rate": 0.0003073614190687362,
      "loss": 0.6631,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.359859436750412,
      "learning_rate": 0.00030630155210643016,
      "loss": 0.6584,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.4018190801143646,
      "learning_rate": 0.00030524168514412415,
      "loss": 0.6357,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.30350229144096375,
      "learning_rate": 0.0003041818181818182,
      "loss": 0.6667,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.35754507780075073,
      "learning_rate": 0.00030312195121951223,
      "loss": 0.6565,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.399149090051651,
      "learning_rate": 0.0003020620842572062,
      "loss": 0.6746,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.3958664834499359,
      "learning_rate": 0.00030100221729490026,
      "loss": 0.6506,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.32290762662887573,
      "learning_rate": 0.00029994235033259424,
      "loss": 0.6816,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.48313409090042114,
      "learning_rate": 0.00029888248337028823,
      "loss": 0.6262,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.35737237334251404,
      "learning_rate": 0.00029782261640798227,
      "loss": 0.654,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.3466680943965912,
      "learning_rate": 0.0002967627494456763,
      "loss": 0.6356,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.39362478256225586,
      "learning_rate": 0.0002957028824833703,
      "loss": 0.6485,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.402873158454895,
      "learning_rate": 0.00029464301552106434,
      "loss": 0.6457,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.3372310996055603,
      "learning_rate": 0.0002935831485587583,
      "loss": 0.6354,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.3874308168888092,
      "learning_rate": 0.0002925232815964523,
      "loss": 0.7243,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.4037889838218689,
      "learning_rate": 0.00029146341463414635,
      "loss": 0.6482,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.37217509746551514,
      "learning_rate": 0.0002904035476718404,
      "loss": 0.7087,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.3493293821811676,
      "learning_rate": 0.0002893436807095344,
      "loss": 0.6694,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.4025772213935852,
      "learning_rate": 0.0002882838137472284,
      "loss": 0.6237,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.34033340215682983,
      "learning_rate": 0.0002872239467849224,
      "loss": 0.5906,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.36151084303855896,
      "learning_rate": 0.0002861640798226164,
      "loss": 0.6349,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.36955204606056213,
      "learning_rate": 0.00028510421286031043,
      "loss": 0.673,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.3759375810623169,
      "learning_rate": 0.0002840443458980045,
      "loss": 0.6669,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.3453136086463928,
      "learning_rate": 0.00028298447893569846,
      "loss": 0.6001,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.39012014865875244,
      "learning_rate": 0.0002819246119733925,
      "loss": 0.6824,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.35880038142204285,
      "learning_rate": 0.00028086474501108643,
      "loss": 0.6539,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4133313000202179,
      "learning_rate": 0.0002798048780487805,
      "loss": 0.6706,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.39098864793777466,
      "learning_rate": 0.0002787450110864745,
      "loss": 0.5938,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.32598677277565,
      "learning_rate": 0.0002776851441241685,
      "loss": 0.7272,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.3618911802768707,
      "learning_rate": 0.00027662527716186254,
      "loss": 0.676,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.37141621112823486,
      "learning_rate": 0.0002755654101995566,
      "loss": 0.626,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.3062952160835266,
      "learning_rate": 0.0002745055432372505,
      "loss": 0.5656,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.37736329436302185,
      "learning_rate": 0.00027344567627494455,
      "loss": 0.7134,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.3816686272621155,
      "learning_rate": 0.0002723858093126386,
      "loss": 0.6379,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.3832955062389374,
      "learning_rate": 0.0002713259423503326,
      "loss": 0.6502,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.33459657430648804,
      "learning_rate": 0.0002702660753880266,
      "loss": 0.659,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.42061227560043335,
      "learning_rate": 0.00026920620842572066,
      "loss": 0.6586,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.3629121780395508,
      "learning_rate": 0.00026814634146341465,
      "loss": 0.5816,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.3140220642089844,
      "learning_rate": 0.00026708647450110864,
      "loss": 0.6568,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.36066094040870667,
      "learning_rate": 0.0002660266075388027,
      "loss": 0.6666,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.3712823987007141,
      "learning_rate": 0.00026496674057649666,
      "loss": 0.6371,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.4108193516731262,
      "learning_rate": 0.0002639068736141907,
      "loss": 0.6652,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.3651275932788849,
      "learning_rate": 0.00026284700665188474,
      "loss": 0.6161,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.3415852189064026,
      "learning_rate": 0.00026178713968957873,
      "loss": 0.6737,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.4050087034702301,
      "learning_rate": 0.0002607272727272727,
      "loss": 0.5946,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.3588634431362152,
      "learning_rate": 0.00025966740576496676,
      "loss": 0.6445,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.35990527272224426,
      "learning_rate": 0.00025860753880266074,
      "loss": 0.6944,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.3686452805995941,
      "learning_rate": 0.0002575476718403548,
      "loss": 0.6887,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.3962976932525635,
      "learning_rate": 0.0002564878048780488,
      "loss": 0.6894,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.3887828588485718,
      "learning_rate": 0.0002554279379157428,
      "loss": 0.6455,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.3367188274860382,
      "learning_rate": 0.0002543680709534368,
      "loss": 0.5887,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.35716238617897034,
      "learning_rate": 0.00025330820399113084,
      "loss": 0.6222,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.36131733655929565,
      "learning_rate": 0.0002522483370288248,
      "loss": 0.6142,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.40967121720314026,
      "learning_rate": 0.00025118847006651887,
      "loss": 0.6257,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.35617414116859436,
      "learning_rate": 0.0002501286031042129,
      "loss": 0.6287,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.3525332808494568,
      "learning_rate": 0.0002490687361419069,
      "loss": 0.6664,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.39492669701576233,
      "learning_rate": 0.0002480088691796009,
      "loss": 0.6249,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.35548609495162964,
      "learning_rate": 0.0002469490022172949,
      "loss": 0.5817,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.38659876585006714,
      "learning_rate": 0.0002458891352549889,
      "loss": 0.6588,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.3900056779384613,
      "learning_rate": 0.00024482926829268295,
      "loss": 0.6637,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.4056378901004791,
      "learning_rate": 0.00024376940133037696,
      "loss": 0.5983,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.3593887984752655,
      "learning_rate": 0.00024270953436807097,
      "loss": 0.6192,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.3599669933319092,
      "learning_rate": 0.00024164966740576496,
      "loss": 0.5867,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.3734591007232666,
      "learning_rate": 0.00024058980044345897,
      "loss": 0.6821,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.3447280824184418,
      "learning_rate": 0.000239529933481153,
      "loss": 0.6375,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.36874809861183167,
      "learning_rate": 0.00023847006651884703,
      "loss": 0.6779,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.38847875595092773,
      "learning_rate": 0.00023741019955654104,
      "loss": 0.6667,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.39220407605171204,
      "learning_rate": 0.00023635033259423503,
      "loss": 0.6733,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.44259729981422424,
      "learning_rate": 0.00023529046563192907,
      "loss": 0.6365,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.37200653553009033,
      "learning_rate": 0.00023423059866962308,
      "loss": 0.6352,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.3853394389152527,
      "learning_rate": 0.00023317073170731707,
      "loss": 0.6432,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.37795448303222656,
      "learning_rate": 0.0002321108647450111,
      "loss": 0.5782,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.3939788043498993,
      "learning_rate": 0.00023105099778270512,
      "loss": 0.6513,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.37062007188796997,
      "learning_rate": 0.0002299911308203991,
      "loss": 0.6167,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.3661113679409027,
      "learning_rate": 0.00022893126385809315,
      "loss": 0.6161,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.3689832091331482,
      "learning_rate": 0.00022787139689578716,
      "loss": 0.6776,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.3579269349575043,
      "learning_rate": 0.00022681152993348115,
      "loss": 0.6498,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.3285681903362274,
      "learning_rate": 0.00022575166297117516,
      "loss": 0.6519,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.34521231055259705,
      "learning_rate": 0.0002246917960088692,
      "loss": 0.6447,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.3420107066631317,
      "learning_rate": 0.0002236319290465632,
      "loss": 0.6388,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.35361817479133606,
      "learning_rate": 0.0002225720620842572,
      "loss": 0.6077,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.38164547085762024,
      "learning_rate": 0.00022151219512195125,
      "loss": 0.5999,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.3841310441493988,
      "learning_rate": 0.00022045232815964523,
      "loss": 0.6645,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.36244288086891174,
      "learning_rate": 0.00021939246119733925,
      "loss": 0.6422,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.35995614528656006,
      "learning_rate": 0.0002183325942350333,
      "loss": 0.6243,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.3498387336730957,
      "learning_rate": 0.00021727272727272727,
      "loss": 0.7294,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.3545849919319153,
      "learning_rate": 0.0002162128603104213,
      "loss": 0.6,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.3808715045452118,
      "learning_rate": 0.00021515299334811533,
      "loss": 0.6017,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.3720131814479828,
      "learning_rate": 0.00021409312638580931,
      "loss": 0.698,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.365560382604599,
      "learning_rate": 0.00021303325942350333,
      "loss": 0.6549,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.3739791810512543,
      "learning_rate": 0.00021197339246119737,
      "loss": 0.6619,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.3811318278312683,
      "learning_rate": 0.00021091352549889135,
      "loss": 0.6728,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.37915971875190735,
      "learning_rate": 0.00020985365853658537,
      "loss": 0.6009,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.43078261613845825,
      "learning_rate": 0.0002087937915742794,
      "loss": 0.5865,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.39934995770454407,
      "learning_rate": 0.0002077339246119734,
      "loss": 0.5964,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.3778096139431,
      "learning_rate": 0.0002066740576496674,
      "loss": 0.7449,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.37463709712028503,
      "learning_rate": 0.00020561419068736142,
      "loss": 0.5972,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.41654863953590393,
      "learning_rate": 0.00020455432372505544,
      "loss": 0.5918,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.3658749759197235,
      "learning_rate": 0.00020349445676274945,
      "loss": 0.58,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.3733176290988922,
      "learning_rate": 0.00020243458980044346,
      "loss": 0.744,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.38651400804519653,
      "learning_rate": 0.00020137472283813748,
      "loss": 0.6206,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.377961665391922,
      "learning_rate": 0.0002003148558758315,
      "loss": 0.7244,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.3353257477283478,
      "learning_rate": 0.0001992549889135255,
      "loss": 0.6618,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.3616909384727478,
      "learning_rate": 0.00019819512195121952,
      "loss": 0.6544,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.35055965185165405,
      "learning_rate": 0.00019713525498891353,
      "loss": 0.62,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.3660716414451599,
      "learning_rate": 0.00019607538802660754,
      "loss": 0.6236,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.37623634934425354,
      "learning_rate": 0.00019501552106430156,
      "loss": 0.6487,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.3791641592979431,
      "learning_rate": 0.00019395565410199557,
      "loss": 0.6505,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.4153837263584137,
      "learning_rate": 0.00019289578713968959,
      "loss": 0.6357,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.3974490165710449,
      "learning_rate": 0.0001918359201773836,
      "loss": 0.635,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.41546180844306946,
      "learning_rate": 0.0001907760532150776,
      "loss": 0.5926,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.36638110876083374,
      "learning_rate": 0.00018971618625277163,
      "loss": 0.6514,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.3790123462677002,
      "learning_rate": 0.00018865631929046564,
      "loss": 0.6576,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.374115526676178,
      "learning_rate": 0.00018759645232815965,
      "loss": 0.6328,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.36899662017822266,
      "learning_rate": 0.00018653658536585367,
      "loss": 0.6007,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.36647939682006836,
      "learning_rate": 0.00018547671840354768,
      "loss": 0.6552,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.37169116735458374,
      "learning_rate": 0.0001844168514412417,
      "loss": 0.591,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.40471574664115906,
      "learning_rate": 0.0001833569844789357,
      "loss": 0.6495,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.3741428852081299,
      "learning_rate": 0.0001822971175166297,
      "loss": 0.599,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.3474360406398773,
      "learning_rate": 0.00018123725055432373,
      "loss": 0.6384,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.3605997562408447,
      "learning_rate": 0.00018017738359201775,
      "loss": 0.6477,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.34898510575294495,
      "learning_rate": 0.00017911751662971173,
      "loss": 0.6447,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.39736175537109375,
      "learning_rate": 0.00017805764966740578,
      "loss": 0.7392,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.3412422239780426,
      "learning_rate": 0.0001769977827050998,
      "loss": 0.6967,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.35411298274993896,
      "learning_rate": 0.00017593791574279378,
      "loss": 0.701,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.3787080645561218,
      "learning_rate": 0.00017487804878048782,
      "loss": 0.5901,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.4306442439556122,
      "learning_rate": 0.00017381818181818183,
      "loss": 0.652,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.43030846118927,
      "learning_rate": 0.00017275831485587582,
      "loss": 0.7147,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.3750913739204407,
      "learning_rate": 0.00017169844789356986,
      "loss": 0.6517,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.3687937557697296,
      "learning_rate": 0.00017063858093126387,
      "loss": 0.6481,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.37245458364486694,
      "learning_rate": 0.00016957871396895788,
      "loss": 0.703,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.35127994418144226,
      "learning_rate": 0.0001685188470066519,
      "loss": 0.6116,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.3911903500556946,
      "learning_rate": 0.0001674589800443459,
      "loss": 0.6367,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.3940306305885315,
      "learning_rate": 0.00016639911308203992,
      "loss": 0.6765,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.40002891421318054,
      "learning_rate": 0.00016533924611973394,
      "loss": 0.6013,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.42048192024230957,
      "learning_rate": 0.00016427937915742795,
      "loss": 0.6515,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.3791607618331909,
      "learning_rate": 0.00016321951219512197,
      "loss": 0.5838,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5695094466209412,
      "learning_rate": 0.00016215964523281595,
      "loss": 0.6227,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.3927454948425293,
      "learning_rate": 0.00016109977827051,
      "loss": 0.5797,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.37926599383354187,
      "learning_rate": 0.000160039911308204,
      "loss": 0.5397,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.3964325189590454,
      "learning_rate": 0.000158980044345898,
      "loss": 0.5796,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.38841575384140015,
      "learning_rate": 0.00015792017738359203,
      "loss": 0.4925,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.410722941160202,
      "learning_rate": 0.00015686031042128605,
      "loss": 0.5662,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.45456835627555847,
      "learning_rate": 0.00015580044345898003,
      "loss": 0.591,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.42649292945861816,
      "learning_rate": 0.00015474057649667407,
      "loss": 0.5464,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.4023902714252472,
      "learning_rate": 0.0001536807095343681,
      "loss": 0.5437,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.3795386850833893,
      "learning_rate": 0.00015262084257206207,
      "loss": 0.4971,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.40091997385025024,
      "learning_rate": 0.00015156097560975611,
      "loss": 0.5157,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.3627980649471283,
      "learning_rate": 0.00015050110864745013,
      "loss": 0.501,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.41095221042633057,
      "learning_rate": 0.00014944124168514411,
      "loss": 0.5733,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.46346715092658997,
      "learning_rate": 0.00014838137472283816,
      "loss": 0.5563,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.4056820571422577,
      "learning_rate": 0.00014732150776053217,
      "loss": 0.5715,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.4651278257369995,
      "learning_rate": 0.00014626164079822616,
      "loss": 0.4923,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.4463025629520416,
      "learning_rate": 0.0001452017738359202,
      "loss": 0.5858,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.44867852330207825,
      "learning_rate": 0.0001441419068736142,
      "loss": 0.558,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.41333332657814026,
      "learning_rate": 0.0001430820399113082,
      "loss": 0.5505,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.4120679795742035,
      "learning_rate": 0.00014202217294900224,
      "loss": 0.5335,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.4014519453048706,
      "learning_rate": 0.00014096230598669625,
      "loss": 0.522,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.4796731472015381,
      "learning_rate": 0.00013990243902439024,
      "loss": 0.5727,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.44720908999443054,
      "learning_rate": 0.00013884257206208425,
      "loss": 0.5739,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.49437999725341797,
      "learning_rate": 0.0001377827050997783,
      "loss": 0.567,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.45990318059921265,
      "learning_rate": 0.00013672283813747228,
      "loss": 0.5099,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.48705539107322693,
      "learning_rate": 0.0001356629711751663,
      "loss": 0.5058,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.42516469955444336,
      "learning_rate": 0.00013460310421286033,
      "loss": 0.5034,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.4437274932861328,
      "learning_rate": 0.00013354323725055432,
      "loss": 0.538,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.48122531175613403,
      "learning_rate": 0.00013248337028824833,
      "loss": 0.5472,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.5141119956970215,
      "learning_rate": 0.00013142350332594237,
      "loss": 0.5172,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.48253554105758667,
      "learning_rate": 0.00013036363636363636,
      "loss": 0.5747,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.5002180337905884,
      "learning_rate": 0.00012930376940133037,
      "loss": 0.5413,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.5182358622550964,
      "learning_rate": 0.0001282439024390244,
      "loss": 0.5553,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.49602043628692627,
      "learning_rate": 0.0001271840354767184,
      "loss": 0.5302,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.4516575038433075,
      "learning_rate": 0.0001261241685144124,
      "loss": 0.5145,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.5268491506576538,
      "learning_rate": 0.00012506430155210645,
      "loss": 0.6026,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.5656492710113525,
      "learning_rate": 0.00012400443458980044,
      "loss": 0.6146,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.4348342716693878,
      "learning_rate": 0.00012294456762749445,
      "loss": 0.5895,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.4370437562465668,
      "learning_rate": 0.00012188470066518848,
      "loss": 0.5207,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.49735766649246216,
      "learning_rate": 0.00012082483370288248,
      "loss": 0.5473,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.45202648639678955,
      "learning_rate": 0.0001197649667405765,
      "loss": 0.5432,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.44890251755714417,
      "learning_rate": 0.00011870509977827052,
      "loss": 0.498,
      "step": 345
    }
  ],
  "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": 1.5785457601174733e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}