{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0725274725274727,
  "eval_steps": 500,
  "global_step": 315,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.3811920881271362,
      "learning_rate": 0.0,
      "loss": 2.4074,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.1602140665054321,
      "learning_rate": 4e-05,
      "loss": 2.2839,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.8319995403289795,
      "learning_rate": 8e-05,
      "loss": 3.1302,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.870302677154541,
      "learning_rate": 0.00012,
      "loss": 2.6291,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.9151116609573364,
      "learning_rate": 0.00016,
      "loss": 2.2489,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.155876636505127,
      "learning_rate": 0.0002,
      "loss": 2.2943,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.1148955821990967,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.849,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.934097409248352,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.722,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8389161825180054,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.4487,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.9894236922264099,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1892,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.993594765663147,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.1734,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.7020053267478943,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1522,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.6377735137939453,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1678,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5987263917922974,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.2205,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.45545557141304016,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.2664,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.41364356875419617,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.2119,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.38649460673332214,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.041,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.3318747878074646,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9883,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4029198884963989,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.1352,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.41015514731407166,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.077,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3768792450428009,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9937,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.37947240471839905,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.0659,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.36634671688079834,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.1018,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.330288827419281,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8562,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.33478638529777527,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.0718,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.4069267511367798,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9157,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.31170564889907837,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9145,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.352420449256897,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0871,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.36795908212661743,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.1471,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.30119454860687256,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.095,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.31143656373023987,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.9926,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.32986146211624146,
      "learning_rate": 0.00018847006651884703,
      "loss": 1.0715,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.296937495470047,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.1942,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2734869420528412,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.0527,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.32269832491874695,
      "learning_rate": 0.00018713968957871397,
      "loss": 1.0471,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3464144766330719,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.9689,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3004181385040283,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.983,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.310374915599823,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.9668,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3439410924911499,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9566,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.32972270250320435,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9076,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.305091917514801,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.8555,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3746737539768219,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.1334,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.32704272866249084,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.9888,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.37634921073913574,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.0156,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.35462135076522827,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.0956,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.26339033246040344,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9784,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.2839420437812805,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.8358,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.3123251795768738,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.0008,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.31478673219680786,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9974,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.4063723385334015,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.0785,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.348345011472702,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0264,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.2888275682926178,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9065,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3500926196575165,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9085,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2687546908855438,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9944,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.2749953866004944,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.8673,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3421938717365265,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.8816,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.25709301233291626,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8322,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.32386237382888794,
      "learning_rate": 0.000176940133037694,
      "loss": 0.9619,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3056727945804596,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.9981,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.309624046087265,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.877,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.31504714488983154,
      "learning_rate": 0.000175609756097561,
      "loss": 0.8403,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3200717866420746,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.8984,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.2880253791809082,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.9097,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.2771207094192505,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.929,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.34761157631874084,
      "learning_rate": 0.0001738359201773836,
      "loss": 1.1349,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.33324652910232544,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9871,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.28624290227890015,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9669,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3222275674343109,
      "learning_rate": 0.00017250554323725056,
      "loss": 1.1397,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.30758264660835266,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9979,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3401052951812744,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.1765,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3259827196598053,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.1234,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.26390549540519714,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.8297,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.3299182951450348,
      "learning_rate": 0.00017028824833702883,
      "loss": 1.0228,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.34075310826301575,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.8968,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3508496582508087,
      "learning_rate": 0.00016940133037694015,
      "loss": 1.0168,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3906101882457733,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9841,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.35411369800567627,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.0248,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.29985886812210083,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9614,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3597535789012909,
      "learning_rate": 0.00016762749445676275,
      "loss": 1.1809,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.34332171082496643,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.1002,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3691633939743042,
      "learning_rate": 0.00016674057649667407,
      "loss": 1.0131,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3695796728134155,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.016,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.4563911557197571,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.0426,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.35026583075523376,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9062,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.29392629861831665,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.0741,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3824733793735504,
      "learning_rate": 0.00016452328159645234,
      "loss": 1.0026,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3096954822540283,
      "learning_rate": 0.000164079822616408,
      "loss": 0.9873,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.36505717039108276,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9611,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.34280988574028015,
      "learning_rate": 0.0001631929046563193,
      "loss": 1.0564,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.2732785940170288,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.8998,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3460013270378113,
      "learning_rate": 0.0001623059866962306,
      "loss": 1.1162,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3438647389411926,
      "learning_rate": 0.00016186252771618626,
      "loss": 1.0306,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.2942659556865692,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.8644,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.29716387391090393,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.8981,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.2853240966796875,
      "learning_rate": 0.00016053215077605322,
      "loss": 1.0931,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3307726979255676,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.8001,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.27847638726234436,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9187,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.36320236325263977,
      "learning_rate": 0.00015920177383592018,
      "loss": 1.3116,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.32366451621055603,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.8453,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.30113381147384644,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9299,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.29754576086997986,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.09,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.28849929571151733,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8432,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3458065390586853,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.8066,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.32526496052742004,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.9838,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.2753767669200897,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.8748,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.318471759557724,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.0128,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.33525350689888,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.9742,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.2945750951766968,
      "learning_rate": 0.0001547671840354767,
      "loss": 1.0353,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.3046523928642273,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9937,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.3300830125808716,
      "learning_rate": 0.00015388026607538802,
      "loss": 1.0916,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3568447530269623,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.8268,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.3059159815311432,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.9796,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.30546003580093384,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.8564,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.32714706659317017,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.8371,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.2836191952228546,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9791,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.29888391494750977,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.8368,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.30832260847091675,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9593,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3636506497859955,
      "learning_rate": 0.0001503325942350333,
      "loss": 1.0048,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3550063967704773,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.7936,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3425007164478302,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.9733,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.32022032141685486,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.8501,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.3691856563091278,
      "learning_rate": 0.0001485587583148559,
      "loss": 1.0348,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3445797562599182,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.9769,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.36145415902137756,
      "learning_rate": 0.0001476718403547672,
      "loss": 1.008,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3763088583946228,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.9301,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.28162434697151184,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.9811,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.2691023647785187,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.8787,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.3300941586494446,
      "learning_rate": 0.0001458980044345898,
      "loss": 1.1127,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3238241672515869,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.9611,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.362900048494339,
      "learning_rate": 0.00014501108647450113,
      "loss": 1.0181,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3071531057357788,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.9975,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.30482736229896545,
      "learning_rate": 0.00014412416851441242,
      "loss": 1.0626,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.3414318263530731,
      "learning_rate": 0.00014368070953436806,
      "loss": 1.0023,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3004287779331207,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.8561,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.333492249250412,
      "learning_rate": 0.00014279379157427938,
      "loss": 1.0141,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.3137277066707611,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.9367,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3388824760913849,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.9451,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.32571226358413696,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.9266,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.3652912378311157,
      "learning_rate": 0.000141019955654102,
      "loss": 0.9614,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.33211708068847656,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.8914,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3609882593154907,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.8518,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.32345569133758545,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.9509,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.35085490345954895,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.8458,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.34508341550827026,
      "learning_rate": 0.00013880266075388026,
      "loss": 1.0389,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.47932854294776917,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.9406,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.36878255009651184,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.9495,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3231103718280792,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.8088,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.29075154662132263,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.9349,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.34949028491973877,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.983,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.31099194288253784,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.956,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.35499194264411926,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.8879,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.43646296858787537,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.7941,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.30879101157188416,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.8986,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.34262481331825256,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.8466,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3679031431674957,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.9952,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.35594701766967773,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.8475,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.32133790850639343,
      "learning_rate": 0.00013303769401330377,
      "loss": 1.1176,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3077213168144226,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.9752,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.37782880663871765,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.9863,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3571804165840149,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.8647,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.4493478238582611,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7936,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.34722283482551575,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.8263,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.3414715528488159,
      "learning_rate": 0.0001303769401330377,
      "loss": 1.0,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.36553120613098145,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.8784,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.4135945439338684,
      "learning_rate": 0.000129490022172949,
      "loss": 0.9416,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3653314709663391,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.8756,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.3750187158584595,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.9377,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.34501907229423523,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.9824,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.36142048239707947,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.964,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.37406840920448303,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.7455,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3261415958404541,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.9754,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.37785905599594116,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.8755,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.4342544376850128,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.9069,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.3809872269630432,
      "learning_rate": 0.00012549889135254989,
      "loss": 1.0354,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.44167035818099976,
      "learning_rate": 0.00012505543237250553,
      "loss": 1.0236,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.39276036620140076,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.9112,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.44575512409210205,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.9016,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.34426161646842957,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.7511,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.4274899661540985,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.9918,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.3838531970977783,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.8497,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.42053210735321045,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.7753,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.3414655029773712,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.6518,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.37465909123420715,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.7442,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.4132935106754303,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.828,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.40961402654647827,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.8608,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.41758406162261963,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.9602,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.39394980669021606,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.8228,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.4103316068649292,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.9203,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.4683172404766083,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.9148,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.43221455812454224,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.8999,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.48005807399749756,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.7599,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.3963695764541626,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.8715,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4713021218776703,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.983,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.4138881266117096,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.8445,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.4260016679763794,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.8957,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.4461864233016968,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.8767,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.5024107098579407,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.7977,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4576614499092102,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.8428,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.41738060116767883,
      "learning_rate": 0.00011441241685144124,
      "loss": 1.0596,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.4091884195804596,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.6286,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.48064282536506653,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.8377,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.46567344665527344,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.7523,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.3642124831676483,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.8026,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4464606046676636,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.7965,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.4099564254283905,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.8065,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.40912213921546936,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.7349,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.4927590489387512,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.8816,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.4889482855796814,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.8872,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.4548379182815552,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.7995,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.4733491539955139,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.8446,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.47942036390304565,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.9461,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.5793269276618958,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.9457,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.5649895668029785,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.9208,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.5023480653762817,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.9147,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.5141881704330444,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.9027,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.44841939210891724,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.9438,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.4795355498790741,
      "learning_rate": 0.00010643015521064301,
      "loss": 1.0307,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.48444321751594543,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.9905,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.42991480231285095,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.8254,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.5515939593315125,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.8913,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.489729642868042,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.8164,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.46348434686660767,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.8413,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.4178984761238098,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.8691,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.49219754338264465,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.807,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.4845030903816223,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.9028,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.4843251705169678,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.9402,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.5330051183700562,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.8474,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.46163877844810486,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.7967,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.48188892006874084,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.9385,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.581975519657135,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.9194,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.5488189458847046,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.8501,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.5423700213432312,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.8197,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.5232661366462708,
      "learning_rate": 9.933481152993348e-05,
      "loss": 1.0412,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.510104238986969,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.8093,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.5215854048728943,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.7906,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.5600224733352661,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.824,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.5537103414535522,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.8347,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.5224615931510925,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.8002,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.49553102254867554,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.836,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.5366898775100708,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.7379,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.48425981402397156,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.8159,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.5496232509613037,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.9894,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.5164010524749756,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.8715,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.49101150035858154,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.7673,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.47393888235092163,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.7917,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.602984607219696,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.8634,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.5482746362686157,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.7762,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.4565388262271881,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.8436,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.46821677684783936,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.778,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.49466970562934875,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.8255,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.4536782503128052,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.9369,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.553232729434967,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.8113,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.5385431051254272,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.814,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.5508939623832703,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.8658,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.5805878043174744,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.835,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.5162469744682312,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.7308,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.6074327826499939,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.8426,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.5325859189033508,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.7929,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.5415855646133423,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.6677,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.639832615852356,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.7386,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.5412299036979675,
      "learning_rate": 8.69179600886918e-05,
      "loss": 1.075,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.4979498088359833,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.8098,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.5330032706260681,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.8261,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.591980516910553,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.9122,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.5644874572753906,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.8284,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.5778195261955261,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.878,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.591587245464325,
      "learning_rate": 8.425720620842572e-05,
      "loss": 1.0132,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.4799944758415222,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.8176,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.5877734422683716,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.8785,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.5516407489776611,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.9344,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.6243887543678284,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.9967,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.5267444252967834,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.8372,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.5111743807792664,
      "learning_rate": 8.159645232815965e-05,
      "loss": 1.025,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.545026421546936,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.8219,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.5710747838020325,
      "learning_rate": 8.070953436807095e-05,
      "loss": 1.0502,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.6957282423973083,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.9715,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.5677179098129272,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.9274,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.5105527639389038,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.8956,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.5264143347740173,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.7976,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.5719877481460571,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.8344,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.5348645448684692,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.8547,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.48854389786720276,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.8108,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.5082598924636841,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.92,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.5953463315963745,
      "learning_rate": 7.671840354767185e-05,
      "loss": 1.0027,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.4982782006263733,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.8543,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.4882511794567108,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.8542,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.4724072217941284,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.7406,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.6163045167922974,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.8405,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.4670993983745575,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.7763,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.5541887879371643,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.8485,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.543720543384552,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.7993,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.6802257895469666,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.9231,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.6244099736213684,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.7802,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.5423873066902161,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.887,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.5621044039726257,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.8598,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.5742719769477844,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.8576,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.6025928258895874,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.9631,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.5526483654975891,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.8072,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.5989035964012146,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.9605,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.6198786497116089,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.8598,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.58564293384552,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.9078,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.585856020450592,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.86,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.5899369716644287,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.777,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6699763536453247,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.7863,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.4946701228618622,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.6584,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.6134518384933472,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.822,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.43551310896873474,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.5719,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.5584573745727539,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.6236,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.46903643012046814,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.6923,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.4920395016670227,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.8235,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.49655547738075256,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.7529,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.5522664785385132,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.8788,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.5621050000190735,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.7021,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.6896621584892273,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.735,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.5521341562271118,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.8088,
      "step": 315
    }
  ],
  "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": 4.316268715337318e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}