{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 288,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 2.0365,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 2.066,
      "step": 2
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.0303,
      "step": 3
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.888888888888889e-05,
      "loss": 2.0011,
      "step": 4
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00011111111111111112,
      "loss": 1.9033,
      "step": 5
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.8849,
      "step": 6
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.8357,
      "step": 7
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.7318,
      "step": 8
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.77,
      "step": 9
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001999936604744804,
      "loss": 1.679,
      "step": 10
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001999746427017133,
      "loss": 1.6819,
      "step": 11
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001999429490929718,
      "loss": 1.6999,
      "step": 12
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019989858366670476,
      "loss": 1.6876,
      "step": 13
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019984155204802714,
      "loss": 1.6702,
      "step": 14
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019977186146800707,
      "loss": 1.6607,
      "step": 15
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019968952076274872,
      "loss": 1.6519,
      "step": 16
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019959454037227214,
      "loss": 1.6445,
      "step": 17
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019948693233918952,
      "loss": 1.6258,
      "step": 18
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001993667103071783,
      "loss": 1.5944,
      "step": 19
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019923388951925125,
      "loss": 1.6484,
      "step": 20
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019908848681582391,
      "loss": 1.6131,
      "step": 21
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001989305206325792,
      "loss": 1.6264,
      "step": 22
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019876001099813017,
      "loss": 1.6238,
      "step": 23
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019857697953148037,
      "loss": 1.6249,
      "step": 24
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001983814494392829,
      "loss": 1.5891,
      "step": 25
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019817344551289795,
      "loss": 1.6246,
      "step": 26
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019795299412524945,
      "loss": 1.615,
      "step": 27
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001977201232274814,
      "loss": 1.5451,
      "step": 28
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019747486234541383,
      "loss": 1.5968,
      "step": 29
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019721724257579907,
      "loss": 1.5895,
      "step": 30
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019694729658237926,
      "loss": 1.6084,
      "step": 31
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019666505859174463,
      "loss": 1.5562,
      "step": 32
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001963705643889941,
      "loss": 1.5704,
      "step": 33
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019606385131319792,
      "loss": 1.5856,
      "step": 34
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019574495825266358,
      "loss": 1.6082,
      "step": 35
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019541392564000488,
      "loss": 1.5809,
      "step": 36
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019507079544701583,
      "loss": 1.6034,
      "step": 37
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019471561117934868,
      "loss": 1.5573,
      "step": 38
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019434841787099803,
      "loss": 1.5286,
      "step": 39
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019396926207859084,
      "loss": 1.5683,
      "step": 40
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001935781918754836,
      "loss": 1.5521,
      "step": 41
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00019317525684566685,
      "loss": 1.5245,
      "step": 42
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001927605080774788,
      "loss": 1.5501,
      "step": 43
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00019233399815712736,
      "loss": 1.5389,
      "step": 44
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00019189578116202307,
      "loss": 1.5595,
      "step": 45
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001914459126539224,
      "loss": 1.5618,
      "step": 46
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00019098444967188306,
      "loss": 1.5576,
      "step": 47
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00019051145072503215,
      "loss": 1.4294,
      "step": 48
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00019002697578514747,
      "loss": 1.3713,
      "step": 49
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018953108627905394,
      "loss": 1.4402,
      "step": 50
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018902384508083517,
      "loss": 1.3995,
      "step": 51
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00018850531650386153,
      "loss": 1.374,
      "step": 52
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00018797556629263602,
      "loss": 1.3839,
      "step": 53
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018743466161445823,
      "loss": 1.3465,
      "step": 54
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001868826710509084,
      "loss": 1.4043,
      "step": 55
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001863196645891518,
      "loss": 1.3152,
      "step": 56
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001857457136130651,
      "loss": 1.3446,
      "step": 57
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00018516089089418549,
      "loss": 1.3554,
      "step": 58
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.000184565270582484,
      "loss": 1.3529,
      "step": 59
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00018395892819696389,
      "loss": 1.3498,
      "step": 60
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00018334194061608576,
      "loss": 1.3836,
      "step": 61
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00018271438606801986,
      "loss": 1.3502,
      "step": 62
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00018207634412072764,
      "loss": 1.3961,
      "step": 63
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00018142789567187327,
      "loss": 1.319,
      "step": 64
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001807691229385665,
      "loss": 1.3707,
      "step": 65
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00018010010944693848,
      "loss": 1.3051,
      "step": 66
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001794209400215512,
      "loss": 1.3259,
      "step": 67
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00017873170077464283,
      "loss": 1.3874,
      "step": 68
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001780324790952092,
      "loss": 1.3599,
      "step": 69
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00017732336363792395,
      "loss": 1.3649,
      "step": 70
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001766044443118978,
      "loss": 1.3707,
      "step": 71
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001758758122692791,
      "loss": 1.3653,
      "step": 72
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00017513755989369636,
      "loss": 1.3411,
      "step": 73
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00017438978078854512,
      "loss": 1.3397,
      "step": 74
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00017363256976511972,
      "loss": 1.3914,
      "step": 75
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00017286602283059238,
      "loss": 1.3515,
      "step": 76
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00017209023717584013,
      "loss": 1.3399,
      "step": 77
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00017130531116312203,
      "loss": 1.3233,
      "step": 78
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00017051134431360796,
      "loss": 1.3346,
      "step": 79
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00016970843729475991,
      "loss": 1.3604,
      "step": 80
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00016889669190756868,
      "loss": 1.3503,
      "step": 81
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00016807621107364613,
      "loss": 1.3472,
      "step": 82
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00016724709882217603,
      "loss": 1.3482,
      "step": 83
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00016640946027672392,
      "loss": 1.3414,
      "step": 84
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00016556340164190845,
      "loss": 1.4021,
      "step": 85
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00016470903018993578,
      "loss": 1.3689,
      "step": 86
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00016384645424699835,
      "loss": 1.3341,
      "step": 87
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00016297578317954025,
      "loss": 1.3414,
      "step": 88
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00016209712738039049,
      "loss": 1.3386,
      "step": 89
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001612105982547663,
      "loss": 1.3425,
      "step": 90
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00016031630820614797,
      "loss": 1.3599,
      "step": 91
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001594143706220273,
      "loss": 1.3706,
      "step": 92
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00015850489985953076,
      "loss": 1.3107,
      "step": 93
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00015758801123092066,
      "loss": 1.3324,
      "step": 94
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00015666382098897412,
      "loss": 1.3469,
      "step": 95
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00015573244631224365,
      "loss": 1.1865,
      "step": 96
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00015479400529019985,
      "loss": 1.181,
      "step": 97
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001538486169082589,
      "loss": 1.1968,
      "step": 98
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00015289640103269625,
      "loss": 1.1365,
      "step": 99
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00015193747839544876,
      "loss": 1.1734,
      "step": 100
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00015097197057880706,
      "loss": 1.1399,
      "step": 101
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0993,
      "step": 102
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00014902168989567335,
      "loss": 1.1613,
      "step": 103
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00014803716430626456,
      "loss": 1.1317,
      "step": 104
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0001470465480602756,
      "loss": 1.1656,
      "step": 105
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00014604996675844585,
      "loss": 1.1501,
      "step": 106
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001450475467578273,
      "loss": 1.1233,
      "step": 107
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00014403941515576344,
      "loss": 1.1439,
      "step": 108
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001430256997737746,
      "loss": 1.1664,
      "step": 109
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0001420065291413515,
      "loss": 1.1584,
      "step": 110
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00014098203247965875,
      "loss": 1.1161,
      "step": 111
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00013995233968515104,
      "loss": 1.1207,
      "step": 112
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0001389175813131033,
      "loss": 1.1216,
      "step": 113
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0001378778885610576,
      "loss": 1.1373,
      "step": 114
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00013683339325218873,
      "loss": 1.1292,
      "step": 115
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00013578422781858993,
      "loss": 1.1381,
      "step": 116
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00013473052528448201,
      "loss": 1.1236,
      "step": 117
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00013367241924934714,
      "loss": 1.1479,
      "step": 118
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0001326100438709895,
      "loss": 1.1445,
      "step": 119
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00013154353384852558,
      "loss": 1.1658,
      "step": 120
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00013047302440530537,
      "loss": 1.1165,
      "step": 121
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0001293986512717677,
      "loss": 1.1418,
      "step": 122
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00012832055066823038,
      "loss": 1.1195,
      "step": 123
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.00012723885928761933,
      "loss": 1.1395,
      "step": 124
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0001261537142781367,
      "loss": 1.1039,
      "step": 125
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.00012506525322587207,
      "loss": 1.1465,
      "step": 126
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.00012397361413735784,
      "loss": 1.1199,
      "step": 127
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0001228789354220712,
      "loss": 1.1098,
      "step": 128
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.00012178135587488515,
      "loss": 1.1116,
      "step": 129
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00012068101465847075,
      "loss": 1.1007,
      "step": 130
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.00011957805128565232,
      "loss": 1.1688,
      "step": 131
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.00011847260560171896,
      "loss": 1.1404,
      "step": 132
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00011736481776669306,
      "loss": 1.1526,
      "step": 133
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00011625482823755965,
      "loss": 1.1444,
      "step": 134
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00011514277775045768,
      "loss": 1.1252,
      "step": 135
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.00011402880730283598,
      "loss": 1.1544,
      "step": 136
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00011291305813557615,
      "loss": 1.1349,
      "step": 137
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00011179567171508463,
      "loss": 1.1086,
      "step": 138
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.00011067678971535589,
      "loss": 1.1274,
      "step": 139
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.00010955655400000984,
      "loss": 1.1648,
      "step": 140
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.00010843510660430447,
      "loss": 1.1158,
      "step": 141
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00010731258971712761,
      "loss": 1.1279,
      "step": 142
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0001061891456629682,
      "loss": 1.1101,
      "step": 143
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00010506491688387127,
      "loss": 1.0081,
      "step": 144
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00010394004592137757,
      "loss": 0.9643,
      "step": 145
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.00010281467539845051,
      "loss": 0.9642,
      "step": 146
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.0001016889480013931,
      "loss": 0.9563,
      "step": 147
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0001005630064617566,
      "loss": 0.9485,
      "step": 148
    },
    {
      "epoch": 3.1,
      "learning_rate": 9.943699353824345e-05,
      "loss": 0.9159,
      "step": 149
    },
    {
      "epoch": 3.12,
      "learning_rate": 9.83110519986069e-05,
      "loss": 0.9132,
      "step": 150
    },
    {
      "epoch": 3.15,
      "learning_rate": 9.718532460154948e-05,
      "loss": 0.929,
      "step": 151
    },
    {
      "epoch": 3.17,
      "learning_rate": 9.605995407862247e-05,
      "loss": 0.9148,
      "step": 152
    },
    {
      "epoch": 3.19,
      "learning_rate": 9.493508311612874e-05,
      "loss": 0.9436,
      "step": 153
    },
    {
      "epoch": 3.21,
      "learning_rate": 9.381085433703182e-05,
      "loss": 0.9221,
      "step": 154
    },
    {
      "epoch": 3.23,
      "learning_rate": 9.268741028287239e-05,
      "loss": 0.8885,
      "step": 155
    },
    {
      "epoch": 3.25,
      "learning_rate": 9.156489339569554e-05,
      "loss": 0.9517,
      "step": 156
    },
    {
      "epoch": 3.27,
      "learning_rate": 9.04434459999902e-05,
      "loss": 0.9354,
      "step": 157
    },
    {
      "epoch": 3.29,
      "learning_rate": 8.932321028464412e-05,
      "loss": 0.9805,
      "step": 158
    },
    {
      "epoch": 3.31,
      "learning_rate": 8.820432828491542e-05,
      "loss": 0.95,
      "step": 159
    },
    {
      "epoch": 3.33,
      "learning_rate": 8.708694186442388e-05,
      "loss": 0.953,
      "step": 160
    },
    {
      "epoch": 3.35,
      "learning_rate": 8.597119269716403e-05,
      "loss": 0.9426,
      "step": 161
    },
    {
      "epoch": 3.38,
      "learning_rate": 8.485722224954237e-05,
      "loss": 0.9284,
      "step": 162
    },
    {
      "epoch": 3.4,
      "learning_rate": 8.374517176244038e-05,
      "loss": 0.9287,
      "step": 163
    },
    {
      "epoch": 3.42,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.9112,
      "step": 164
    },
    {
      "epoch": 3.44,
      "learning_rate": 8.15273943982811e-05,
      "loss": 0.9438,
      "step": 165
    },
    {
      "epoch": 3.46,
      "learning_rate": 8.04219487143477e-05,
      "loss": 0.9362,
      "step": 166
    },
    {
      "epoch": 3.48,
      "learning_rate": 7.931898534152928e-05,
      "loss": 0.9414,
      "step": 167
    },
    {
      "epoch": 3.5,
      "learning_rate": 7.821864412511485e-05,
      "loss": 0.9463,
      "step": 168
    },
    {
      "epoch": 3.52,
      "learning_rate": 7.712106457792884e-05,
      "loss": 0.9643,
      "step": 169
    },
    {
      "epoch": 3.54,
      "learning_rate": 7.602638586264219e-05,
      "loss": 0.9276,
      "step": 170
    },
    {
      "epoch": 3.56,
      "learning_rate": 7.493474677412794e-05,
      "loss": 0.9255,
      "step": 171
    },
    {
      "epoch": 3.58,
      "learning_rate": 7.384628572186333e-05,
      "loss": 0.9094,
      "step": 172
    },
    {
      "epoch": 3.6,
      "learning_rate": 7.276114071238069e-05,
      "loss": 0.9376,
      "step": 173
    },
    {
      "epoch": 3.62,
      "learning_rate": 7.16794493317696e-05,
      "loss": 0.9424,
      "step": 174
    },
    {
      "epoch": 3.65,
      "learning_rate": 7.060134872823234e-05,
      "loss": 0.92,
      "step": 175
    },
    {
      "epoch": 3.67,
      "learning_rate": 6.952697559469464e-05,
      "loss": 0.9739,
      "step": 176
    },
    {
      "epoch": 3.69,
      "learning_rate": 6.845646615147445e-05,
      "loss": 0.9308,
      "step": 177
    },
    {
      "epoch": 3.71,
      "learning_rate": 6.738995612901051e-05,
      "loss": 0.9392,
      "step": 178
    },
    {
      "epoch": 3.73,
      "learning_rate": 6.632758075065288e-05,
      "loss": 0.9179,
      "step": 179
    },
    {
      "epoch": 3.75,
      "learning_rate": 6.526947471551798e-05,
      "loss": 0.9393,
      "step": 180
    },
    {
      "epoch": 3.77,
      "learning_rate": 6.421577218141008e-05,
      "loss": 0.9353,
      "step": 181
    },
    {
      "epoch": 3.79,
      "learning_rate": 6.31666067478113e-05,
      "loss": 0.9051,
      "step": 182
    },
    {
      "epoch": 3.81,
      "learning_rate": 6.21221114389424e-05,
      "loss": 0.9285,
      "step": 183
    },
    {
      "epoch": 3.83,
      "learning_rate": 6.108241868689675e-05,
      "loss": 0.9345,
      "step": 184
    },
    {
      "epoch": 3.85,
      "learning_rate": 6.0047660314849006e-05,
      "loss": 0.8936,
      "step": 185
    },
    {
      "epoch": 3.88,
      "learning_rate": 5.901796752034128e-05,
      "loss": 0.9324,
      "step": 186
    },
    {
      "epoch": 3.9,
      "learning_rate": 5.799347085864851e-05,
      "loss": 0.9514,
      "step": 187
    },
    {
      "epoch": 3.92,
      "learning_rate": 5.697430022622542e-05,
      "loss": 0.9571,
      "step": 188
    },
    {
      "epoch": 3.94,
      "learning_rate": 5.596058484423656e-05,
      "loss": 0.9109,
      "step": 189
    },
    {
      "epoch": 3.96,
      "learning_rate": 5.495245324217271e-05,
      "loss": 0.92,
      "step": 190
    },
    {
      "epoch": 3.98,
      "learning_rate": 5.3950033241554146e-05,
      "loss": 0.9387,
      "step": 191
    },
    {
      "epoch": 4.0,
      "learning_rate": 5.2953451939724454e-05,
      "loss": 0.8087,
      "step": 192
    },
    {
      "epoch": 4.02,
      "learning_rate": 5.19628356937355e-05,
      "loss": 0.8224,
      "step": 193
    },
    {
      "epoch": 4.04,
      "learning_rate": 5.097831010432666e-05,
      "loss": 0.7526,
      "step": 194
    },
    {
      "epoch": 4.06,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.7709,
      "step": 195
    },
    {
      "epoch": 4.08,
      "learning_rate": 4.902802942119293e-05,
      "loss": 0.7642,
      "step": 196
    },
    {
      "epoch": 4.1,
      "learning_rate": 4.806252160455125e-05,
      "loss": 0.7933,
      "step": 197
    },
    {
      "epoch": 4.12,
      "learning_rate": 4.710359896730379e-05,
      "loss": 0.789,
      "step": 198
    },
    {
      "epoch": 4.15,
      "learning_rate": 4.6151383091741115e-05,
      "loss": 0.7902,
      "step": 199
    },
    {
      "epoch": 4.17,
      "learning_rate": 4.520599470980015e-05,
      "loss": 0.7809,
      "step": 200
    },
    {
      "epoch": 4.19,
      "learning_rate": 4.426755368775637e-05,
      "loss": 0.75,
      "step": 201
    },
    {
      "epoch": 4.21,
      "learning_rate": 4.333617901102591e-05,
      "loss": 0.8145,
      "step": 202
    },
    {
      "epoch": 4.23,
      "learning_rate": 4.241198876907936e-05,
      "loss": 0.796,
      "step": 203
    },
    {
      "epoch": 4.25,
      "learning_rate": 4.149510014046922e-05,
      "loss": 0.7791,
      "step": 204
    },
    {
      "epoch": 4.27,
      "learning_rate": 4.0585629377972744e-05,
      "loss": 0.7962,
      "step": 205
    },
    {
      "epoch": 4.29,
      "learning_rate": 3.968369179385204e-05,
      "loss": 0.7876,
      "step": 206
    },
    {
      "epoch": 4.31,
      "learning_rate": 3.878940174523371e-05,
      "loss": 0.7861,
      "step": 207
    },
    {
      "epoch": 4.33,
      "learning_rate": 3.790287261960953e-05,
      "loss": 0.7772,
      "step": 208
    },
    {
      "epoch": 4.35,
      "learning_rate": 3.7024216820459756e-05,
      "loss": 0.7788,
      "step": 209
    },
    {
      "epoch": 4.38,
      "learning_rate": 3.615354575300166e-05,
      "loss": 0.8003,
      "step": 210
    },
    {
      "epoch": 4.4,
      "learning_rate": 3.5290969810064255e-05,
      "loss": 0.7462,
      "step": 211
    },
    {
      "epoch": 4.42,
      "learning_rate": 3.443659835809158e-05,
      "loss": 0.7519,
      "step": 212
    },
    {
      "epoch": 4.44,
      "learning_rate": 3.3590539723276083e-05,
      "loss": 0.7578,
      "step": 213
    },
    {
      "epoch": 4.46,
      "learning_rate": 3.275290117782397e-05,
      "loss": 0.7778,
      "step": 214
    },
    {
      "epoch": 4.48,
      "learning_rate": 3.1923788926353884e-05,
      "loss": 0.7937,
      "step": 215
    },
    {
      "epoch": 4.5,
      "learning_rate": 3.110330809243134e-05,
      "loss": 0.79,
      "step": 216
    },
    {
      "epoch": 4.52,
      "learning_rate": 3.0291562705240105e-05,
      "loss": 0.7717,
      "step": 217
    },
    {
      "epoch": 4.54,
      "learning_rate": 2.9488655686392086e-05,
      "loss": 0.7414,
      "step": 218
    },
    {
      "epoch": 4.56,
      "learning_rate": 2.869468883687798e-05,
      "loss": 0.7859,
      "step": 219
    },
    {
      "epoch": 4.58,
      "learning_rate": 2.790976282415989e-05,
      "loss": 0.7633,
      "step": 220
    },
    {
      "epoch": 4.6,
      "learning_rate": 2.713397716940763e-05,
      "loss": 0.7858,
      "step": 221
    },
    {
      "epoch": 4.62,
      "learning_rate": 2.6367430234880284e-05,
      "loss": 0.8008,
      "step": 222
    },
    {
      "epoch": 4.65,
      "learning_rate": 2.56102192114549e-05,
      "loss": 0.7677,
      "step": 223
    },
    {
      "epoch": 4.67,
      "learning_rate": 2.4862440106303665e-05,
      "loss": 0.7928,
      "step": 224
    },
    {
      "epoch": 4.69,
      "learning_rate": 2.4124187730720917e-05,
      "loss": 0.7949,
      "step": 225
    },
    {
      "epoch": 4.71,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.7621,
      "step": 226
    },
    {
      "epoch": 4.73,
      "learning_rate": 2.2676636362076076e-05,
      "loss": 0.7776,
      "step": 227
    },
    {
      "epoch": 4.75,
      "learning_rate": 2.1967520904790827e-05,
      "loss": 0.7959,
      "step": 228
    },
    {
      "epoch": 4.77,
      "learning_rate": 2.126829922535718e-05,
      "loss": 0.7657,
      "step": 229
    },
    {
      "epoch": 4.79,
      "learning_rate": 2.05790599784488e-05,
      "loss": 0.7759,
      "step": 230
    },
    {
      "epoch": 4.81,
      "learning_rate": 1.9899890553061562e-05,
      "loss": 0.7679,
      "step": 231
    },
    {
      "epoch": 4.83,
      "learning_rate": 1.9230877061433507e-05,
      "loss": 0.7726,
      "step": 232
    },
    {
      "epoch": 4.85,
      "learning_rate": 1.857210432812674e-05,
      "loss": 0.7841,
      "step": 233
    },
    {
      "epoch": 4.88,
      "learning_rate": 1.7923655879272393e-05,
      "loss": 0.762,
      "step": 234
    },
    {
      "epoch": 4.9,
      "learning_rate": 1.728561393198016e-05,
      "loss": 0.7579,
      "step": 235
    },
    {
      "epoch": 4.92,
      "learning_rate": 1.6658059383914248e-05,
      "loss": 0.7911,
      "step": 236
    },
    {
      "epoch": 4.94,
      "learning_rate": 1.60410718030361e-05,
      "loss": 0.7901,
      "step": 237
    },
    {
      "epoch": 4.96,
      "learning_rate": 1.5434729417516047e-05,
      "loss": 0.7889,
      "step": 238
    },
    {
      "epoch": 4.98,
      "learning_rate": 1.483910910581452e-05,
      "loss": 0.7559,
      "step": 239
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.425428638693489e-05,
      "loss": 0.7221,
      "step": 240
    },
    {
      "epoch": 5.02,
      "learning_rate": 1.368033541084821e-05,
      "loss": 0.6921,
      "step": 241
    },
    {
      "epoch": 5.04,
      "learning_rate": 1.3117328949091634e-05,
      "loss": 0.7043,
      "step": 242
    },
    {
      "epoch": 5.06,
      "learning_rate": 1.2565338385541792e-05,
      "loss": 0.7169,
      "step": 243
    },
    {
      "epoch": 5.08,
      "learning_rate": 1.2024433707364002e-05,
      "loss": 0.7287,
      "step": 244
    },
    {
      "epoch": 5.1,
      "learning_rate": 1.1494683496138458e-05,
      "loss": 0.6954,
      "step": 245
    },
    {
      "epoch": 5.12,
      "learning_rate": 1.097615491916485e-05,
      "loss": 0.6995,
      "step": 246
    },
    {
      "epoch": 5.15,
      "learning_rate": 1.0468913720946084e-05,
      "loss": 0.7289,
      "step": 247
    },
    {
      "epoch": 5.17,
      "learning_rate": 9.973024214852567e-06,
      "loss": 0.7059,
      "step": 248
    },
    {
      "epoch": 5.19,
      "learning_rate": 9.488549274967872e-06,
      "loss": 0.6897,
      "step": 249
    },
    {
      "epoch": 5.21,
      "learning_rate": 9.015550328116939e-06,
      "loss": 0.695,
      "step": 250
    },
    {
      "epoch": 5.23,
      "learning_rate": 8.554087346077633e-06,
      "loss": 0.7015,
      "step": 251
    },
    {
      "epoch": 5.25,
      "learning_rate": 8.10421883797694e-06,
      "loss": 0.7266,
      "step": 252
    },
    {
      "epoch": 5.27,
      "learning_rate": 7.666001842872638e-06,
      "loss": 0.7254,
      "step": 253
    },
    {
      "epoch": 5.29,
      "learning_rate": 7.239491922521246e-06,
      "loss": 0.7123,
      "step": 254
    },
    {
      "epoch": 5.31,
      "learning_rate": 6.824743154333157e-06,
      "loss": 0.6989,
      "step": 255
    },
    {
      "epoch": 5.33,
      "learning_rate": 6.421808124516437e-06,
      "loss": 0.7203,
      "step": 256
    },
    {
      "epoch": 5.35,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.6886,
      "step": 257
    },
    {
      "epoch": 5.38,
      "learning_rate": 5.651582129001986e-06,
      "loss": 0.7221,
      "step": 258
    },
    {
      "epoch": 5.4,
      "learning_rate": 5.284388820651331e-06,
      "loss": 0.6851,
      "step": 259
    },
    {
      "epoch": 5.42,
      "learning_rate": 4.929204552984168e-06,
      "loss": 0.7138,
      "step": 260
    },
    {
      "epoch": 5.44,
      "learning_rate": 4.586074359995119e-06,
      "loss": 0.712,
      "step": 261
    },
    {
      "epoch": 5.46,
      "learning_rate": 4.255041747336452e-06,
      "loss": 0.713,
      "step": 262
    },
    {
      "epoch": 5.48,
      "learning_rate": 3.936148686802077e-06,
      "loss": 0.7207,
      "step": 263
    },
    {
      "epoch": 5.5,
      "learning_rate": 3.6294356110059157e-06,
      "loss": 0.6864,
      "step": 264
    },
    {
      "epoch": 5.52,
      "learning_rate": 3.3349414082553875e-06,
      "loss": 0.6759,
      "step": 265
    },
    {
      "epoch": 5.54,
      "learning_rate": 3.0527034176207727e-06,
      "loss": 0.7169,
      "step": 266
    },
    {
      "epoch": 5.56,
      "learning_rate": 2.7827574242009437e-06,
      "loss": 0.6766,
      "step": 267
    },
    {
      "epoch": 5.58,
      "learning_rate": 2.525137654586185e-06,
      "loss": 0.6986,
      "step": 268
    },
    {
      "epoch": 5.6,
      "learning_rate": 2.2798767725185853e-06,
      "loss": 0.707,
      "step": 269
    },
    {
      "epoch": 5.62,
      "learning_rate": 2.0470058747505516e-06,
      "loss": 0.7098,
      "step": 270
    },
    {
      "epoch": 5.65,
      "learning_rate": 1.8265544871020723e-06,
      "loss": 0.7201,
      "step": 271
    },
    {
      "epoch": 5.67,
      "learning_rate": 1.6185505607171026e-06,
      "loss": 0.7201,
      "step": 272
    },
    {
      "epoch": 5.69,
      "learning_rate": 1.4230204685196203e-06,
      "loss": 0.6995,
      "step": 273
    },
    {
      "epoch": 5.71,
      "learning_rate": 1.2399890018698347e-06,
      "loss": 0.6899,
      "step": 274
    },
    {
      "epoch": 5.73,
      "learning_rate": 1.0694793674208114e-06,
      "loss": 0.6689,
      "step": 275
    },
    {
      "epoch": 5.75,
      "learning_rate": 9.11513184176116e-07,
      "loss": 0.7259,
      "step": 276
    },
    {
      "epoch": 5.77,
      "learning_rate": 7.661104807487607e-07,
      "loss": 0.7346,
      "step": 277
    },
    {
      "epoch": 5.79,
      "learning_rate": 6.332896928217257e-07,
      "loss": 0.701,
      "step": 278
    },
    {
      "epoch": 5.81,
      "learning_rate": 5.130676608104845e-07,
      "loss": 0.6666,
      "step": 279
    },
    {
      "epoch": 5.83,
      "learning_rate": 4.054596277278666e-07,
      "loss": 0.6859,
      "step": 280
    },
    {
      "epoch": 5.85,
      "learning_rate": 3.104792372512821e-07,
      "loss": 0.6497,
      "step": 281
    },
    {
      "epoch": 5.88,
      "learning_rate": 2.2813853199292746e-07,
      "loss": 0.7257,
      "step": 282
    },
    {
      "epoch": 5.9,
      "learning_rate": 1.58447951972851e-07,
      "loss": 0.6726,
      "step": 283
    },
    {
      "epoch": 5.92,
      "learning_rate": 1.0141633329525668e-07,
      "loss": 0.7093,
      "step": 284
    },
    {
      "epoch": 5.94,
      "learning_rate": 5.705090702819993e-08,
      "loss": 0.708,
      "step": 285
    },
    {
      "epoch": 5.96,
      "learning_rate": 2.5357298286698973e-08,
      "loss": 0.7173,
      "step": 286
    },
    {
      "epoch": 5.98,
      "learning_rate": 6.3395255195941585e-09,
      "loss": 0.6994,
      "step": 287
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.0,
      "loss": 0.6607,
      "step": 288
    },
    {
      "epoch": 6.0,
      "step": 288,
      "total_flos": 86917169807360.0,
      "train_loss": 1.0930437861631315,
      "train_runtime": 2990.5988,
      "train_samples_per_second": 18.903,
      "train_steps_per_second": 0.096
    }
  ],
  "logging_steps": 1,
  "max_steps": 288,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 50000,
  "total_flos": 86917169807360.0,
  "train_batch_size": 50,
  "trial_name": null,
  "trial_params": null
}