{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 174,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.0336,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.1471,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 2.5604,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.0848,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.8695,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.6627,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019998251609127464,
      "loss": 1.6042,
      "step": 7
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019993007047883988,
      "loss": 1.6334,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019984268150178167,
      "loss": 1.5498,
      "step": 9
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019972037971811802,
      "loss": 1.4238,
      "step": 10
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019956320789411337,
      "loss": 1.5104,
      "step": 11
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019937122098932428,
      "loss": 1.399,
      "step": 12
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019914448613738106,
      "loss": 1.4097,
      "step": 13
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019888308262251285,
      "loss": 1.2895,
      "step": 14
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001985871018518236,
      "loss": 1.2686,
      "step": 15
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019825664732332884,
      "loss": 1.3434,
      "step": 16
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019789183458976484,
      "loss": 1.3547,
      "step": 17
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019749279121818235,
      "loss": 1.2858,
      "step": 18
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001970596567453391,
      "loss": 1.2182,
      "step": 19
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019659258262890683,
      "loss": 1.2566,
      "step": 20
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019609173219450998,
      "loss": 1.1689,
      "step": 21
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001955572805786141,
      "loss": 1.2791,
      "step": 22
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001949894146672846,
      "loss": 1.2545,
      "step": 23
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019438833303083678,
      "loss": 1.2585,
      "step": 24
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019375424585439994,
      "loss": 1.155,
      "step": 25
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019308737486442045,
      "loss": 1.2322,
      "step": 26
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001923879532511287,
      "loss": 1.0583,
      "step": 27
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019165622558699763,
      "loss": 1.0604,
      "step": 28
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001908924477412211,
      "loss": 1.1765,
      "step": 29
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001900968867902419,
      "loss": 1.0841,
      "step": 30
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018926982092436117,
      "loss": 1.2448,
      "step": 31
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018841153935046098,
      "loss": 1.2845,
      "step": 32
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018752234219087538,
      "loss": 1.0631,
      "step": 33
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.1415,
      "step": 34
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018565245554778517,
      "loss": 1.0635,
      "step": 35
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018467241992282843,
      "loss": 1.118,
      "step": 36
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018366277620064197,
      "loss": 1.125,
      "step": 37
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001826238774315995,
      "loss": 1.0472,
      "step": 38
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018155608689592604,
      "loss": 1.0681,
      "step": 39
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018045977797666684,
      "loss": 1.0575,
      "step": 40
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017933533402912354,
      "loss": 1.1236,
      "step": 41
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000178183148246803,
      "loss": 0.9568,
      "step": 42
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001770036235239263,
      "loss": 0.9808,
      "step": 43
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001757971723145453,
      "loss": 1.0124,
      "step": 44
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017456421648831655,
      "loss": 1.0146,
      "step": 45
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017330518718298264,
      "loss": 0.8494,
      "step": 46
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017202052465361268,
      "loss": 0.9945,
      "step": 47
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.9945,
      "step": 48
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016937610560285418,
      "loss": 0.9627,
      "step": 49
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016801727377709194,
      "loss": 1.0944,
      "step": 50
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001666346577952004,
      "loss": 0.9068,
      "step": 51
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016522874112781213,
      "loss": 0.9744,
      "step": 52
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001638000153933009,
      "loss": 0.9814,
      "step": 53
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.897,
      "step": 54
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.916,
      "step": 55
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015938201855735014,
      "loss": 0.9574,
      "step": 56
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001578671296179806,
      "loss": 0.9101,
      "step": 57
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001563320058063622,
      "loss": 0.9506,
      "step": 58
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015477718392178716,
      "loss": 0.8437,
      "step": 59
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015320320765153367,
      "loss": 0.9731,
      "step": 60
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015161062738075067,
      "loss": 0.8724,
      "step": 61
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0002,
      "step": 62
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000148371888710524,
      "loss": 0.9179,
      "step": 63
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001467268628273062,
      "loss": 0.9031,
      "step": 64
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014506549757999454,
      "loss": 0.9408,
      "step": 65
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014338837391175582,
      "loss": 0.8223,
      "step": 66
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014169607827613283,
      "loss": 0.8489,
      "step": 67
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013998920243197407,
      "loss": 0.857,
      "step": 68
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000138268343236509,
      "loss": 0.883,
      "step": 69
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013653410243663952,
      "loss": 0.8169,
      "step": 70
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013478708645852272,
      "loss": 0.7553,
      "step": 71
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013302790619551674,
      "loss": 0.8621,
      "step": 72
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013125717679456447,
      "loss": 0.779,
      "step": 73
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012947551744109043,
      "loss": 0.8823,
      "step": 74
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012768355114248494,
      "loss": 0.8303,
      "step": 75
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.8004,
      "step": 76
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012407120754089732,
      "loss": 0.7605,
      "step": 77
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.7432,
      "step": 78
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012042519817896804,
      "loss": 0.8013,
      "step": 79
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011859116071629149,
      "loss": 0.8088,
      "step": 80
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011675062233047364,
      "loss": 0.834,
      "step": 81
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011490422661761744,
      "loss": 0.7438,
      "step": 82
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.8594,
      "step": 83
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011119644761033078,
      "loss": 0.7394,
      "step": 84
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010933636084529506,
      "loss": 0.7285,
      "step": 85
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010747300935864243,
      "loss": 0.8386,
      "step": 86
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010560704472371919,
      "loss": 0.6397,
      "step": 87
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001037391194276326,
      "loss": 0.6312,
      "step": 88
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010186988664309023,
      "loss": 0.7131,
      "step": 89
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 0.7044,
      "step": 90
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.813011335690981e-05,
      "loss": 0.6069,
      "step": 91
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.626088057236745e-05,
      "loss": 0.7156,
      "step": 92
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.439295527628081e-05,
      "loss": 0.6827,
      "step": 93
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.252699064135758e-05,
      "loss": 0.7909,
      "step": 94
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.066363915470495e-05,
      "loss": 0.6702,
      "step": 95
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.880355238966923e-05,
      "loss": 0.78,
      "step": 96
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.6501,
      "step": 97
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.509577338238255e-05,
      "loss": 0.7133,
      "step": 98
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.324937766952638e-05,
      "loss": 0.6917,
      "step": 99
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.140883928370855e-05,
      "loss": 0.6802,
      "step": 100
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.957480182103198e-05,
      "loss": 0.6907,
      "step": 101
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.5801,
      "step": 102
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.592879245910273e-05,
      "loss": 0.6508,
      "step": 103
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.7096,
      "step": 104
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.231644885751507e-05,
      "loss": 0.6661,
      "step": 105
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.052448255890957e-05,
      "loss": 0.6926,
      "step": 106
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.874282320543557e-05,
      "loss": 0.6867,
      "step": 107
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.697209380448333e-05,
      "loss": 0.6498,
      "step": 108
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.521291354147727e-05,
      "loss": 0.6701,
      "step": 109
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.34658975633605e-05,
      "loss": 0.6017,
      "step": 110
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.6007,
      "step": 111
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.001079756802592e-05,
      "loss": 0.6231,
      "step": 112
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.830392172386723e-05,
      "loss": 0.6004,
      "step": 113
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.6116,
      "step": 114
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.493450242000546e-05,
      "loss": 0.6014,
      "step": 115
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.32731371726938e-05,
      "loss": 0.6195,
      "step": 116
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.162811128947602e-05,
      "loss": 0.5959,
      "step": 117
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.5329,
      "step": 118
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.8389372619249326e-05,
      "loss": 0.5667,
      "step": 119
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.6796792348466356e-05,
      "loss": 0.5541,
      "step": 120
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.522281607821288e-05,
      "loss": 0.572,
      "step": 121
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.3667994193637796e-05,
      "loss": 0.5608,
      "step": 122
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.213287038201943e-05,
      "loss": 0.6407,
      "step": 123
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0617981442649855e-05,
      "loss": 0.6392,
      "step": 124
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.5541,
      "step": 125
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 0.6149,
      "step": 126
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.6199984606699155e-05,
      "loss": 0.5239,
      "step": 127
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.477125887218792e-05,
      "loss": 0.6098,
      "step": 128
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.336534220479961e-05,
      "loss": 0.5971,
      "step": 129
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.198272622290804e-05,
      "loss": 0.5751,
      "step": 130
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.062389439714584e-05,
      "loss": 0.5351,
      "step": 131
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.5096,
      "step": 132
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.797947534638736e-05,
      "loss": 0.5955,
      "step": 133
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.669481281701739e-05,
      "loss": 0.5452,
      "step": 134
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5435783511683443e-05,
      "loss": 0.5363,
      "step": 135
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.420282768545469e-05,
      "loss": 0.4915,
      "step": 136
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2996376476073723e-05,
      "loss": 0.5574,
      "step": 137
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.181685175319702e-05,
      "loss": 0.5438,
      "step": 138
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.5464,
      "step": 139
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9540222023333166e-05,
      "loss": 0.5587,
      "step": 140
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8443913104073983e-05,
      "loss": 0.5535,
      "step": 141
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7376122568400532e-05,
      "loss": 0.5958,
      "step": 142
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6337223799358026e-05,
      "loss": 0.5997,
      "step": 143
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5327580077171587e-05,
      "loss": 0.5441,
      "step": 144
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4347544452214868e-05,
      "loss": 0.4945,
      "step": 145
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.5564,
      "step": 146
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2477657809124631e-05,
      "loss": 0.4948,
      "step": 147
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1588460649539035e-05,
      "loss": 0.5315,
      "step": 148
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0730179075638868e-05,
      "loss": 0.5196,
      "step": 149
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.903113209758096e-06,
      "loss": 0.5382,
      "step": 150
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.107552258778907e-06,
      "loss": 0.55,
      "step": 151
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.343774413002381e-06,
      "loss": 0.524,
      "step": 152
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.5602,
      "step": 153
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.9126251355795864e-06,
      "loss": 0.5391,
      "step": 154
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.245754145600091e-06,
      "loss": 0.5259,
      "step": 155
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.611666969163243e-06,
      "loss": 0.5483,
      "step": 156
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.0105853327154e-06,
      "loss": 0.5533,
      "step": 157
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.442719421385922e-06,
      "loss": 0.5403,
      "step": 158
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.908267805490051e-06,
      "loss": 0.5192,
      "step": 159
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.5134,
      "step": 160
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.9403432546609043e-06,
      "loss": 0.4957,
      "step": 161
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.5072087818176382e-06,
      "loss": 0.429,
      "step": 162
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1081654102351635e-06,
      "loss": 0.5649,
      "step": 163
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7433526766711728e-06,
      "loss": 0.5655,
      "step": 164
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4128981481764115e-06,
      "loss": 0.568,
      "step": 165
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1169173774871478e-06,
      "loss": 0.5024,
      "step": 166
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.555138626189618e-07,
      "loss": 0.5127,
      "step": 167
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.287790106757396e-07,
      "loss": 0.5509,
      "step": 168
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.3679210588661866e-07,
      "loss": 0.5531,
      "step": 169
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.7962028188198706e-07,
      "loss": 0.5437,
      "step": 170
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.5731849821833954e-07,
      "loss": 0.4631,
      "step": 171
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.992952116013918e-08,
      "loss": 0.5563,
      "step": 172
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.7483908725357545e-08,
      "loss": 0.5058,
      "step": 173
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.5082,
      "step": 174
    },
    {
      "epoch": 1.0,
      "step": 174,
      "total_flos": 4413720231936.0,
      "train_loss": 0.8584621692525929,
      "train_runtime": 3538.7692,
      "train_samples_per_second": 3.132,
      "train_steps_per_second": 0.049
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 174,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 4413720231936.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}