{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.9207,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 2.118,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.6691,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.0591,
      "step": 4
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019996891820008164,
      "loss": 1.1013,
      "step": 5
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019987569212189224,
      "loss": 0.7172,
      "step": 6
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019972037971811802,
      "loss": 0.818,
      "step": 7
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019950307753654017,
      "loss": 0.7755,
      "step": 8
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019922392066001722,
      "loss": 0.7291,
      "step": 9
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019888308262251285,
      "loss": 0.7732,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019848077530122083,
      "loss": 0.7987,
      "step": 11
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019801724878485438,
      "loss": 0.7909,
      "step": 12
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.8374,
      "step": 13
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001969077286229078,
      "loss": 0.6982,
      "step": 14
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001962624246950012,
      "loss": 0.6,
      "step": 15
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001955572805786141,
      "loss": 0.5954,
      "step": 16
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001947927346167132,
      "loss": 0.6166,
      "step": 17
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.5259,
      "step": 18
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019308737486442045,
      "loss": 0.7272,
      "step": 19
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019214762118704076,
      "loss": 0.6852,
      "step": 20
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019115058523116733,
      "loss": 0.6652,
      "step": 21
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.6103,
      "step": 22
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001889871808811469,
      "loss": 0.6218,
      "step": 23
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018782215733702286,
      "loss": 0.6948,
      "step": 24
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.511,
      "step": 25
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018532908816321558,
      "loss": 0.6502,
      "step": 26
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018400259231507717,
      "loss": 0.7126,
      "step": 27
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001826238774315995,
      "loss": 0.8326,
      "step": 28
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018119380057158568,
      "loss": 0.5867,
      "step": 29
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017971325072229226,
      "loss": 0.7719,
      "step": 30
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000178183148246803,
      "loss": 0.621,
      "step": 31
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.5924,
      "step": 32
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017497812029677344,
      "loss": 0.4965,
      "step": 33
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017330518718298264,
      "loss": 0.5869,
      "step": 34
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017158668492597186,
      "loss": 0.7057,
      "step": 35
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016982368180860728,
      "loss": 0.5441,
      "step": 36
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016801727377709194,
      "loss": 0.5765,
      "step": 37
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016616858375968595,
      "loss": 0.673,
      "step": 38
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.6578,
      "step": 39
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.59,
      "step": 40
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016038044103254775,
      "loss": 0.4679,
      "step": 41
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000158374367223479,
      "loss": 0.4859,
      "step": 42
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001563320058063622,
      "loss": 0.5695,
      "step": 43
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015425462638657595,
      "loss": 0.5171,
      "step": 44
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001521435203379498,
      "loss": 0.4349,
      "step": 45
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.593,
      "step": 46
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014782539786213183,
      "loss": 0.6236,
      "step": 47
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001456210657353163,
      "loss": 0.6262,
      "step": 48
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014338837391175582,
      "loss": 0.5783,
      "step": 49
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014112871031306119,
      "loss": 0.5118,
      "step": 50
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013884347962746948,
      "loss": 0.5476,
      "step": 51
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013653410243663952,
      "loss": 0.5761,
      "step": 52
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013420201433256689,
      "loss": 0.5885,
      "step": 53
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013184866502516845,
      "loss": 0.6564,
      "step": 54
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012947551744109043,
      "loss": 0.739,
      "step": 55
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012708404681430053,
      "loss": 0.76,
      "step": 56
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012467573976902935,
      "loss": 0.5222,
      "step": 57
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.5721,
      "step": 58
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011981461431993977,
      "loss": 0.6089,
      "step": 59
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.6067,
      "step": 60
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011490422661761744,
      "loss": 0.5093,
      "step": 61
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011243437046474853,
      "loss": 0.6065,
      "step": 62
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010995678465958168,
      "loss": 0.4474,
      "step": 63
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010747300935864243,
      "loss": 0.55,
      "step": 64
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010498458856606972,
      "loss": 0.4878,
      "step": 65
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001024930691738073,
      "loss": 0.4153,
      "step": 66
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 0.5653,
      "step": 67
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.750693082619273e-05,
      "loss": 0.4938,
      "step": 68
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.501541143393028e-05,
      "loss": 0.4816,
      "step": 69
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.252699064135758e-05,
      "loss": 0.4389,
      "step": 70
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.004321534041835e-05,
      "loss": 0.5041,
      "step": 71
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.756562953525152e-05,
      "loss": 0.4546,
      "step": 72
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.509577338238255e-05,
      "loss": 0.5348,
      "step": 73
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.6939,
      "step": 74
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.018538568006027e-05,
      "loss": 0.6287,
      "step": 75
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.7004,
      "step": 76
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.532426023097063e-05,
      "loss": 0.5614,
      "step": 77
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.291595318569951e-05,
      "loss": 0.5321,
      "step": 78
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.052448255890957e-05,
      "loss": 0.428,
      "step": 79
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.815133497483157e-05,
      "loss": 0.5208,
      "step": 80
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.579798566743314e-05,
      "loss": 0.3875,
      "step": 81
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.34658975633605e-05,
      "loss": 0.4374,
      "step": 82
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.115652037253053e-05,
      "loss": 0.5944,
      "step": 83
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.887128968693887e-05,
      "loss": 0.5426,
      "step": 84
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.5236,
      "step": 85
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.43789342646837e-05,
      "loss": 0.5215,
      "step": 86
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.217460213786821e-05,
      "loss": 0.6276,
      "step": 87
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.6398,
      "step": 88
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.78564796620502e-05,
      "loss": 0.5767,
      "step": 89
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.574537361342407e-05,
      "loss": 0.5475,
      "step": 90
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.3667994193637796e-05,
      "loss": 0.6272,
      "step": 91
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.1625632776521037e-05,
      "loss": 0.6999,
      "step": 92
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.961955896745224e-05,
      "loss": 0.5685,
      "step": 93
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 0.4134,
      "step": 94
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.5588,
      "step": 95
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.383141624031408e-05,
      "loss": 0.5292,
      "step": 96
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.198272622290804e-05,
      "loss": 0.5415,
      "step": 97
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0176318191392726e-05,
      "loss": 0.5875,
      "step": 98
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8413315074028158e-05,
      "loss": 0.5756,
      "step": 99
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.669481281701739e-05,
      "loss": 0.5324,
      "step": 100
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.502187970322657e-05,
      "loss": 0.5035,
      "step": 101
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.5883,
      "step": 102
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.181685175319702e-05,
      "loss": 0.3632,
      "step": 103
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0286749277707782e-05,
      "loss": 0.4206,
      "step": 104
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.880619942841435e-05,
      "loss": 0.4867,
      "step": 105
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7376122568400532e-05,
      "loss": 0.5097,
      "step": 106
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5997407684922862e-05,
      "loss": 0.4196,
      "step": 107
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.467091183678444e-05,
      "loss": 0.4502,
      "step": 108
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.4994,
      "step": 109
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2177842662977135e-05,
      "loss": 0.5945,
      "step": 110
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1012819118853147e-05,
      "loss": 0.6632,
      "step": 111
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.903113209758096e-06,
      "loss": 0.5267,
      "step": 112
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.849414768832687e-06,
      "loss": 0.4464,
      "step": 113
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.852378812959227e-06,
      "loss": 0.5007,
      "step": 114
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.9126251355795864e-06,
      "loss": 0.4689,
      "step": 115
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.6377,
      "step": 116
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.20726538328683e-06,
      "loss": 0.4218,
      "step": 117
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.442719421385922e-06,
      "loss": 0.4671,
      "step": 118
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.7375753049987973e-06,
      "loss": 0.7304,
      "step": 119
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.092271377092215e-06,
      "loss": 0.4949,
      "step": 120
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.5072087818176382e-06,
      "loss": 0.4776,
      "step": 121
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9827512151456173e-06,
      "loss": 0.4822,
      "step": 122
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 0.4209,
      "step": 123
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1169173774871478e-06,
      "loss": 0.5444,
      "step": 124
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.760793399827937e-07,
      "loss": 0.4981,
      "step": 125
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.969224634598591e-07,
      "loss": 0.5573,
      "step": 126
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.7962028188198706e-07,
      "loss": 0.5132,
      "step": 127
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.2430787810776555e-07,
      "loss": 0.6259,
      "step": 128
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.1081799918375454e-08,
      "loss": 0.6139,
      "step": 129
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.6752,
      "step": 130
    },
    {
      "epoch": 1.0,
      "step": 130,
      "total_flos": 1539524413440.0,
      "train_loss": 0.615638983478913,
      "train_runtime": 265.7004,
      "train_samples_per_second": 7.787,
      "train_steps_per_second": 0.489
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 1539524413440.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}