{
  "best_metric": 2.0390162467956543,
  "best_model_checkpoint": "output/checkpoint-200",
  "epoch": 0.13673679768829353,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.9999999999999997e-06,
      "loss": 2.0077,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.999999999999999e-06,
      "loss": 2.1786,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.999999999999999e-06,
      "loss": 2.1404,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.1999999999999999e-05,
      "loss": 2.1009,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 2.1208,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.7999999999999997e-05,
      "loss": 2.1575,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.1e-05,
      "loss": 2.1128,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.3999999999999997e-05,
      "loss": 2.2115,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6999999999999996e-05,
      "loss": 2.151,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.1026,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.2999999999999996e-05,
      "loss": 2.0163,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.5999999999999994e-05,
      "loss": 2.0976,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.9e-05,
      "loss": 2.0799,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.2e-05,
      "loss": 2.0675,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 1.9994,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.7999999999999994e-05,
      "loss": 2.0982,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.1e-05,
      "loss": 2.1543,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.399999999999999e-05,
      "loss": 2.0545,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 1.9721,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.0459,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.299999999999999e-05,
      "loss": 1.9305,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.599999999999999e-05,
      "loss": 2.0157,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.9e-05,
      "loss": 2.0086,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.199999999999999e-05,
      "loss": 2.0465,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.5e-05,
      "loss": 1.9646,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.8e-05,
      "loss": 1.9861,
      "step": 26
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.1e-05,
      "loss": 2.0234,
      "step": 27
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.4e-05,
      "loss": 2.0791,
      "step": 28
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.699999999999999e-05,
      "loss": 2.0444,
      "step": 29
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.0175,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.3e-05,
      "loss": 2.0487,
      "step": 31
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.599999999999999e-05,
      "loss": 1.9894,
      "step": 32
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.9e-05,
      "loss": 2.0274,
      "step": 33
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000102,
      "loss": 2.0745,
      "step": 34
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010499999999999999,
      "loss": 2.0062,
      "step": 35
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010799999999999998,
      "loss": 2.0295,
      "step": 36
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011099999999999999,
      "loss": 2.0375,
      "step": 37
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011399999999999999,
      "loss": 2.0231,
      "step": 38
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000117,
      "loss": 2.0579,
      "step": 39
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.0871,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00012299999999999998,
      "loss": 1.9509,
      "step": 41
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00012599999999999997,
      "loss": 1.8855,
      "step": 42
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000129,
      "loss": 2.0348,
      "step": 43
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013199999999999998,
      "loss": 2.0375,
      "step": 44
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000135,
      "loss": 2.0577,
      "step": 45
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000138,
      "loss": 2.0738,
      "step": 46
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014099999999999998,
      "loss": 2.0123,
      "step": 47
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014399999999999998,
      "loss": 2.0051,
      "step": 48
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000147,
      "loss": 2.0202,
      "step": 49
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015,
      "loss": 2.0341,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015299999999999998,
      "loss": 2.0641,
      "step": 51
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000156,
      "loss": 2.0062,
      "step": 52
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000159,
      "loss": 2.0098,
      "step": 53
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000162,
      "loss": 2.0048,
      "step": 54
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000165,
      "loss": 2.024,
      "step": 55
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000168,
      "loss": 2.1095,
      "step": 56
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017099999999999998,
      "loss": 2.0006,
      "step": 57
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017399999999999997,
      "loss": 1.9974,
      "step": 58
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017699999999999997,
      "loss": 1.9859,
      "step": 59
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.9709,
      "step": 60
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00018299999999999998,
      "loss": 2.0321,
      "step": 61
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000186,
      "loss": 2.0237,
      "step": 62
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00018899999999999999,
      "loss": 2.0283,
      "step": 63
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019199999999999998,
      "loss": 2.0366,
      "step": 64
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000195,
      "loss": 1.896,
      "step": 65
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000198,
      "loss": 1.9694,
      "step": 66
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000201,
      "loss": 2.0214,
      "step": 67
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000204,
      "loss": 1.9792,
      "step": 68
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00020699999999999996,
      "loss": 1.9212,
      "step": 69
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.8687,
      "step": 70
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00021299999999999997,
      "loss": 1.9514,
      "step": 71
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00021599999999999996,
      "loss": 1.9373,
      "step": 72
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00021899999999999998,
      "loss": 2.0325,
      "step": 73
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00022199999999999998,
      "loss": 1.9904,
      "step": 74
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000225,
      "loss": 1.9753,
      "step": 75
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00022799999999999999,
      "loss": 1.9835,
      "step": 76
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00023099999999999998,
      "loss": 1.866,
      "step": 77
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000234,
      "loss": 1.9926,
      "step": 78
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000237,
      "loss": 1.9915,
      "step": 79
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.9351,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000243,
      "loss": 2.008,
      "step": 81
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00024599999999999996,
      "loss": 1.9728,
      "step": 82
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000249,
      "loss": 2.0915,
      "step": 83
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00025199999999999995,
      "loss": 2.008,
      "step": 84
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00025499999999999996,
      "loss": 1.9635,
      "step": 85
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000258,
      "loss": 1.9995,
      "step": 86
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000261,
      "loss": 1.8813,
      "step": 87
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00026399999999999997,
      "loss": 1.9433,
      "step": 88
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000267,
      "loss": 1.9815,
      "step": 89
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00027,
      "loss": 1.9644,
      "step": 90
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00027299999999999997,
      "loss": 1.9775,
      "step": 91
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000276,
      "loss": 1.9424,
      "step": 92
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000279,
      "loss": 1.8931,
      "step": 93
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00028199999999999997,
      "loss": 1.982,
      "step": 94
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000285,
      "loss": 1.9369,
      "step": 95
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00028799999999999995,
      "loss": 1.9895,
      "step": 96
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00029099999999999997,
      "loss": 1.9581,
      "step": 97
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000294,
      "loss": 1.9321,
      "step": 98
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00029699999999999996,
      "loss": 1.972,
      "step": 99
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 2.0379,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000303,
      "loss": 1.9495,
      "step": 101
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00030599999999999996,
      "loss": 2.0403,
      "step": 102
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000309,
      "loss": 1.9609,
      "step": 103
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000312,
      "loss": 1.8649,
      "step": 104
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00031499999999999996,
      "loss": 1.9075,
      "step": 105
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000318,
      "loss": 1.9003,
      "step": 106
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000321,
      "loss": 1.9617,
      "step": 107
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000324,
      "loss": 2.0252,
      "step": 108
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000327,
      "loss": 1.9904,
      "step": 109
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00033,
      "loss": 1.9021,
      "step": 110
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000333,
      "loss": 1.9953,
      "step": 111
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000336,
      "loss": 1.9547,
      "step": 112
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00033899999999999995,
      "loss": 1.9819,
      "step": 113
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00034199999999999996,
      "loss": 1.9297,
      "step": 114
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00034499999999999993,
      "loss": 2.0428,
      "step": 115
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00034799999999999995,
      "loss": 1.9725,
      "step": 116
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035099999999999997,
      "loss": 2.011,
      "step": 117
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035399999999999993,
      "loss": 1.9258,
      "step": 118
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035699999999999995,
      "loss": 1.9744,
      "step": 119
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035999999999999997,
      "loss": 1.9285,
      "step": 120
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00036299999999999993,
      "loss": 1.9671,
      "step": 121
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00036599999999999995,
      "loss": 1.961,
      "step": 122
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00036899999999999997,
      "loss": 1.9486,
      "step": 123
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000372,
      "loss": 1.9547,
      "step": 124
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00037499999999999995,
      "loss": 1.9198,
      "step": 125
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00037799999999999997,
      "loss": 2.0241,
      "step": 126
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000381,
      "loss": 1.9285,
      "step": 127
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00038399999999999996,
      "loss": 2.0473,
      "step": 128
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000387,
      "loss": 1.972,
      "step": 129
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00039,
      "loss": 2.0174,
      "step": 130
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00039299999999999996,
      "loss": 2.042,
      "step": 131
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000396,
      "loss": 1.9143,
      "step": 132
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000399,
      "loss": 1.9869,
      "step": 133
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000402,
      "loss": 1.902,
      "step": 134
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000405,
      "loss": 2.0594,
      "step": 135
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000408,
      "loss": 1.996,
      "step": 136
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000411,
      "loss": 1.9112,
      "step": 137
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004139999999999999,
      "loss": 1.8769,
      "step": 138
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00041699999999999994,
      "loss": 1.9617,
      "step": 139
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00041999999999999996,
      "loss": 2.0377,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00042299999999999993,
      "loss": 1.9877,
      "step": 141
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00042599999999999995,
      "loss": 1.9169,
      "step": 142
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00042899999999999997,
      "loss": 2.0591,
      "step": 143
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00043199999999999993,
      "loss": 1.8444,
      "step": 144
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00043499999999999995,
      "loss": 1.9824,
      "step": 145
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00043799999999999997,
      "loss": 1.9722,
      "step": 146
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00044099999999999993,
      "loss": 1.9294,
      "step": 147
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00044399999999999995,
      "loss": 1.9214,
      "step": 148
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00044699999999999997,
      "loss": 1.9745,
      "step": 149
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00045,
      "loss": 2.0246,
      "step": 150
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00045299999999999995,
      "loss": 2.0081,
      "step": 151
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00045599999999999997,
      "loss": 1.9461,
      "step": 152
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000459,
      "loss": 2.0223,
      "step": 153
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00046199999999999995,
      "loss": 1.9378,
      "step": 154
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00046499999999999997,
      "loss": 2.078,
      "step": 155
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000468,
      "loss": 1.8492,
      "step": 156
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00047099999999999996,
      "loss": 1.9702,
      "step": 157
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000474,
      "loss": 2.0145,
      "step": 158
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000477,
      "loss": 1.9919,
      "step": 159
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00047999999999999996,
      "loss": 1.859,
      "step": 160
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000483,
      "loss": 2.0404,
      "step": 161
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000486,
      "loss": 1.9834,
      "step": 162
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000489,
      "loss": 1.9675,
      "step": 163
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004919999999999999,
      "loss": 1.9736,
      "step": 164
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004949999999999999,
      "loss": 1.9782,
      "step": 165
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000498,
      "loss": 1.9871,
      "step": 166
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0005009999999999999,
      "loss": 1.8851,
      "step": 167
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0005039999999999999,
      "loss": 1.843,
      "step": 168
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000507,
      "loss": 2.0048,
      "step": 169
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005099999999999999,
      "loss": 1.9889,
      "step": 170
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005129999999999999,
      "loss": 1.8957,
      "step": 171
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000516,
      "loss": 1.973,
      "step": 172
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005189999999999999,
      "loss": 1.9994,
      "step": 173
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000522,
      "loss": 1.8714,
      "step": 174
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000525,
      "loss": 1.9058,
      "step": 175
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005279999999999999,
      "loss": 1.883,
      "step": 176
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000531,
      "loss": 1.9557,
      "step": 177
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000534,
      "loss": 1.9734,
      "step": 178
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005369999999999999,
      "loss": 1.9472,
      "step": 179
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00054,
      "loss": 1.8726,
      "step": 180
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000543,
      "loss": 1.9167,
      "step": 181
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005459999999999999,
      "loss": 1.9731,
      "step": 182
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000549,
      "loss": 1.9897,
      "step": 183
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000552,
      "loss": 2.0158,
      "step": 184
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005549999999999999,
      "loss": 1.8802,
      "step": 185
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000558,
      "loss": 1.9343,
      "step": 186
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000561,
      "loss": 1.928,
      "step": 187
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005639999999999999,
      "loss": 2.0039,
      "step": 188
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005669999999999999,
      "loss": 1.8459,
      "step": 189
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00057,
      "loss": 1.9679,
      "step": 190
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005729999999999999,
      "loss": 1.9395,
      "step": 191
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005759999999999999,
      "loss": 1.9677,
      "step": 192
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000579,
      "loss": 1.9577,
      "step": 193
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005819999999999999,
      "loss": 2.0165,
      "step": 194
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005849999999999999,
      "loss": 1.9697,
      "step": 195
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000588,
      "loss": 2.0005,
      "step": 196
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005909999999999999,
      "loss": 1.9252,
      "step": 197
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005939999999999999,
      "loss": 1.9321,
      "step": 198
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000597,
      "loss": 1.8474,
      "step": 199
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0006,
      "loss": 1.9134,
      "step": 200
    },
    {
      "epoch": 0.14,
      "eval_loss": 2.0390162467956543,
      "eval_runtime": 114.9464,
      "eval_samples_per_second": 8.7,
      "eval_steps_per_second": 8.7,
      "step": 200
    }
  ],
  "max_steps": 5848,
  "num_train_epochs": 4,
  "total_flos": 2.4532993377759744e+17,
  "trial_name": null,
  "trial_params": null
}