{
  "best_metric": 2.0144975185394287,
  "best_model_checkpoint": "output/checkpoint-400",
  "epoch": 0.27347359537658705,
  "global_step": 400,
  "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
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005998937677053823,
      "loss": 1.9258,
      "step": 201
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005997875354107648,
      "loss": 1.9414,
      "step": 202
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005996813031161472,
      "loss": 1.9516,
      "step": 203
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005995750708215297,
      "loss": 2.0185,
      "step": 204
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005994688385269121,
      "loss": 2.0142,
      "step": 205
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005993626062322946,
      "loss": 1.9021,
      "step": 206
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000599256373937677,
      "loss": 1.9439,
      "step": 207
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005991501416430595,
      "loss": 1.9489,
      "step": 208
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005990439093484419,
      "loss": 1.8585,
      "step": 209
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005989376770538244,
      "loss": 1.982,
      "step": 210
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005988314447592068,
      "loss": 1.9516,
      "step": 211
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005987252124645891,
      "loss": 1.9344,
      "step": 212
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005986189801699716,
      "loss": 1.8629,
      "step": 213
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000598512747875354,
      "loss": 1.9363,
      "step": 214
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005984065155807364,
      "loss": 2.0402,
      "step": 215
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005983002832861189,
      "loss": 1.9,
      "step": 216
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005981940509915014,
      "loss": 1.8588,
      "step": 217
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005980878186968838,
      "loss": 1.8654,
      "step": 218
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005979815864022663,
      "loss": 1.9509,
      "step": 219
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005978753541076487,
      "loss": 1.9325,
      "step": 220
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005977691218130311,
      "loss": 1.8617,
      "step": 221
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005976628895184136,
      "loss": 1.9164,
      "step": 222
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000597556657223796,
      "loss": 1.8987,
      "step": 223
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005974504249291785,
      "loss": 2.0317,
      "step": 224
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005973441926345608,
      "loss": 1.9936,
      "step": 225
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005972379603399432,
      "loss": 1.9103,
      "step": 226
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005971317280453257,
      "loss": 1.9545,
      "step": 227
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005970254957507082,
      "loss": 1.9247,
      "step": 228
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005969192634560906,
      "loss": 1.8792,
      "step": 229
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005968130311614731,
      "loss": 1.9461,
      "step": 230
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005967067988668555,
      "loss": 1.8948,
      "step": 231
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005966005665722379,
      "loss": 2.0436,
      "step": 232
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005964943342776204,
      "loss": 2.0009,
      "step": 233
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005963881019830028,
      "loss": 1.9595,
      "step": 234
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005962818696883852,
      "loss": 1.9346,
      "step": 235
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005961756373937677,
      "loss": 2.0312,
      "step": 236
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00059606940509915,
      "loss": 2.0205,
      "step": 237
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005959631728045325,
      "loss": 1.8533,
      "step": 238
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000595856940509915,
      "loss": 1.9943,
      "step": 239
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005957507082152974,
      "loss": 1.9002,
      "step": 240
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005956444759206798,
      "loss": 2.0044,
      "step": 241
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005955382436260623,
      "loss": 2.032,
      "step": 242
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005954320113314447,
      "loss": 1.8933,
      "step": 243
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005953257790368272,
      "loss": 1.8971,
      "step": 244
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005952195467422096,
      "loss": 1.9241,
      "step": 245
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000595113314447592,
      "loss": 1.9246,
      "step": 246
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005950070821529745,
      "loss": 1.8752,
      "step": 247
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005949008498583569,
      "loss": 1.8325,
      "step": 248
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005947946175637393,
      "loss": 2.0427,
      "step": 249
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005946883852691218,
      "loss": 2.0028,
      "step": 250
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005945821529745042,
      "loss": 1.8925,
      "step": 251
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005944759206798866,
      "loss": 1.9451,
      "step": 252
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005943696883852691,
      "loss": 2.0214,
      "step": 253
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005942634560906515,
      "loss": 1.9055,
      "step": 254
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005941572237960339,
      "loss": 2.0471,
      "step": 255
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005940509915014164,
      "loss": 1.9051,
      "step": 256
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005939447592067988,
      "loss": 1.9161,
      "step": 257
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005938385269121813,
      "loss": 1.9885,
      "step": 258
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005937322946175637,
      "loss": 1.8885,
      "step": 259
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000593626062322946,
      "loss": 1.9312,
      "step": 260
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005935198300283285,
      "loss": 2.007,
      "step": 261
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000593413597733711,
      "loss": 2.0364,
      "step": 262
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005933073654390934,
      "loss": 1.9795,
      "step": 263
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005932011331444759,
      "loss": 2.0227,
      "step": 264
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005930949008498583,
      "loss": 2.0389,
      "step": 265
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005929886685552407,
      "loss": 2.0966,
      "step": 266
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005928824362606232,
      "loss": 2.0527,
      "step": 267
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005927762039660056,
      "loss": 1.9479,
      "step": 268
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005926699716713881,
      "loss": 1.9406,
      "step": 269
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005925637393767705,
      "loss": 1.9553,
      "step": 270
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005924575070821529,
      "loss": 1.9249,
      "step": 271
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005923512747875354,
      "loss": 1.8754,
      "step": 272
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005922450424929179,
      "loss": 1.9168,
      "step": 273
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005921388101983002,
      "loss": 1.8502,
      "step": 274
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005920325779036826,
      "loss": 1.909,
      "step": 275
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005919263456090651,
      "loss": 1.9713,
      "step": 276
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005918201133144475,
      "loss": 1.9817,
      "step": 277
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00059171388101983,
      "loss": 1.9468,
      "step": 278
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005916076487252124,
      "loss": 1.9499,
      "step": 279
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005915014164305948,
      "loss": 2.0154,
      "step": 280
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005913951841359773,
      "loss": 2.0013,
      "step": 281
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005912889518413597,
      "loss": 1.9174,
      "step": 282
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005911827195467422,
      "loss": 2.0181,
      "step": 283
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005910764872521247,
      "loss": 1.8739,
      "step": 284
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000590970254957507,
      "loss": 1.9622,
      "step": 285
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005908640226628894,
      "loss": 1.992,
      "step": 286
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005907577903682719,
      "loss": 1.9311,
      "step": 287
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005906515580736543,
      "loss": 1.8938,
      "step": 288
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005905453257790368,
      "loss": 1.939,
      "step": 289
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005904390934844192,
      "loss": 1.946,
      "step": 290
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005903328611898016,
      "loss": 1.969,
      "step": 291
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005902266288951841,
      "loss": 1.9189,
      "step": 292
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005901203966005665,
      "loss": 1.9114,
      "step": 293
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000590014164305949,
      "loss": 1.919,
      "step": 294
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005899079320113314,
      "loss": 1.9174,
      "step": 295
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005898016997167139,
      "loss": 1.9578,
      "step": 296
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005896954674220963,
      "loss": 1.9573,
      "step": 297
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005895892351274787,
      "loss": 1.9774,
      "step": 298
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005894830028328611,
      "loss": 2.0076,
      "step": 299
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005893767705382435,
      "loss": 1.9378,
      "step": 300
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000589270538243626,
      "loss": 1.9127,
      "step": 301
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005891643059490084,
      "loss": 1.9028,
      "step": 302
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005890580736543909,
      "loss": 2.0307,
      "step": 303
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005889518413597733,
      "loss": 1.886,
      "step": 304
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005888456090651558,
      "loss": 1.9288,
      "step": 305
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005887393767705382,
      "loss": 1.9184,
      "step": 306
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005886331444759207,
      "loss": 1.8903,
      "step": 307
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005885269121813031,
      "loss": 1.9464,
      "step": 308
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005884206798866856,
      "loss": 1.9017,
      "step": 309
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000588314447592068,
      "loss": 1.9359,
      "step": 310
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005882082152974503,
      "loss": 2.07,
      "step": 311
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005881019830028328,
      "loss": 1.899,
      "step": 312
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005879957507082152,
      "loss": 1.9346,
      "step": 313
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005878895184135976,
      "loss": 1.9751,
      "step": 314
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005877832861189801,
      "loss": 1.8593,
      "step": 315
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005876770538243626,
      "loss": 1.9072,
      "step": 316
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000587570821529745,
      "loss": 2.0165,
      "step": 317
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005874645892351275,
      "loss": 2.0048,
      "step": 318
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005873583569405099,
      "loss": 2.0082,
      "step": 319
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005872521246458923,
      "loss": 1.9908,
      "step": 320
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005871458923512748,
      "loss": 1.8866,
      "step": 321
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005870396600566571,
      "loss": 1.8997,
      "step": 322
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005869334277620396,
      "loss": 2.0193,
      "step": 323
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000586827195467422,
      "loss": 2.0157,
      "step": 324
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005867209631728044,
      "loss": 1.9045,
      "step": 325
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005866147308781869,
      "loss": 1.9727,
      "step": 326
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005865084985835694,
      "loss": 1.9071,
      "step": 327
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005864022662889518,
      "loss": 1.9013,
      "step": 328
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005862960339943343,
      "loss": 1.9227,
      "step": 329
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005861898016997167,
      "loss": 1.9121,
      "step": 330
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005860835694050991,
      "loss": 1.9515,
      "step": 331
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005859773371104816,
      "loss": 1.8773,
      "step": 332
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000585871104815864,
      "loss": 1.979,
      "step": 333
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005857648725212463,
      "loss": 1.9036,
      "step": 334
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005856586402266288,
      "loss": 1.9582,
      "step": 335
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005855524079320112,
      "loss": 1.8322,
      "step": 336
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005854461756373937,
      "loss": 2.0046,
      "step": 337
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005853399433427762,
      "loss": 1.9435,
      "step": 338
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005852337110481586,
      "loss": 1.942,
      "step": 339
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000585127478753541,
      "loss": 1.9315,
      "step": 340
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005850212464589235,
      "loss": 1.95,
      "step": 341
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005849150141643059,
      "loss": 1.9401,
      "step": 342
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005848087818696884,
      "loss": 1.98,
      "step": 343
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005847025495750708,
      "loss": 1.9448,
      "step": 344
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005845963172804532,
      "loss": 1.9539,
      "step": 345
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005844900849858357,
      "loss": 2.0188,
      "step": 346
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000584383852691218,
      "loss": 1.9267,
      "step": 347
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005842776203966005,
      "loss": 2.0382,
      "step": 348
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000584171388101983,
      "loss": 1.9714,
      "step": 349
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005840651558073654,
      "loss": 1.9789,
      "step": 350
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005839589235127478,
      "loss": 1.8664,
      "step": 351
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005838526912181303,
      "loss": 2.0072,
      "step": 352
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005837464589235127,
      "loss": 1.936,
      "step": 353
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005836402266288951,
      "loss": 1.8285,
      "step": 354
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005835339943342776,
      "loss": 1.9294,
      "step": 355
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00058342776203966,
      "loss": 1.8979,
      "step": 356
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005833215297450425,
      "loss": 1.9088,
      "step": 357
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005832152974504249,
      "loss": 1.9107,
      "step": 358
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005831090651558072,
      "loss": 1.9215,
      "step": 359
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005830028328611897,
      "loss": 1.9034,
      "step": 360
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005828966005665722,
      "loss": 1.8581,
      "step": 361
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005827903682719546,
      "loss": 1.8922,
      "step": 362
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005826841359773371,
      "loss": 1.8397,
      "step": 363
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005825779036827195,
      "loss": 1.9799,
      "step": 364
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005824716713881019,
      "loss": 1.9085,
      "step": 365
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005823654390934844,
      "loss": 1.865,
      "step": 366
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005822592067988668,
      "loss": 2.0325,
      "step": 367
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005821529745042493,
      "loss": 1.9283,
      "step": 368
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005820467422096317,
      "loss": 1.8934,
      "step": 369
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000581940509915014,
      "loss": 1.9225,
      "step": 370
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005818342776203965,
      "loss": 1.8816,
      "step": 371
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000581728045325779,
      "loss": 1.897,
      "step": 372
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005816218130311614,
      "loss": 1.9609,
      "step": 373
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005815155807365438,
      "loss": 1.9549,
      "step": 374
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005814093484419263,
      "loss": 2.0133,
      "step": 375
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005813031161473087,
      "loss": 1.8156,
      "step": 376
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005811968838526912,
      "loss": 1.9295,
      "step": 377
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005810906515580736,
      "loss": 1.9548,
      "step": 378
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000580984419263456,
      "loss": 1.9483,
      "step": 379
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005808781869688385,
      "loss": 1.8704,
      "step": 380
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005807719546742209,
      "loss": 1.9807,
      "step": 381
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005806657223796034,
      "loss": 1.9642,
      "step": 382
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005805594900849859,
      "loss": 1.9625,
      "step": 383
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005804532577903682,
      "loss": 1.8797,
      "step": 384
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005803470254957506,
      "loss": 1.933,
      "step": 385
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005802407932011331,
      "loss": 1.8383,
      "step": 386
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005801345609065155,
      "loss": 1.9156,
      "step": 387
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000580028328611898,
      "loss": 1.9132,
      "step": 388
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005799220963172804,
      "loss": 2.038,
      "step": 389
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005798158640226628,
      "loss": 1.9887,
      "step": 390
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005797096317280453,
      "loss": 1.8482,
      "step": 391
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005796033994334277,
      "loss": 1.9472,
      "step": 392
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005794971671388101,
      "loss": 1.9624,
      "step": 393
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005793909348441927,
      "loss": 1.8782,
      "step": 394
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000579284702549575,
      "loss": 1.8894,
      "step": 395
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005791784702549574,
      "loss": 1.8229,
      "step": 396
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005790722379603399,
      "loss": 1.8939,
      "step": 397
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005789660056657223,
      "loss": 1.886,
      "step": 398
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005788597733711047,
      "loss": 1.8785,
      "step": 399
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005787535410764872,
      "loss": 1.8943,
      "step": 400
    },
    {
      "epoch": 0.27,
      "eval_loss": 2.0144975185394287,
      "eval_runtime": 115.2996,
      "eval_samples_per_second": 8.673,
      "eval_steps_per_second": 8.673,
      "step": 400
    }
  ],
  "max_steps": 5848,
  "num_train_epochs": 4,
  "total_flos": 4.8975138397771776e+17,
  "trial_name": null,
  "trial_params": null
}