{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 446,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 6e-07,
      "loss": 4.7556,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.2e-06,
      "loss": 4.8976,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8e-06,
      "loss": 4.8688,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8e-06,
      "loss": 4.8422,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-06,
      "loss": 4.7856,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.9999999999999997e-06,
      "loss": 4.8246,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-06,
      "loss": 4.7754,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.2e-06,
      "loss": 4.7944,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-06,
      "loss": 4.7514,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.399999999999999e-06,
      "loss": 4.5898,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.999999999999999e-06,
      "loss": 4.6861,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.599999999999999e-06,
      "loss": 4.6332,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.2e-06,
      "loss": 4.5493,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.799999999999998e-06,
      "loss": 4.5413,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.4e-06,
      "loss": 4.4151,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.999999999999999e-06,
      "loss": 4.538,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.6e-06,
      "loss": 4.4373,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.02e-05,
      "loss": 4.5295,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.0799999999999998e-05,
      "loss": 4.3354,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.14e-05,
      "loss": 4.4804,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.1999999999999999e-05,
      "loss": 4.455,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.26e-05,
      "loss": 4.3989,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.3199999999999997e-05,
      "loss": 4.4764,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.3799999999999998e-05,
      "loss": 4.4451,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.44e-05,
      "loss": 4.2551,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 4.5147,
      "step": 26
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.5599999999999996e-05,
      "loss": 4.3701,
      "step": 27
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.6199999999999997e-05,
      "loss": 4.2124,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.68e-05,
      "loss": 4.1934,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.74e-05,
      "loss": 4.4269,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.7999999999999997e-05,
      "loss": 4.3935,
      "step": 31
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.8599999999999998e-05,
      "loss": 4.2527,
      "step": 32
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.92e-05,
      "loss": 4.3303,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.98e-05,
      "loss": 4.2801,
      "step": 34
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.04e-05,
      "loss": 4.3412,
      "step": 35
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.1e-05,
      "loss": 4.3273,
      "step": 36
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.1599999999999996e-05,
      "loss": 4.3727,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.2199999999999998e-05,
      "loss": 4.3086,
      "step": 38
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.28e-05,
      "loss": 4.414,
      "step": 39
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.34e-05,
      "loss": 4.251,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.3999999999999997e-05,
      "loss": 4.3068,
      "step": 41
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.4599999999999998e-05,
      "loss": 4.3946,
      "step": 42
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.52e-05,
      "loss": 4.1459,
      "step": 43
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.5799999999999997e-05,
      "loss": 4.3287,
      "step": 44
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.6399999999999995e-05,
      "loss": 4.4167,
      "step": 45
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.6999999999999996e-05,
      "loss": 4.4696,
      "step": 46
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.7599999999999997e-05,
      "loss": 4.3917,
      "step": 47
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.8199999999999998e-05,
      "loss": 4.6109,
      "step": 48
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.88e-05,
      "loss": 4.7011,
      "step": 49
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.88e-05,
      "loss": 4.4026,
      "step": 50
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.94e-05,
      "loss": 4.2793,
      "step": 51
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 4.1631,
      "step": 52
    },
    {
      "epoch": 0.12,
      "learning_rate": 3.06e-05,
      "loss": 4.3255,
      "step": 53
    },
    {
      "epoch": 0.12,
      "learning_rate": 3.119999999999999e-05,
      "loss": 4.2389,
      "step": 54
    },
    {
      "epoch": 0.12,
      "learning_rate": 3.1799999999999994e-05,
      "loss": 4.0638,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 3.2399999999999995e-05,
      "loss": 4.2621,
      "step": 56
    },
    {
      "epoch": 0.13,
      "learning_rate": 3.2999999999999996e-05,
      "loss": 4.2888,
      "step": 57
    },
    {
      "epoch": 0.13,
      "learning_rate": 3.36e-05,
      "loss": 4.3768,
      "step": 58
    },
    {
      "epoch": 0.13,
      "learning_rate": 3.42e-05,
      "loss": 4.2974,
      "step": 59
    },
    {
      "epoch": 0.13,
      "learning_rate": 3.48e-05,
      "loss": 4.1693,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.539999999999999e-05,
      "loss": 4.2442,
      "step": 61
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.5999999999999994e-05,
      "loss": 4.1914,
      "step": 62
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.6599999999999995e-05,
      "loss": 4.1744,
      "step": 63
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.7199999999999996e-05,
      "loss": 4.2779,
      "step": 64
    },
    {
      "epoch": 0.15,
      "learning_rate": 3.78e-05,
      "loss": 4.2428,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 3.84e-05,
      "loss": 4.1126,
      "step": 66
    },
    {
      "epoch": 0.15,
      "learning_rate": 3.9e-05,
      "loss": 4.2649,
      "step": 67
    },
    {
      "epoch": 0.15,
      "learning_rate": 3.96e-05,
      "loss": 4.1396,
      "step": 68
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.02e-05,
      "loss": 4.1793,
      "step": 69
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.08e-05,
      "loss": 4.1507,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.14e-05,
      "loss": 4.2735,
      "step": 71
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.2e-05,
      "loss": 4.3299,
      "step": 72
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.259999999999999e-05,
      "loss": 4.1417,
      "step": 73
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.319999999999999e-05,
      "loss": 4.2308,
      "step": 74
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.3799999999999994e-05,
      "loss": 4.2123,
      "step": 75
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.4399999999999995e-05,
      "loss": 4.1712,
      "step": 76
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 4.2178,
      "step": 77
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.56e-05,
      "loss": 4.1639,
      "step": 78
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.62e-05,
      "loss": 4.1641,
      "step": 79
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.68e-05,
      "loss": 4.3178,
      "step": 80
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.7399999999999993e-05,
      "loss": 4.2517,
      "step": 81
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.7999999999999994e-05,
      "loss": 4.1994,
      "step": 82
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.8599999999999995e-05,
      "loss": 4.3129,
      "step": 83
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.9199999999999997e-05,
      "loss": 4.1858,
      "step": 84
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.98e-05,
      "loss": 4.2606,
      "step": 85
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.04e-05,
      "loss": 4.2162,
      "step": 86
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.1e-05,
      "loss": 4.2794,
      "step": 87
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.1599999999999994e-05,
      "loss": 4.1588,
      "step": 88
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.2199999999999995e-05,
      "loss": 4.3253,
      "step": 89
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.279999999999999e-05,
      "loss": 4.3031,
      "step": 90
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.339999999999999e-05,
      "loss": 4.179,
      "step": 91
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.399999999999999e-05,
      "loss": 4.4271,
      "step": 92
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.459999999999999e-05,
      "loss": 4.3513,
      "step": 93
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.519999999999999e-05,
      "loss": 4.3588,
      "step": 94
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.5799999999999994e-05,
      "loss": 4.2543,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.6399999999999995e-05,
      "loss": 4.493,
      "step": 96
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 4.3912,
      "step": 97
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.76e-05,
      "loss": 4.26,
      "step": 98
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.82e-05,
      "loss": 4.6017,
      "step": 99
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.88e-05,
      "loss": 4.386,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.94e-05,
      "loss": 4.2662,
      "step": 101
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 4.2116,
      "step": 102
    },
    {
      "epoch": 0.23,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 4.0773,
      "step": 103
    },
    {
      "epoch": 0.23,
      "learning_rate": 6.12e-05,
      "loss": 4.1472,
      "step": 104
    },
    {
      "epoch": 0.24,
      "learning_rate": 6.18e-05,
      "loss": 4.0741,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 6.239999999999999e-05,
      "loss": 4.1222,
      "step": 106
    },
    {
      "epoch": 0.24,
      "learning_rate": 6.299999999999999e-05,
      "loss": 4.1845,
      "step": 107
    },
    {
      "epoch": 0.24,
      "learning_rate": 6.359999999999999e-05,
      "loss": 4.0898,
      "step": 108
    },
    {
      "epoch": 0.24,
      "learning_rate": 6.419999999999999e-05,
      "loss": 4.1178,
      "step": 109
    },
    {
      "epoch": 0.25,
      "learning_rate": 6.479999999999999e-05,
      "loss": 4.1598,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 6.539999999999999e-05,
      "loss": 4.1892,
      "step": 111
    },
    {
      "epoch": 0.25,
      "learning_rate": 6.599999999999999e-05,
      "loss": 4.2004,
      "step": 112
    },
    {
      "epoch": 0.25,
      "learning_rate": 6.659999999999999e-05,
      "loss": 4.1612,
      "step": 113
    },
    {
      "epoch": 0.26,
      "learning_rate": 6.72e-05,
      "loss": 4.1313,
      "step": 114
    },
    {
      "epoch": 0.26,
      "learning_rate": 6.78e-05,
      "loss": 4.1708,
      "step": 115
    },
    {
      "epoch": 0.26,
      "learning_rate": 6.84e-05,
      "loss": 4.2872,
      "step": 116
    },
    {
      "epoch": 0.26,
      "learning_rate": 6.9e-05,
      "loss": 4.1456,
      "step": 117
    },
    {
      "epoch": 0.26,
      "learning_rate": 6.96e-05,
      "loss": 4.3008,
      "step": 118
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.02e-05,
      "loss": 4.2124,
      "step": 119
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.079999999999999e-05,
      "loss": 4.2371,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.139999999999999e-05,
      "loss": 4.048,
      "step": 121
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.199999999999999e-05,
      "loss": 4.1717,
      "step": 122
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.259999999999999e-05,
      "loss": 4.1803,
      "step": 123
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.319999999999999e-05,
      "loss": 4.1608,
      "step": 124
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.379999999999999e-05,
      "loss": 4.2752,
      "step": 125
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.439999999999999e-05,
      "loss": 4.2868,
      "step": 126
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.5e-05,
      "loss": 4.1882,
      "step": 127
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.56e-05,
      "loss": 4.1631,
      "step": 128
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.62e-05,
      "loss": 4.0885,
      "step": 129
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.68e-05,
      "loss": 4.2642,
      "step": 130
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.74e-05,
      "loss": 4.1487,
      "step": 131
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.8e-05,
      "loss": 4.2225,
      "step": 132
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.86e-05,
      "loss": 4.0983,
      "step": 133
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.92e-05,
      "loss": 4.1975,
      "step": 134
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.98e-05,
      "loss": 4.3307,
      "step": 135
    },
    {
      "epoch": 0.3,
      "learning_rate": 8.04e-05,
      "loss": 4.1701,
      "step": 136
    },
    {
      "epoch": 0.31,
      "learning_rate": 8.1e-05,
      "loss": 4.27,
      "step": 137
    },
    {
      "epoch": 0.31,
      "learning_rate": 8.16e-05,
      "loss": 4.3063,
      "step": 138
    },
    {
      "epoch": 0.31,
      "learning_rate": 8.22e-05,
      "loss": 4.3268,
      "step": 139
    },
    {
      "epoch": 0.31,
      "learning_rate": 8.28e-05,
      "loss": 4.2758,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 8.34e-05,
      "loss": 4.39,
      "step": 141
    },
    {
      "epoch": 0.32,
      "learning_rate": 8.4e-05,
      "loss": 4.3409,
      "step": 142
    },
    {
      "epoch": 0.32,
      "learning_rate": 8.459999999999998e-05,
      "loss": 4.3092,
      "step": 143
    },
    {
      "epoch": 0.32,
      "learning_rate": 8.519999999999998e-05,
      "loss": 4.3459,
      "step": 144
    },
    {
      "epoch": 0.33,
      "learning_rate": 8.579999999999998e-05,
      "loss": 4.2443,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 8.639999999999999e-05,
      "loss": 4.3578,
      "step": 146
    },
    {
      "epoch": 0.33,
      "learning_rate": 8.699999999999999e-05,
      "loss": 4.6777,
      "step": 147
    },
    {
      "epoch": 0.33,
      "learning_rate": 8.759999999999999e-05,
      "loss": 4.6753,
      "step": 148
    },
    {
      "epoch": 0.33,
      "learning_rate": 8.819999999999999e-05,
      "loss": 4.5273,
      "step": 149
    },
    {
      "epoch": 0.34,
      "learning_rate": 8.879999999999999e-05,
      "loss": 4.5163,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 8.939999999999999e-05,
      "loss": 4.1214,
      "step": 151
    },
    {
      "epoch": 0.34,
      "learning_rate": 8.999999999999999e-05,
      "loss": 4.211,
      "step": 152
    },
    {
      "epoch": 0.34,
      "learning_rate": 9.059999999999999e-05,
      "loss": 4.2786,
      "step": 153
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.12e-05,
      "loss": 4.0919,
      "step": 154
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.18e-05,
      "loss": 4.2591,
      "step": 155
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.24e-05,
      "loss": 4.0978,
      "step": 156
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.3e-05,
      "loss": 4.1477,
      "step": 157
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.36e-05,
      "loss": 4.2391,
      "step": 158
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.419999999999999e-05,
      "loss": 4.2568,
      "step": 159
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.479999999999999e-05,
      "loss": 4.2874,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.539999999999999e-05,
      "loss": 4.3125,
      "step": 161
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.599999999999999e-05,
      "loss": 4.2459,
      "step": 162
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.659999999999999e-05,
      "loss": 4.2133,
      "step": 163
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.719999999999999e-05,
      "loss": 4.2734,
      "step": 164
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.779999999999999e-05,
      "loss": 4.1366,
      "step": 165
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.839999999999999e-05,
      "loss": 4.1946,
      "step": 166
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.9e-05,
      "loss": 4.1331,
      "step": 167
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.96e-05,
      "loss": 4.1572,
      "step": 168
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001002,
      "loss": 4.2745,
      "step": 169
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001008,
      "loss": 4.2518,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001014,
      "loss": 4.2305,
      "step": 171
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000102,
      "loss": 4.3334,
      "step": 172
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001026,
      "loss": 4.1392,
      "step": 173
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00010319999999999999,
      "loss": 4.3183,
      "step": 174
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00010379999999999999,
      "loss": 4.3215,
      "step": 175
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00010439999999999999,
      "loss": 4.1605,
      "step": 176
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00010499999999999999,
      "loss": 4.129,
      "step": 177
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00010559999999999998,
      "loss": 4.3029,
      "step": 178
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00010619999999999998,
      "loss": 4.3742,
      "step": 179
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00010679999999999998,
      "loss": 4.2763,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00010739999999999998,
      "loss": 4.2651,
      "step": 181
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00010799999999999998,
      "loss": 4.2919,
      "step": 182
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00010859999999999998,
      "loss": 4.3384,
      "step": 183
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00010919999999999998,
      "loss": 4.2915,
      "step": 184
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00010979999999999999,
      "loss": 4.2921,
      "step": 185
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011039999999999999,
      "loss": 4.1351,
      "step": 186
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011099999999999999,
      "loss": 4.2015,
      "step": 187
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011159999999999999,
      "loss": 4.1486,
      "step": 188
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011219999999999999,
      "loss": 4.3484,
      "step": 189
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011279999999999999,
      "loss": 4.3122,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011339999999999999,
      "loss": 4.3702,
      "step": 191
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011399999999999999,
      "loss": 4.2959,
      "step": 192
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001146,
      "loss": 4.2193,
      "step": 193
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001152,
      "loss": 4.3976,
      "step": 194
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001158,
      "loss": 4.5722,
      "step": 195
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001164,
      "loss": 4.3863,
      "step": 196
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000117,
      "loss": 4.6552,
      "step": 197
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001176,
      "loss": 4.6178,
      "step": 198
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001182,
      "loss": 4.4768,
      "step": 199
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001188,
      "loss": 4.5382,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001194,
      "loss": 4.4213,
      "step": 201
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011999999999999999,
      "loss": 4.397,
      "step": 202
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00012059999999999999,
      "loss": 4.3509,
      "step": 203
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00012119999999999999,
      "loss": 4.2907,
      "step": 204
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00012179999999999999,
      "loss": 4.3604,
      "step": 205
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001224,
      "loss": 4.3155,
      "step": 206
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00012299999999999998,
      "loss": 4.1779,
      "step": 207
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001236,
      "loss": 4.3342,
      "step": 208
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012419999999999998,
      "loss": 4.3674,
      "step": 209
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012479999999999997,
      "loss": 4.4109,
      "step": 210
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012539999999999999,
      "loss": 4.1487,
      "step": 211
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012599999999999997,
      "loss": 4.2717,
      "step": 212
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001266,
      "loss": 4.2143,
      "step": 213
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012719999999999997,
      "loss": 4.1991,
      "step": 214
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001278,
      "loss": 4.2652,
      "step": 215
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012839999999999998,
      "loss": 4.2753,
      "step": 216
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000129,
      "loss": 4.3038,
      "step": 217
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012959999999999998,
      "loss": 4.2704,
      "step": 218
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001302,
      "loss": 4.2562,
      "step": 219
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00013079999999999998,
      "loss": 4.2529,
      "step": 220
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001314,
      "loss": 4.2522,
      "step": 221
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00013199999999999998,
      "loss": 4.3732,
      "step": 222
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001326,
      "loss": 4.4052,
      "step": 223
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00013319999999999999,
      "loss": 4.3487,
      "step": 224
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001338,
      "loss": 4.3883,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001344,
      "loss": 4.3272,
      "step": 226
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000135,
      "loss": 4.485,
      "step": 227
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001356,
      "loss": 4.3491,
      "step": 228
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001362,
      "loss": 4.2183,
      "step": 229
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001368,
      "loss": 4.3852,
      "step": 230
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001374,
      "loss": 4.3161,
      "step": 231
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000138,
      "loss": 4.1663,
      "step": 232
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001386,
      "loss": 4.3379,
      "step": 233
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001392,
      "loss": 4.362,
      "step": 234
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00013979999999999998,
      "loss": 4.525,
      "step": 235
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001404,
      "loss": 4.2465,
      "step": 236
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00014099999999999998,
      "loss": 4.2932,
      "step": 237
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00014159999999999997,
      "loss": 4.2231,
      "step": 238
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001422,
      "loss": 4.2978,
      "step": 239
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00014279999999999997,
      "loss": 4.4569,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001434,
      "loss": 4.2881,
      "step": 241
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00014399999999999998,
      "loss": 4.399,
      "step": 242
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001446,
      "loss": 4.5997,
      "step": 243
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00014519999999999998,
      "loss": 4.3953,
      "step": 244
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001458,
      "loss": 4.3519,
      "step": 245
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00014639999999999998,
      "loss": 4.2577,
      "step": 246
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000147,
      "loss": 4.0995,
      "step": 247
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00014759999999999998,
      "loss": 4.8691,
      "step": 248
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001482,
      "loss": 4.7885,
      "step": 249
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00014879999999999998,
      "loss": 5.0766,
      "step": 250
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001494,
      "loss": 4.4758,
      "step": 251
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00015,
      "loss": 4.4885,
      "step": 252
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00015059999999999997,
      "loss": 4.4668,
      "step": 253
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001512,
      "loss": 4.3194,
      "step": 254
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00015179999999999998,
      "loss": 4.3164,
      "step": 255
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001524,
      "loss": 4.3077,
      "step": 256
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00015299999999999998,
      "loss": 4.2822,
      "step": 257
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001536,
      "loss": 4.3208,
      "step": 258
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00015419999999999998,
      "loss": 4.3895,
      "step": 259
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001548,
      "loss": 4.3,
      "step": 260
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00015539999999999998,
      "loss": 4.4501,
      "step": 261
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000156,
      "loss": 4.3404,
      "step": 262
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00015659999999999998,
      "loss": 4.5072,
      "step": 263
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001572,
      "loss": 4.2912,
      "step": 264
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001578,
      "loss": 4.3544,
      "step": 265
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001584,
      "loss": 4.3234,
      "step": 266
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000159,
      "loss": 4.3221,
      "step": 267
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001596,
      "loss": 4.2633,
      "step": 268
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001602,
      "loss": 4.4572,
      "step": 269
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001608,
      "loss": 4.4001,
      "step": 270
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001614,
      "loss": 4.2458,
      "step": 271
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000162,
      "loss": 4.312,
      "step": 272
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001626,
      "loss": 4.3604,
      "step": 273
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001632,
      "loss": 4.2737,
      "step": 274
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001638,
      "loss": 4.5393,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001644,
      "loss": 4.4073,
      "step": 276
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000165,
      "loss": 4.2604,
      "step": 277
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001656,
      "loss": 4.4389,
      "step": 278
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001662,
      "loss": 4.3704,
      "step": 279
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001668,
      "loss": 4.4282,
      "step": 280
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001674,
      "loss": 4.4334,
      "step": 281
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000168,
      "loss": 4.2849,
      "step": 282
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001686,
      "loss": 4.3171,
      "step": 283
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00016919999999999997,
      "loss": 4.2541,
      "step": 284
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00016979999999999998,
      "loss": 4.5257,
      "step": 285
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00017039999999999997,
      "loss": 5.1541,
      "step": 286
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00017099999999999998,
      "loss": 4.5727,
      "step": 287
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00017159999999999997,
      "loss": 4.3898,
      "step": 288
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00017219999999999998,
      "loss": 4.3269,
      "step": 289
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00017279999999999997,
      "loss": 4.3766,
      "step": 290
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00017339999999999996,
      "loss": 4.6615,
      "step": 291
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00017399999999999997,
      "loss": 4.4404,
      "step": 292
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00017459999999999996,
      "loss": 4.4725,
      "step": 293
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00017519999999999998,
      "loss": 4.5832,
      "step": 294
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00017579999999999996,
      "loss": 4.6187,
      "step": 295
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00017639999999999998,
      "loss": 4.6338,
      "step": 296
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00017699999999999997,
      "loss": 4.7781,
      "step": 297
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00017759999999999998,
      "loss": 4.7394,
      "step": 298
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00017819999999999997,
      "loss": 4.316,
      "step": 299
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00017879999999999998,
      "loss": 4.8654,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00017939999999999997,
      "loss": 4.4355,
      "step": 301
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017999999999999998,
      "loss": 4.4773,
      "step": 302
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00018059999999999997,
      "loss": 4.4691,
      "step": 303
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00018119999999999999,
      "loss": 4.4878,
      "step": 304
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00018179999999999997,
      "loss": 4.3227,
      "step": 305
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001824,
      "loss": 4.3465,
      "step": 306
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00018299999999999998,
      "loss": 4.4829,
      "step": 307
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001836,
      "loss": 4.3547,
      "step": 308
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00018419999999999998,
      "loss": 4.41,
      "step": 309
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001848,
      "loss": 4.4728,
      "step": 310
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00018539999999999998,
      "loss": 4.1818,
      "step": 311
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000186,
      "loss": 4.5282,
      "step": 312
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00018659999999999998,
      "loss": 4.5797,
      "step": 313
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001872,
      "loss": 4.3441,
      "step": 314
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00018779999999999998,
      "loss": 4.3694,
      "step": 315
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00018839999999999997,
      "loss": 4.243,
      "step": 316
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00018899999999999999,
      "loss": 4.3554,
      "step": 317
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00018959999999999997,
      "loss": 4.2382,
      "step": 318
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001902,
      "loss": 4.3095,
      "step": 319
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019079999999999998,
      "loss": 4.4703,
      "step": 320
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001914,
      "loss": 4.3619,
      "step": 321
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019199999999999998,
      "loss": 4.1853,
      "step": 322
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001926,
      "loss": 4.3589,
      "step": 323
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019319999999999998,
      "loss": 4.2226,
      "step": 324
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001938,
      "loss": 4.4577,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019439999999999998,
      "loss": 4.4968,
      "step": 326
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000195,
      "loss": 4.2916,
      "step": 327
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019559999999999998,
      "loss": 4.1742,
      "step": 328
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001962,
      "loss": 4.3647,
      "step": 329
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019679999999999999,
      "loss": 4.438,
      "step": 330
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001974,
      "loss": 4.346,
      "step": 331
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000198,
      "loss": 4.2271,
      "step": 332
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001986,
      "loss": 4.353,
      "step": 333
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001992,
      "loss": 4.5941,
      "step": 334
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001998,
      "loss": 4.6264,
      "step": 335
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002004,
      "loss": 4.3837,
      "step": 336
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000201,
      "loss": 4.4402,
      "step": 337
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002016,
      "loss": 4.4158,
      "step": 338
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002022,
      "loss": 4.4913,
      "step": 339
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002028,
      "loss": 4.5728,
      "step": 340
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00020339999999999998,
      "loss": 4.4069,
      "step": 341
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000204,
      "loss": 4.6356,
      "step": 342
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00020459999999999999,
      "loss": 4.5075,
      "step": 343
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002052,
      "loss": 4.5244,
      "step": 344
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002058,
      "loss": 4.2865,
      "step": 345
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00020639999999999998,
      "loss": 4.4042,
      "step": 346
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00020699999999999996,
      "loss": 4.6676,
      "step": 347
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00020759999999999998,
      "loss": 4.48,
      "step": 348
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00020819999999999996,
      "loss": 4.9826,
      "step": 349
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00020879999999999998,
      "loss": 4.4187,
      "step": 350
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00020939999999999997,
      "loss": 4.6491,
      "step": 351
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00020999999999999998,
      "loss": 4.5337,
      "step": 352
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00021059999999999997,
      "loss": 4.2791,
      "step": 353
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00021119999999999996,
      "loss": 4.5545,
      "step": 354
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00021179999999999997,
      "loss": 4.5379,
      "step": 355
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00021239999999999996,
      "loss": 4.6913,
      "step": 356
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00021299999999999997,
      "loss": 4.6171,
      "step": 357
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00021359999999999996,
      "loss": 4.5704,
      "step": 358
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00021419999999999998,
      "loss": 4.3849,
      "step": 359
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00021479999999999996,
      "loss": 4.4353,
      "step": 360
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00021539999999999998,
      "loss": 4.5627,
      "step": 361
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00021599999999999996,
      "loss": 4.4172,
      "step": 362
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00021659999999999998,
      "loss": 4.3125,
      "step": 363
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00021719999999999997,
      "loss": 4.6123,
      "step": 364
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00021779999999999998,
      "loss": 4.5523,
      "step": 365
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00021839999999999997,
      "loss": 4.3891,
      "step": 366
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00021899999999999998,
      "loss": 4.4283,
      "step": 367
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00021959999999999997,
      "loss": 4.4099,
      "step": 368
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00022019999999999999,
      "loss": 4.4941,
      "step": 369
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00022079999999999997,
      "loss": 4.4114,
      "step": 370
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002214,
      "loss": 4.3696,
      "step": 371
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00022199999999999998,
      "loss": 4.3713,
      "step": 372
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002226,
      "loss": 4.3933,
      "step": 373
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00022319999999999998,
      "loss": 4.2505,
      "step": 374
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002238,
      "loss": 4.2947,
      "step": 375
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00022439999999999998,
      "loss": 4.3779,
      "step": 376
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000225,
      "loss": 4.4394,
      "step": 377
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00022559999999999998,
      "loss": 4.4394,
      "step": 378
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00022619999999999997,
      "loss": 4.6147,
      "step": 379
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00022679999999999998,
      "loss": 4.2979,
      "step": 380
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00022739999999999997,
      "loss": 4.6721,
      "step": 381
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00022799999999999999,
      "loss": 4.8685,
      "step": 382
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00022859999999999997,
      "loss": 4.3676,
      "step": 383
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002292,
      "loss": 4.3411,
      "step": 384
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00022979999999999997,
      "loss": 4.5083,
      "step": 385
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002304,
      "loss": 4.2368,
      "step": 386
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00023099999999999998,
      "loss": 4.6233,
      "step": 387
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002316,
      "loss": 4.4809,
      "step": 388
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00023219999999999998,
      "loss": 4.4144,
      "step": 389
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002328,
      "loss": 4.2928,
      "step": 390
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00023339999999999998,
      "loss": 4.4507,
      "step": 391
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000234,
      "loss": 4.3618,
      "step": 392
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00023459999999999998,
      "loss": 4.2873,
      "step": 393
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002352,
      "loss": 4.5993,
      "step": 394
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00023579999999999999,
      "loss": 4.6642,
      "step": 395
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002364,
      "loss": 4.429,
      "step": 396
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000237,
      "loss": 4.5691,
      "step": 397
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002376,
      "loss": 4.5302,
      "step": 398
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002382,
      "loss": 4.8725,
      "step": 399
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002388,
      "loss": 4.4504,
      "step": 400
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002394,
      "loss": 4.6489,
      "step": 401
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00023999999999999998,
      "loss": 4.4011,
      "step": 402
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002406,
      "loss": 4.5411,
      "step": 403
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00024119999999999998,
      "loss": 4.3335,
      "step": 404
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002418,
      "loss": 4.3515,
      "step": 405
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00024239999999999998,
      "loss": 4.5316,
      "step": 406
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.000243,
      "loss": 4.515,
      "step": 407
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00024359999999999999,
      "loss": 4.4707,
      "step": 408
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00024419999999999997,
      "loss": 4.4713,
      "step": 409
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002448,
      "loss": 4.3561,
      "step": 410
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00024539999999999995,
      "loss": 4.5945,
      "step": 411
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00024599999999999996,
      "loss": 4.5222,
      "step": 412
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002466,
      "loss": 4.2503,
      "step": 413
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002472,
      "loss": 4.5353,
      "step": 414
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00024779999999999995,
      "loss": 4.7153,
      "step": 415
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00024839999999999997,
      "loss": 4.3515,
      "step": 416
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000249,
      "loss": 4.607,
      "step": 417
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00024959999999999994,
      "loss": 4.3256,
      "step": 418
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00025019999999999996,
      "loss": 4.5059,
      "step": 419
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00025079999999999997,
      "loss": 4.4982,
      "step": 420
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002514,
      "loss": 4.7228,
      "step": 421
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00025199999999999995,
      "loss": 4.342,
      "step": 422
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00025259999999999996,
      "loss": 4.4941,
      "step": 423
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002532,
      "loss": 4.549,
      "step": 424
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002538,
      "loss": 4.4566,
      "step": 425
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00025439999999999995,
      "loss": 4.4028,
      "step": 426
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00025499999999999996,
      "loss": 4.4576,
      "step": 427
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002556,
      "loss": 4.4446,
      "step": 428
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002562,
      "loss": 4.2655,
      "step": 429
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00025679999999999995,
      "loss": 4.5732,
      "step": 430
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00025739999999999997,
      "loss": 4.4672,
      "step": 431
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000258,
      "loss": 4.721,
      "step": 432
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002586,
      "loss": 4.3734,
      "step": 433
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00025919999999999996,
      "loss": 4.4878,
      "step": 434
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00025979999999999997,
      "loss": 4.6865,
      "step": 435
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002604,
      "loss": 4.3611,
      "step": 436
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000261,
      "loss": 4.4157,
      "step": 437
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00026159999999999996,
      "loss": 4.668,
      "step": 438
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002622,
      "loss": 4.4607,
      "step": 439
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002628,
      "loss": 4.439,
      "step": 440
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00026339999999999995,
      "loss": 4.4888,
      "step": 441
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00026399999999999997,
      "loss": 4.8581,
      "step": 442
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002646,
      "loss": 4.9797,
      "step": 443
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002652,
      "loss": 4.9424,
      "step": 444
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00026579999999999996,
      "loss": 4.6381,
      "step": 445
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00026639999999999997,
      "loss": 4.3897,
      "step": 446
    },
    {
      "epoch": 1.0,
      "step": 446,
      "total_flos": 0.0,
      "train_loss": 4.383164462487259,
      "train_runtime": 5167.2788,
      "train_samples_per_second": 5.523,
      "train_steps_per_second": 0.086
    }
  ],
  "max_steps": 446,
  "num_train_epochs": 1,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}