{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4,
  "eval_steps": 500,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.2774,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1392,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.0406,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.7694,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.6012,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.3276,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.0459,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.9823,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.8292,
      "step": 9
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.86,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7928,
      "step": 11
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7172,
      "step": 12
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7299,
      "step": 13
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.655,
      "step": 14
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6247,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6996,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6586,
      "step": 17
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6789,
      "step": 18
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6364,
      "step": 19
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6086,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5941,
      "step": 21
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6156,
      "step": 22
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5568,
      "step": 23
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5795,
      "step": 24
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5942,
      "step": 25
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5944,
      "step": 26
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5243,
      "step": 27
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5537,
      "step": 28
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5832,
      "step": 29
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5331,
      "step": 30
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.4489,
      "step": 31
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5053,
      "step": 32
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5542,
      "step": 33
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5015,
      "step": 34
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.506,
      "step": 35
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.4779,
      "step": 36
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.4744,
      "step": 37
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.4729,
      "step": 38
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4295,
      "step": 39
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.5112,
      "step": 40
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4288,
      "step": 41
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.4433,
      "step": 42
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.4535,
      "step": 43
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4776,
      "step": 44
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4129,
      "step": 45
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4393,
      "step": 46
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.3426,
      "step": 47
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.3826,
      "step": 48
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.3797,
      "step": 49
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.4392,
      "step": 50
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.9009,
      "step": 51
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.7807,
      "step": 52
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.6645,
      "step": 53
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.6614,
      "step": 54
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.6729,
      "step": 55
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.6466,
      "step": 56
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.6916,
      "step": 57
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.6067,
      "step": 58
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.623,
      "step": 59
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.5987,
      "step": 60
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.6124,
      "step": 61
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.561,
      "step": 62
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.6036,
      "step": 63
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.6038,
      "step": 64
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.5408,
      "step": 65
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.5779,
      "step": 66
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.5617,
      "step": 67
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.608,
      "step": 68
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.5205,
      "step": 69
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.599,
      "step": 70
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.5013,
      "step": 71
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.5672,
      "step": 72
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.5373,
      "step": 73
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.5397,
      "step": 74
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.531,
      "step": 75
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.4584,
      "step": 76
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.4835,
      "step": 77
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.5493,
      "step": 78
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.5379,
      "step": 79
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.5795,
      "step": 80
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.4421,
      "step": 81
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.4947,
      "step": 82
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.4997,
      "step": 83
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.4571,
      "step": 84
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.3947,
      "step": 85
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.4796,
      "step": 86
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.3846,
      "step": 87
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.4606,
      "step": 88
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.3776,
      "step": 89
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.4627,
      "step": 90
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.4095,
      "step": 91
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.4047,
      "step": 92
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.3684,
      "step": 93
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.4086,
      "step": 94
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.358,
      "step": 95
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.3824,
      "step": 96
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.3751,
      "step": 97
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.3897,
      "step": 98
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.349,
      "step": 99
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.4674,
      "step": 100
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.7479,
      "step": 101
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.7174,
      "step": 102
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.7081,
      "step": 103
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.6064,
      "step": 104
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.6217,
      "step": 105
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.5967,
      "step": 106
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.5808,
      "step": 107
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.5926,
      "step": 108
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.5861,
      "step": 109
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.5996,
      "step": 110
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.5933,
      "step": 111
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.5812,
      "step": 112
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.5401,
      "step": 113
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.5436,
      "step": 114
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.5415,
      "step": 115
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.5266,
      "step": 116
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.5048,
      "step": 117
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.5286,
      "step": 118
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.5292,
      "step": 119
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.594,
      "step": 120
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.5481,
      "step": 121
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.493,
      "step": 122
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.4596,
      "step": 123
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.5249,
      "step": 124
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.5121,
      "step": 125
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.4943,
      "step": 126
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.4765,
      "step": 127
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.4952,
      "step": 128
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.4852,
      "step": 129
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.5511,
      "step": 130
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.4721,
      "step": 131
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.4612,
      "step": 132
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.4672,
      "step": 133
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.4875,
      "step": 134
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.3908,
      "step": 135
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.4813,
      "step": 136
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.4423,
      "step": 137
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.4593,
      "step": 138
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.4399,
      "step": 139
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.3959,
      "step": 140
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.4063,
      "step": 141
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.3643,
      "step": 142
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.3982,
      "step": 143
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.355,
      "step": 144
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.3645,
      "step": 145
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.3516,
      "step": 146
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.3945,
      "step": 147
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.3166,
      "step": 148
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.3054,
      "step": 149
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.3719,
      "step": 150
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.7191,
      "step": 151
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.6457,
      "step": 152
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.7385,
      "step": 153
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.5479,
      "step": 154
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.6008,
      "step": 155
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.669,
      "step": 156
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.5624,
      "step": 157
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.669,
      "step": 158
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.6167,
      "step": 159
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.5228,
      "step": 160
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.5331,
      "step": 161
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.5176,
      "step": 162
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.5237,
      "step": 163
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.5622,
      "step": 164
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.5641,
      "step": 165
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.5955,
      "step": 166
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.5265,
      "step": 167
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.5471,
      "step": 168
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.5106,
      "step": 169
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.54,
      "step": 170
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.5257,
      "step": 171
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.4932,
      "step": 172
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.5014,
      "step": 173
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.5609,
      "step": 174
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.4734,
      "step": 175
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.4856,
      "step": 176
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.4713,
      "step": 177
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.5715,
      "step": 178
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.4694,
      "step": 179
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.5254,
      "step": 180
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.4411,
      "step": 181
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 0.4509,
      "step": 182
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 0.4022,
      "step": 183
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.4521,
      "step": 184
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.4068,
      "step": 185
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.4607,
      "step": 186
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.3928,
      "step": 187
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.3734,
      "step": 188
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.3981,
      "step": 189
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.3618,
      "step": 190
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.3835,
      "step": 191
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.3484,
      "step": 192
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.3711,
      "step": 193
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.3687,
      "step": 194
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.3464,
      "step": 195
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.3862,
      "step": 196
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.3307,
      "step": 197
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.3385,
      "step": 198
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.3804,
      "step": 199
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.3577,
      "step": 200
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.772,
      "step": 201
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.6349,
      "step": 202
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.6594,
      "step": 203
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.6314,
      "step": 204
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.5817,
      "step": 205
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.5818,
      "step": 206
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.5681,
      "step": 207
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.5914,
      "step": 208
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.5819,
      "step": 209
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.5599,
      "step": 210
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.5197,
      "step": 211
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.5391,
      "step": 212
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.5636,
      "step": 213
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.5104,
      "step": 214
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.4798,
      "step": 215
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.5137,
      "step": 216
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.5574,
      "step": 217
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.525,
      "step": 218
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.4651,
      "step": 219
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.5069,
      "step": 220
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.4966,
      "step": 221
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.5619,
      "step": 222
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.5081,
      "step": 223
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.5203,
      "step": 224
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.4565,
      "step": 225
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.4283,
      "step": 226
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.4522,
      "step": 227
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.4712,
      "step": 228
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.5018,
      "step": 229
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.4691,
      "step": 230
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.4537,
      "step": 231
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.4482,
      "step": 232
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.4369,
      "step": 233
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.4772,
      "step": 234
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.4546,
      "step": 235
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.4321,
      "step": 236
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 0.3777,
      "step": 237
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 0.4099,
      "step": 238
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.3694,
      "step": 239
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.3902,
      "step": 240
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.3989,
      "step": 241
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 0.4031,
      "step": 242
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 0.4104,
      "step": 243
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.3533,
      "step": 244
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.364,
      "step": 245
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.3696,
      "step": 246
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.3252,
      "step": 247
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.3523,
      "step": 248
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.3395,
      "step": 249
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.3503,
      "step": 250
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.6092,
      "step": 251
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.5481,
      "step": 252
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.5902,
      "step": 253
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.4603,
      "step": 254
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.5344,
      "step": 255
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.5136,
      "step": 256
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.5304,
      "step": 257
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.4625,
      "step": 258
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.4841,
      "step": 259
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.4548,
      "step": 260
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.4686,
      "step": 261
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 0.4717,
      "step": 262
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 0.4775,
      "step": 263
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.503,
      "step": 264
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.4712,
      "step": 265
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.4782,
      "step": 266
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.4649,
      "step": 267
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.4758,
      "step": 268
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.4192,
      "step": 269
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.4511,
      "step": 270
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.4572,
      "step": 271
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.4277,
      "step": 272
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.4366,
      "step": 273
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.403,
      "step": 274
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.4161,
      "step": 275
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.4239,
      "step": 276
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.4541,
      "step": 277
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.3711,
      "step": 278
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.4385,
      "step": 279
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.4188,
      "step": 280
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.4628,
      "step": 281
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.3999,
      "step": 282
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.368,
      "step": 283
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.393,
      "step": 284
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.3992,
      "step": 285
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.334,
      "step": 286
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.3043,
      "step": 287
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.3939,
      "step": 288
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.3215,
      "step": 289
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.3277,
      "step": 290
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.3899,
      "step": 291
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.3257,
      "step": 292
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.2819,
      "step": 293
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.342,
      "step": 294
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.3677,
      "step": 295
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.3077,
      "step": 296
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 0.3102,
      "step": 297
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 0.3398,
      "step": 298
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.2884,
      "step": 299
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.3419,
      "step": 300
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.6055,
      "step": 301
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.6022,
      "step": 302
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.5849,
      "step": 303
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.4591,
      "step": 304
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.5527,
      "step": 305
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.4893,
      "step": 306
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.4901,
      "step": 307
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.5406,
      "step": 308
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.5152,
      "step": 309
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.5013,
      "step": 310
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.5074,
      "step": 311
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.4718,
      "step": 312
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.4602,
      "step": 313
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.4424,
      "step": 314
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.4844,
      "step": 315
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.5499,
      "step": 316
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.5265,
      "step": 317
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.4419,
      "step": 318
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 0.4753,
      "step": 319
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 0.493,
      "step": 320
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 0.4885,
      "step": 321
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 0.464,
      "step": 322
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 0.4767,
      "step": 323
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.4766,
      "step": 324
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.4449,
      "step": 325
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.3912,
      "step": 326
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 0.4508,
      "step": 327
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 0.4124,
      "step": 328
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.4305,
      "step": 329
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.4207,
      "step": 330
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.3785,
      "step": 331
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.428,
      "step": 332
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.3683,
      "step": 333
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 0.3742,
      "step": 334
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 0.3734,
      "step": 335
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 0.3748,
      "step": 336
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 0.4496,
      "step": 337
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 0.3368,
      "step": 338
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 0.3801,
      "step": 339
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 0.3133,
      "step": 340
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 0.3159,
      "step": 341
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 0.3227,
      "step": 342
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 0.3268,
      "step": 343
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.402,
      "step": 344
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.327,
      "step": 345
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.2898,
      "step": 346
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 0.3437,
      "step": 347
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 0.3099,
      "step": 348
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 0.2742,
      "step": 349
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 0.3122,
      "step": 350
    }
  ],
  "logging_steps": 1,
  "max_steps": 500,
  "num_train_epochs": 2,
  "save_steps": 25,
  "total_flos": 4.187771329769472e+16,
  "trial_name": null,
  "trial_params": null
}