{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 250,
  "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": 2.1262,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.0795,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.8381,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.6144,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.4531,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.0781,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.9191,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.8296,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.8927,
      "step": 9
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7623,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7604,
      "step": 11
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7753,
      "step": 12
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7267,
      "step": 13
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7733,
      "step": 14
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7031,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.635,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7216,
      "step": 17
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6733,
      "step": 18
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.679,
      "step": 19
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6507,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6304,
      "step": 21
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6275,
      "step": 22
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6455,
      "step": 23
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7032,
      "step": 24
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5893,
      "step": 25
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6587,
      "step": 26
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.6113,
      "step": 27
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5731,
      "step": 28
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5886,
      "step": 29
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5692,
      "step": 30
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5662,
      "step": 31
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5367,
      "step": 32
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5187,
      "step": 33
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.548,
      "step": 34
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.478,
      "step": 35
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5043,
      "step": 36
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5444,
      "step": 37
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5076,
      "step": 38
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.522,
      "step": 39
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4969,
      "step": 40
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.5652,
      "step": 41
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.4171,
      "step": 42
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.4089,
      "step": 43
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4814,
      "step": 44
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4041,
      "step": 45
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.3966,
      "step": 46
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.4862,
      "step": 47
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.3708,
      "step": 48
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.3644,
      "step": 49
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.5372,
      "step": 50
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.8328,
      "step": 51
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.8185,
      "step": 52
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.8372,
      "step": 53
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.6878,
      "step": 54
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.755,
      "step": 55
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.718,
      "step": 56
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.6373,
      "step": 57
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.7161,
      "step": 58
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.6732,
      "step": 59
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.7193,
      "step": 60
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.6438,
      "step": 61
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.6976,
      "step": 62
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.7565,
      "step": 63
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.6425,
      "step": 64
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.7157,
      "step": 65
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.6467,
      "step": 66
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.6041,
      "step": 67
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.6636,
      "step": 68
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.6813,
      "step": 69
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.6519,
      "step": 70
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.5999,
      "step": 71
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.5278,
      "step": 72
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.5462,
      "step": 73
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.5401,
      "step": 74
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.5947,
      "step": 75
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.5637,
      "step": 76
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.6006,
      "step": 77
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.506,
      "step": 78
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.504,
      "step": 79
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.4854,
      "step": 80
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.5162,
      "step": 81
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.5698,
      "step": 82
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.5169,
      "step": 83
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.4287,
      "step": 84
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.4389,
      "step": 85
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.5316,
      "step": 86
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.4874,
      "step": 87
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.4707,
      "step": 88
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.4227,
      "step": 89
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.4631,
      "step": 90
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.3901,
      "step": 91
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.4807,
      "step": 92
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.4907,
      "step": 93
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.4152,
      "step": 94
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.4146,
      "step": 95
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.4564,
      "step": 96
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.448,
      "step": 97
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.3938,
      "step": 98
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.3665,
      "step": 99
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.4806,
      "step": 100
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.7619,
      "step": 101
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.8268,
      "step": 102
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.7547,
      "step": 103
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.7147,
      "step": 104
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.7702,
      "step": 105
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.6515,
      "step": 106
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.6289,
      "step": 107
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.6513,
      "step": 108
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.6657,
      "step": 109
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.5834,
      "step": 110
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.6159,
      "step": 111
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.6479,
      "step": 112
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.6606,
      "step": 113
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.6919,
      "step": 114
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.6257,
      "step": 115
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.5836,
      "step": 116
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.5772,
      "step": 117
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.5966,
      "step": 118
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.6732,
      "step": 119
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.5193,
      "step": 120
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.5443,
      "step": 121
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.5536,
      "step": 122
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.5855,
      "step": 123
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.5514,
      "step": 124
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.5952,
      "step": 125
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.623,
      "step": 126
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.5513,
      "step": 127
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.5448,
      "step": 128
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.5296,
      "step": 129
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.4895,
      "step": 130
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.549,
      "step": 131
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.4949,
      "step": 132
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.5025,
      "step": 133
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.4735,
      "step": 134
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.4664,
      "step": 135
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.5314,
      "step": 136
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.5509,
      "step": 137
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.4169,
      "step": 138
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.4409,
      "step": 139
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.4957,
      "step": 140
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.3844,
      "step": 141
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.4247,
      "step": 142
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.4182,
      "step": 143
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.3953,
      "step": 144
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.5123,
      "step": 145
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.369,
      "step": 146
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.3902,
      "step": 147
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.3843,
      "step": 148
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.4022,
      "step": 149
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.4401,
      "step": 150
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.7516,
      "step": 151
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.7478,
      "step": 152
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.7672,
      "step": 153
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.6856,
      "step": 154
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.7185,
      "step": 155
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.6214,
      "step": 156
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.6161,
      "step": 157
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.6837,
      "step": 158
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.6142,
      "step": 159
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.6948,
      "step": 160
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.6003,
      "step": 161
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.6179,
      "step": 162
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.6373,
      "step": 163
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.5763,
      "step": 164
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.6553,
      "step": 165
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.6018,
      "step": 166
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.5537,
      "step": 167
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.5703,
      "step": 168
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.5142,
      "step": 169
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.5437,
      "step": 170
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.6246,
      "step": 171
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.5837,
      "step": 172
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.5594,
      "step": 173
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.4791,
      "step": 174
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.5009,
      "step": 175
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.5097,
      "step": 176
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.5728,
      "step": 177
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.5391,
      "step": 178
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.5347,
      "step": 179
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.4641,
      "step": 180
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.4879,
      "step": 181
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 0.465,
      "step": 182
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 0.458,
      "step": 183
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.4863,
      "step": 184
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.4928,
      "step": 185
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.3868,
      "step": 186
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.4672,
      "step": 187
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.421,
      "step": 188
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.425,
      "step": 189
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.3822,
      "step": 190
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.4326,
      "step": 191
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.3932,
      "step": 192
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.3672,
      "step": 193
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.3669,
      "step": 194
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.3904,
      "step": 195
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.3255,
      "step": 196
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.3567,
      "step": 197
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.3808,
      "step": 198
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.417,
      "step": 199
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.4644,
      "step": 200
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.6799,
      "step": 201
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.7253,
      "step": 202
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.8481,
      "step": 203
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.662,
      "step": 204
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.6507,
      "step": 205
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.5734,
      "step": 206
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.6026,
      "step": 207
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.7017,
      "step": 208
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.6172,
      "step": 209
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.5782,
      "step": 210
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.5805,
      "step": 211
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.6031,
      "step": 212
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.5795,
      "step": 213
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.6324,
      "step": 214
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.5426,
      "step": 215
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.5527,
      "step": 216
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.6277,
      "step": 217
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.5427,
      "step": 218
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.5526,
      "step": 219
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.5193,
      "step": 220
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.5112,
      "step": 221
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.5111,
      "step": 222
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.5119,
      "step": 223
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.5078,
      "step": 224
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.4422,
      "step": 225
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.5137,
      "step": 226
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.4991,
      "step": 227
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.4743,
      "step": 228
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.5094,
      "step": 229
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.4255,
      "step": 230
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.5178,
      "step": 231
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.45,
      "step": 232
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.4507,
      "step": 233
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.4985,
      "step": 234
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.4585,
      "step": 235
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.4703,
      "step": 236
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 0.4126,
      "step": 237
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 0.4401,
      "step": 238
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.3744,
      "step": 239
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.4532,
      "step": 240
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.4043,
      "step": 241
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 0.3634,
      "step": 242
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 0.4066,
      "step": 243
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.4081,
      "step": 244
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.4268,
      "step": 245
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.3535,
      "step": 246
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.34,
      "step": 247
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.3733,
      "step": 248
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.41,
      "step": 249
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.3494,
      "step": 250
    }
  ],
  "logging_steps": 1,
  "max_steps": 250,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 1.4689489038114816e+16,
  "trial_name": null,
  "trial_params": null
}