{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8,
  "eval_steps": 500,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.3479,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.1675,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.882,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.4621,
      "step": 4
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.168,
      "step": 5
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.935,
      "step": 6
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.8284,
      "step": 7
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.8028,
      "step": 8
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7336,
      "step": 9
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.7472,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6652,
      "step": 11
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6465,
      "step": 12
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7059,
      "step": 13
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.6315,
      "step": 14
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6406,
      "step": 15
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5577,
      "step": 16
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6208,
      "step": 17
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5592,
      "step": 18
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5655,
      "step": 19
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.5357,
      "step": 20
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5189,
      "step": 21
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.48,
      "step": 22
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4946,
      "step": 23
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5393,
      "step": 24
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.4939,
      "step": 25
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.4876,
      "step": 26
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.4655,
      "step": 27
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.4474,
      "step": 28
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.4279,
      "step": 29
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.4244,
      "step": 30
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.4293,
      "step": 31
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.8789,
      "step": 32
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.7369,
      "step": 33
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.7268,
      "step": 34
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.6907,
      "step": 35
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.6678,
      "step": 36
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.67,
      "step": 37
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.6254,
      "step": 38
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.6333,
      "step": 39
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.5874,
      "step": 40
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.5477,
      "step": 41
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.5809,
      "step": 42
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.5627,
      "step": 43
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.597,
      "step": 44
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.6082,
      "step": 45
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.5083,
      "step": 46
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.5131,
      "step": 47
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.5055,
      "step": 48
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.509,
      "step": 49
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.4697,
      "step": 50
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.5124,
      "step": 51
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.4229,
      "step": 52
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.441,
      "step": 53
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.4336,
      "step": 54
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.4414,
      "step": 55
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.4216,
      "step": 56
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.4271,
      "step": 57
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.4038,
      "step": 58
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.3832,
      "step": 59
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.3842,
      "step": 60
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.4154,
      "step": 61
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.4343,
      "step": 62
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.7601,
      "step": 63
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.699,
      "step": 64
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.6516,
      "step": 65
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.5918,
      "step": 66
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.6279,
      "step": 67
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.5807,
      "step": 68
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.626,
      "step": 69
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.5832,
      "step": 70
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.5663,
      "step": 71
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.5542,
      "step": 72
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.5405,
      "step": 73
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.5333,
      "step": 74
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.5811,
      "step": 75
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.5042,
      "step": 76
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.4639,
      "step": 77
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.489,
      "step": 78
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.4993,
      "step": 79
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.5359,
      "step": 80
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.4741,
      "step": 81
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.4857,
      "step": 82
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.4896,
      "step": 83
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.4386,
      "step": 84
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.4184,
      "step": 85
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.4119,
      "step": 86
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.4549,
      "step": 87
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.4056,
      "step": 88
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.3885,
      "step": 89
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.3585,
      "step": 90
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 0.4061,
      "step": 91
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.3935,
      "step": 92
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.3814,
      "step": 93
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.7408,
      "step": 94
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.7369,
      "step": 95
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.6254,
      "step": 96
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.6206,
      "step": 97
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.5881,
      "step": 98
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.6188,
      "step": 99
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.5896,
      "step": 100
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.5818,
      "step": 101
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.5191,
      "step": 102
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.5396,
      "step": 103
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.5659,
      "step": 104
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.52,
      "step": 105
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.5307,
      "step": 106
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.4462,
      "step": 107
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.5245,
      "step": 108
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.5032,
      "step": 109
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.5449,
      "step": 110
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.472,
      "step": 111
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.4488,
      "step": 112
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.4247,
      "step": 113
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.4124,
      "step": 114
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.4248,
      "step": 115
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.4294,
      "step": 116
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.3919,
      "step": 117
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.4262,
      "step": 118
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 0.3683,
      "step": 119
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.3872,
      "step": 120
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 0.3514,
      "step": 121
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.3697,
      "step": 122
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.3396,
      "step": 123
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.3739,
      "step": 124
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.4894,
      "step": 125
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.6574,
      "step": 126
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.6102,
      "step": 127
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.5459,
      "step": 128
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.5237,
      "step": 129
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.5041,
      "step": 130
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 0.5344,
      "step": 131
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.5144,
      "step": 132
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.461,
      "step": 133
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.4629,
      "step": 134
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.4783,
      "step": 135
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.4263,
      "step": 136
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.4718,
      "step": 137
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.4671,
      "step": 138
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.4783,
      "step": 139
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.4188,
      "step": 140
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.4106,
      "step": 141
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.4498,
      "step": 142
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.4254,
      "step": 143
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.4038,
      "step": 144
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.3871,
      "step": 145
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.4085,
      "step": 146
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.3769,
      "step": 147
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.4008,
      "step": 148
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 0.3574,
      "step": 149
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.3183,
      "step": 150
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.3193,
      "step": 151
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.3076,
      "step": 152
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.3485,
      "step": 153
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.3184,
      "step": 154
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.3462,
      "step": 155
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.3259,
      "step": 156
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.6556,
      "step": 157
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.6423,
      "step": 158
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.5609,
      "step": 159
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 0.5136,
      "step": 160
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 0.5312,
      "step": 161
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.5117,
      "step": 162
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.4626,
      "step": 163
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 0.5142,
      "step": 164
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.4448,
      "step": 165
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.4295,
      "step": 166
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 0.4669,
      "step": 167
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 0.4327,
      "step": 168
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 0.4575,
      "step": 169
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 0.4462,
      "step": 170
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 0.4107,
      "step": 171
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.405,
      "step": 172
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.4124,
      "step": 173
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 0.3947,
      "step": 174
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 0.3692,
      "step": 175
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 0.3934,
      "step": 176
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 0.3419,
      "step": 177
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 0.3716,
      "step": 178
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 0.3332,
      "step": 179
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 0.3787,
      "step": 180
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 0.3554,
      "step": 181
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 0.3415,
      "step": 182
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 0.3248,
      "step": 183
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 0.3096,
      "step": 184
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 0.3194,
      "step": 185
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 0.324,
      "step": 186
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 0.3104,
      "step": 187
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 0.6566,
      "step": 188
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 0.5971,
      "step": 189
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 0.5316,
      "step": 190
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 0.5152,
      "step": 191
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 0.5407,
      "step": 192
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 0.4706,
      "step": 193
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 0.4819,
      "step": 194
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 0.4942,
      "step": 195
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.456,
      "step": 196
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 0.4398,
      "step": 197
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 0.4454,
      "step": 198
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 0.4404,
      "step": 199
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 0.4379,
      "step": 200
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 0.412,
      "step": 201
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.4059,
      "step": 202
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.4189,
      "step": 203
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 0.4127,
      "step": 204
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 0.4131,
      "step": 205
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 0.3867,
      "step": 206
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 0.3402,
      "step": 207
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 0.3755,
      "step": 208
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 0.3904,
      "step": 209
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 0.3413,
      "step": 210
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 0.3568,
      "step": 211
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 0.3333,
      "step": 212
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 0.3481,
      "step": 213
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 0.3571,
      "step": 214
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 0.31,
      "step": 215
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 0.3437,
      "step": 216
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 0.3051,
      "step": 217
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 0.3035,
      "step": 218
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 0.5871,
      "step": 219
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 0.5218,
      "step": 220
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 0.5163,
      "step": 221
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 0.5002,
      "step": 222
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 0.4768,
      "step": 223
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 0.5197,
      "step": 224
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 0.4529,
      "step": 225
    }
  ],
  "logging_steps": 1,
  "max_steps": 250,
  "num_train_epochs": 2,
  "save_steps": 25,
  "total_flos": 2.907887080911667e+16,
  "trial_name": null,
  "trial_params": null
}