{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 1.7148,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 1.9328,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 1.8042,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.6455,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.7203,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.6685,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.4244,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 2.1653,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.9989,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 2.2052,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.672,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.8851,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.6737,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.4328,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.6895,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 2.1673,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.223,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.4876,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.3852,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.8297,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.6105,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.579,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.4408,
      "step": 23
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 2.2866,
      "step": 24
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.6894,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.7306,
      "step": 26
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.6463,
      "step": 27
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.8447,
      "step": 28
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.4352,
      "step": 29
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.8621,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.5328,
      "step": 31
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.6655,
      "step": 32
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 2.0306,
      "step": 33
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.8738,
      "step": 34
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 1.767,
      "step": 35
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 1.8353,
      "step": 36
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 1.6261,
      "step": 37
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 2.1432,
      "step": 38
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 1.8847,
      "step": 39
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 1.4152,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 1.8767,
      "step": 41
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 1.81,
      "step": 42
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 2.0254,
      "step": 43
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 1.7848,
      "step": 44
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 2.2568,
      "step": 45
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 1.973,
      "step": 46
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.4736,
      "step": 47
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.705,
      "step": 48
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.6735,
      "step": 49
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.6599,
      "step": 50
    },
    {
      "epoch": 0.08,
      "eval_loss": 1.7222049236297607,
      "eval_runtime": 72.4104,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.691,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.507,
      "step": 51
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.8072,
      "step": 52
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 2.0659,
      "step": 53
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 1.4914,
      "step": 54
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 1.5957,
      "step": 55
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 1.6989,
      "step": 56
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 1.8415,
      "step": 57
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 1.4516,
      "step": 58
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 1.6054,
      "step": 59
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 1.5,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 1.6041,
      "step": 61
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 1.5754,
      "step": 62
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 1.7746,
      "step": 63
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 1.6594,
      "step": 64
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 1.9716,
      "step": 65
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 1.6362,
      "step": 66
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 1.4446,
      "step": 67
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 1.4261,
      "step": 68
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 1.5764,
      "step": 69
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 1.6063,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 1.8776,
      "step": 71
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 1.3768,
      "step": 72
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 1.9382,
      "step": 73
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 2.2803,
      "step": 74
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 2.0566,
      "step": 75
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 1.7314,
      "step": 76
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 1.5839,
      "step": 77
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 1.6322,
      "step": 78
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 1.8401,
      "step": 79
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 2.0293,
      "step": 80
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 1.6553,
      "step": 81
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 1.8479,
      "step": 82
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 1.7698,
      "step": 83
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 1.9446,
      "step": 84
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 1.6181,
      "step": 85
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 1.5447,
      "step": 86
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 1.7948,
      "step": 87
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 1.3113,
      "step": 88
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 1.4759,
      "step": 89
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 1.6184,
      "step": 90
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 1.6391,
      "step": 91
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 1.7226,
      "step": 92
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 1.3648,
      "step": 93
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 2.4527,
      "step": 94
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 1.6325,
      "step": 95
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 2.0111,
      "step": 96
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 1.6688,
      "step": 97
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 1.6873,
      "step": 98
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 2.1846,
      "step": 99
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 1.5952,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_loss": 1.7072890996932983,
      "eval_runtime": 72.4002,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.691,
      "step": 100
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 1.7563,
      "step": 101
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 1.5295,
      "step": 102
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 1.6132,
      "step": 103
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.5136,
      "step": 104
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 2.0012,
      "step": 105
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.868,
      "step": 106
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.6686,
      "step": 107
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.8268,
      "step": 108
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.492,
      "step": 109
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 1.751,
      "step": 110
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 1.3865,
      "step": 111
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 2.1505,
      "step": 112
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 1.3105,
      "step": 113
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 1.7071,
      "step": 114
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 1.819,
      "step": 115
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 2.1791,
      "step": 116
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 1.5499,
      "step": 117
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 1.9639,
      "step": 118
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 1.5225,
      "step": 119
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 1.6377,
      "step": 120
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 1.664,
      "step": 121
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 1.5906,
      "step": 122
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 1.4926,
      "step": 123
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 2.1501,
      "step": 124
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 1.8551,
      "step": 125
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 1.9488,
      "step": 126
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 2.1481,
      "step": 127
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 2.0448,
      "step": 128
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 1.5366,
      "step": 129
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 2.1715,
      "step": 130
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 1.8581,
      "step": 131
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 1.3447,
      "step": 132
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 1.9304,
      "step": 133
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 1.6903,
      "step": 134
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 1.8249,
      "step": 135
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 1.5649,
      "step": 136
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 1.8228,
      "step": 137
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 1.4223,
      "step": 138
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 1.4123,
      "step": 139
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 1.3626,
      "step": 140
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 1.7496,
      "step": 141
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 1.807,
      "step": 142
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 1.425,
      "step": 143
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 1.6768,
      "step": 144
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 2.0477,
      "step": 145
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 2.0605,
      "step": 146
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 1.8897,
      "step": 147
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 1.7963,
      "step": 148
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 1.5537,
      "step": 149
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 1.8135,
      "step": 150
    },
    {
      "epoch": 0.24,
      "eval_loss": 1.700058102607727,
      "eval_runtime": 72.4238,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.69,
      "step": 150
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 1.8727,
      "step": 151
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 1.7317,
      "step": 152
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 1.825,
      "step": 153
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.4779,
      "step": 154
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.72,
      "step": 155
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.7643,
      "step": 156
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.522,
      "step": 157
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.972,
      "step": 158
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.6848,
      "step": 159
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.8364,
      "step": 160
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.5812,
      "step": 161
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.6297,
      "step": 162
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.8459,
      "step": 163
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.4169,
      "step": 164
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.6954,
      "step": 165
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 1.7117,
      "step": 166
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 1.6202,
      "step": 167
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 1.4712,
      "step": 168
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 1.5926,
      "step": 169
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 2.1698,
      "step": 170
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 1.3223,
      "step": 171
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 1.5033,
      "step": 172
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 1.4251,
      "step": 173
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 1.5875,
      "step": 174
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 1.6676,
      "step": 175
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 1.5111,
      "step": 176
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 2.0565,
      "step": 177
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 1.537,
      "step": 178
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 1.9023,
      "step": 179
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 1.1597,
      "step": 180
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 2.065,
      "step": 181
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 1.4474,
      "step": 182
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 1.7032,
      "step": 183
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 1.6556,
      "step": 184
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 1.6716,
      "step": 185
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 1.8552,
      "step": 186
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 1.7467,
      "step": 187
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 2.0586,
      "step": 188
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 2.108,
      "step": 189
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 2.2611,
      "step": 190
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 1.2171,
      "step": 191
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 2.0427,
      "step": 192
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 1.7751,
      "step": 193
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 1.7191,
      "step": 194
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 1.4726,
      "step": 195
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 1.2757,
      "step": 196
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.3769,
      "step": 197
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.5463,
      "step": 198
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.9345,
      "step": 199
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.5291,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_loss": 1.6957875490188599,
      "eval_runtime": 72.5157,
      "eval_samples_per_second": 2.758,
      "eval_steps_per_second": 0.69,
      "step": 200
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.4821,
      "step": 201
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.7784,
      "step": 202
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.9326,
      "step": 203
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 1.7614,
      "step": 204
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 1.299,
      "step": 205
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 1.5341,
      "step": 206
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 1.8423,
      "step": 207
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 1.8774,
      "step": 208
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 1.9241,
      "step": 209
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001,
      "loss": 1.49,
      "step": 210
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001,
      "loss": 1.6692,
      "step": 211
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001,
      "loss": 1.4803,
      "step": 212
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001,
      "loss": 1.6771,
      "step": 213
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001,
      "loss": 1.4993,
      "step": 214
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001,
      "loss": 1.4852,
      "step": 215
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 1.7914,
      "step": 216
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 1.4072,
      "step": 217
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 2.1311,
      "step": 218
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 1.831,
      "step": 219
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 1.2721,
      "step": 220
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 1.9589,
      "step": 221
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 2.0124,
      "step": 222
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 1.4198,
      "step": 223
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 1.5789,
      "step": 224
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 1.5954,
      "step": 225
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 1.4544,
      "step": 226
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 1.5659,
      "step": 227
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 1.692,
      "step": 228
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 1.5666,
      "step": 229
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 1.8224,
      "step": 230
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 2.0304,
      "step": 231
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 1.6519,
      "step": 232
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 1.308,
      "step": 233
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 1.5397,
      "step": 234
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001,
      "loss": 2.1097,
      "step": 235
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001,
      "loss": 1.4248,
      "step": 236
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001,
      "loss": 2.1366,
      "step": 237
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001,
      "loss": 1.7869,
      "step": 238
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001,
      "loss": 1.9793,
      "step": 239
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001,
      "loss": 1.4827,
      "step": 240
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.6394,
      "step": 241
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.5626,
      "step": 242
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.5402,
      "step": 243
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.9889,
      "step": 244
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.5079,
      "step": 245
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.3189,
      "step": 246
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 1.7653,
      "step": 247
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 1.5157,
      "step": 248
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 1.768,
      "step": 249
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 1.845,
      "step": 250
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.6924077272415161,
      "eval_runtime": 72.2416,
      "eval_samples_per_second": 2.768,
      "eval_steps_per_second": 0.692,
      "step": 250
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 1.7089,
      "step": 251
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 1.3846,
      "step": 252
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 1.5088,
      "step": 253
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 1.3051,
      "step": 254
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 1.7315,
      "step": 255
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 2.1085,
      "step": 256
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 1.8662,
      "step": 257
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 1.343,
      "step": 258
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 2.1685,
      "step": 259
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 1.5185,
      "step": 260
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 1.5658,
      "step": 261
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 2.3013,
      "step": 262
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 1.6212,
      "step": 263
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 1.9284,
      "step": 264
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 1.9426,
      "step": 265
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001,
      "loss": 1.9887,
      "step": 266
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001,
      "loss": 1.5607,
      "step": 267
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001,
      "loss": 2.4152,
      "step": 268
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001,
      "loss": 1.7911,
      "step": 269
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001,
      "loss": 1.8393,
      "step": 270
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001,
      "loss": 1.4956,
      "step": 271
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 1.6191,
      "step": 272
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 1.7058,
      "step": 273
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 1.8404,
      "step": 274
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 1.8271,
      "step": 275
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 1.552,
      "step": 276
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 1.9239,
      "step": 277
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 1.5686,
      "step": 278
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 2.0283,
      "step": 279
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 1.6978,
      "step": 280
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 1.6703,
      "step": 281
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 1.6758,
      "step": 282
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 1.2017,
      "step": 283
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 1.5667,
      "step": 284
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 1.6953,
      "step": 285
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 1.9168,
      "step": 286
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 1.6549,
      "step": 287
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 1.5266,
      "step": 288
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 1.2701,
      "step": 289
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 1.5097,
      "step": 290
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 1.594,
      "step": 291
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 1.8082,
      "step": 292
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 1.7316,
      "step": 293
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 1.7626,
      "step": 294
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 1.6767,
      "step": 295
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 1.7293,
      "step": 296
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 1.89,
      "step": 297
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 1.3799,
      "step": 298
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 1.8499,
      "step": 299
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 1.5534,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_loss": 1.6901886463165283,
      "eval_runtime": 72.426,
      "eval_samples_per_second": 2.761,
      "eval_steps_per_second": 0.69,
      "step": 300
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 1.7924,
      "step": 301
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 1.7642,
      "step": 302
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 1.8088,
      "step": 303
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 1.9209,
      "step": 304
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 1.3394,
      "step": 305
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 1.5837,
      "step": 306
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 1.4254,
      "step": 307
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 1.8479,
      "step": 308
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 1.6706,
      "step": 309
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 1.4787,
      "step": 310
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 2.4559,
      "step": 311
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 1.9913,
      "step": 312
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 1.5819,
      "step": 313
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 1.5148,
      "step": 314
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 1.5434,
      "step": 315
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 1.6875,
      "step": 316
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 1.7861,
      "step": 317
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 1.6002,
      "step": 318
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 1.6026,
      "step": 319
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 1.6075,
      "step": 320
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 1.9892,
      "step": 321
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.5185,
      "step": 322
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.2678,
      "step": 323
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.9131,
      "step": 324
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.713,
      "step": 325
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.9007,
      "step": 326
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.7905,
      "step": 327
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.3132,
      "step": 328
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 1.9024,
      "step": 329
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 2.2366,
      "step": 330
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 1.5218,
      "step": 331
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 1.3332,
      "step": 332
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 2.0362,
      "step": 333
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 1.9536,
      "step": 334
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 1.3341,
      "step": 335
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 2.16,
      "step": 336
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 1.7826,
      "step": 337
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 1.7219,
      "step": 338
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 1.7305,
      "step": 339
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 1.5233,
      "step": 340
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 1.5466,
      "step": 341
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 1.3515,
      "step": 342
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 1.5876,
      "step": 343
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 2.3651,
      "step": 344
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 1.9231,
      "step": 345
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 1.6658,
      "step": 346
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.8819,
      "step": 347
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.5112,
      "step": 348
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.472,
      "step": 349
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.8965,
      "step": 350
    },
    {
      "epoch": 0.56,
      "eval_loss": 1.687639594078064,
      "eval_runtime": 72.2618,
      "eval_samples_per_second": 2.768,
      "eval_steps_per_second": 0.692,
      "step": 350
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.8201,
      "step": 351
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.6049,
      "step": 352
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.7418,
      "step": 353
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 1.3601,
      "step": 354
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 1.5566,
      "step": 355
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 1.7604,
      "step": 356
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 1.4752,
      "step": 357
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 1.4282,
      "step": 358
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 2.0033,
      "step": 359
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001,
      "loss": 1.5684,
      "step": 360
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001,
      "loss": 1.4388,
      "step": 361
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001,
      "loss": 1.9342,
      "step": 362
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001,
      "loss": 1.7494,
      "step": 363
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001,
      "loss": 1.6427,
      "step": 364
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001,
      "loss": 1.7472,
      "step": 365
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.6507,
      "step": 366
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.7274,
      "step": 367
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.5249,
      "step": 368
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.8284,
      "step": 369
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.6145,
      "step": 370
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.3435,
      "step": 371
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 1.5641,
      "step": 372
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 1.9199,
      "step": 373
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 1.658,
      "step": 374
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 1.506,
      "step": 375
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 1.4865,
      "step": 376
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 1.7912,
      "step": 377
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 1.5608,
      "step": 378
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 1.472,
      "step": 379
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 1.6645,
      "step": 380
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 1.9596,
      "step": 381
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 1.5604,
      "step": 382
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 1.7518,
      "step": 383
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 1.8445,
      "step": 384
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 1.8057,
      "step": 385
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 1.3949,
      "step": 386
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 1.5996,
      "step": 387
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 1.4949,
      "step": 388
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 1.4823,
      "step": 389
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 2.0068,
      "step": 390
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 1.5852,
      "step": 391
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 1.528,
      "step": 392
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 1.6447,
      "step": 393
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 1.8469,
      "step": 394
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 1.5576,
      "step": 395
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 1.2581,
      "step": 396
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.6251,
      "step": 397
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.8361,
      "step": 398
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.3945,
      "step": 399
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.3759,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_loss": 1.6861692667007446,
      "eval_runtime": 72.2125,
      "eval_samples_per_second": 2.77,
      "eval_steps_per_second": 0.692,
      "step": 400
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.9115,
      "step": 401
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.9773,
      "step": 402
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.8556,
      "step": 403
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 1.3443,
      "step": 404
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 1.7704,
      "step": 405
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 1.4498,
      "step": 406
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 1.2769,
      "step": 407
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 2.2388,
      "step": 408
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 1.5641,
      "step": 409
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 1.5771,
      "step": 410
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 1.9082,
      "step": 411
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 1.2411,
      "step": 412
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 1.5655,
      "step": 413
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 1.4685,
      "step": 414
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 1.6847,
      "step": 415
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 1.6936,
      "step": 416
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 1.4957,
      "step": 417
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 1.544,
      "step": 418
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 1.7443,
      "step": 419
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 1.2188,
      "step": 420
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 1.9088,
      "step": 421
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 1.4389,
      "step": 422
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 1.9066,
      "step": 423
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 1.4886,
      "step": 424
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 1.6327,
      "step": 425
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 1.3956,
      "step": 426
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 1.7019,
      "step": 427
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 1.6154,
      "step": 428
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 1.829,
      "step": 429
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 1.8598,
      "step": 430
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 1.1253,
      "step": 431
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 1.6298,
      "step": 432
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 1.9162,
      "step": 433
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 1.5363,
      "step": 434
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.6628,
      "step": 435
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.6205,
      "step": 436
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.3481,
      "step": 437
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.6322,
      "step": 438
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.5845,
      "step": 439
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.4038,
      "step": 440
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 1.446,
      "step": 441
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 1.7692,
      "step": 442
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 1.7669,
      "step": 443
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 1.831,
      "step": 444
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 1.7333,
      "step": 445
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 1.989,
      "step": 446
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 1.5675,
      "step": 447
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 1.8357,
      "step": 448
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 1.9312,
      "step": 449
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 1.4623,
      "step": 450
    },
    {
      "epoch": 0.72,
      "eval_loss": 1.684700608253479,
      "eval_runtime": 72.357,
      "eval_samples_per_second": 2.764,
      "eval_steps_per_second": 0.691,
      "step": 450
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 1.4249,
      "step": 451
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 1.9042,
      "step": 452
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 1.9023,
      "step": 453
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 1.503,
      "step": 454
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 2.0438,
      "step": 455
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 1.3851,
      "step": 456
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 1.6779,
      "step": 457
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 2.0325,
      "step": 458
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 1.3163,
      "step": 459
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 1.5299,
      "step": 460
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 1.714,
      "step": 461
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 1.461,
      "step": 462
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 1.9831,
      "step": 463
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 1.684,
      "step": 464
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 1.5808,
      "step": 465
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 1.8707,
      "step": 466
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 1.5493,
      "step": 467
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 1.5617,
      "step": 468
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 1.6881,
      "step": 469
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 1.5051,
      "step": 470
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 1.3957,
      "step": 471
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 2.1595,
      "step": 472
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 1.4259,
      "step": 473
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 1.3713,
      "step": 474
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 1.4895,
      "step": 475
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 1.7634,
      "step": 476
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 1.8764,
      "step": 477
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 1.927,
      "step": 478
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 1.5072,
      "step": 479
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 1.5995,
      "step": 480
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 1.5559,
      "step": 481
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 1.589,
      "step": 482
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 1.3944,
      "step": 483
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 1.6027,
      "step": 484
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 1.6152,
      "step": 485
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 1.1001,
      "step": 486
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 1.9874,
      "step": 487
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 1.5554,
      "step": 488
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 1.4903,
      "step": 489
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 1.4183,
      "step": 490
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 1.8034,
      "step": 491
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 1.8249,
      "step": 492
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 1.7518,
      "step": 493
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 1.6664,
      "step": 494
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 1.6256,
      "step": 495
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 1.9023,
      "step": 496
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001,
      "loss": 1.526,
      "step": 497
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001,
      "loss": 2.2228,
      "step": 498
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001,
      "loss": 1.4878,
      "step": 499
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001,
      "loss": 1.9241,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.6839289665222168,
      "eval_runtime": 72.2535,
      "eval_samples_per_second": 2.768,
      "eval_steps_per_second": 0.692,
      "step": 500
    }
  ],
  "logging_steps": 1,
  "max_steps": 1875,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 6577332675035136.0,
  "trial_name": null,
  "trial_params": null
}