{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9832935560859188,
  "eval_steps": 42,
  "global_step": 838,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.00065,
      "loss": 1.5523,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.5476094484329224,
      "eval_runtime": 57.6973,
      "eval_samples_per_second": 8.666,
      "eval_steps_per_second": 4.333,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00065,
      "loss": 1.6985,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00065,
      "loss": 1.1799,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00065,
      "loss": 1.7743,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00065,
      "loss": 1.6175,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00065,
      "loss": 1.5657,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00065,
      "loss": 1.4462,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00065,
      "loss": 1.4567,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00065,
      "loss": 1.734,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00065,
      "loss": 1.4707,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00065,
      "loss": 1.5891,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00065,
      "loss": 1.4921,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00065,
      "loss": 1.5806,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00065,
      "loss": 1.4224,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00065,
      "loss": 1.4779,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00065,
      "loss": 1.5828,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00065,
      "loss": 1.4379,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00065,
      "loss": 1.5227,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00065,
      "loss": 1.3899,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00065,
      "loss": 1.3557,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00065,
      "loss": 1.5049,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00065,
      "loss": 1.5334,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00065,
      "loss": 1.1747,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00065,
      "loss": 1.5094,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00065,
      "loss": 1.4909,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00065,
      "loss": 1.521,
      "step": 26
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00065,
      "loss": 1.5296,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00065,
      "loss": 1.5475,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00065,
      "loss": 1.5203,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00065,
      "loss": 1.4874,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00065,
      "loss": 1.6169,
      "step": 31
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00065,
      "loss": 1.5158,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00065,
      "loss": 1.5844,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00065,
      "loss": 1.4701,
      "step": 34
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00065,
      "loss": 1.3729,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00065,
      "loss": 1.5067,
      "step": 36
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00065,
      "loss": 1.4972,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00065,
      "loss": 1.8079,
      "step": 38
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00065,
      "loss": 1.5681,
      "step": 39
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00065,
      "loss": 1.4852,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00065,
      "loss": 1.5448,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00065,
      "loss": 1.2139,
      "step": 42
    },
    {
      "epoch": 0.1,
      "eval_loss": 1.500810146331787,
      "eval_runtime": 57.801,
      "eval_samples_per_second": 8.65,
      "eval_steps_per_second": 4.325,
      "step": 42
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00065,
      "loss": 1.4483,
      "step": 43
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00065,
      "loss": 1.3328,
      "step": 44
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00065,
      "loss": 1.4363,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00065,
      "loss": 1.2864,
      "step": 46
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00065,
      "loss": 1.4731,
      "step": 47
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00065,
      "loss": 1.5103,
      "step": 48
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00065,
      "loss": 1.5552,
      "step": 49
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00065,
      "loss": 1.4697,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00065,
      "loss": 1.5153,
      "step": 51
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00065,
      "loss": 1.4696,
      "step": 52
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00065,
      "loss": 1.4874,
      "step": 53
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00065,
      "loss": 1.6397,
      "step": 54
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00065,
      "loss": 1.5159,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00065,
      "loss": 1.5399,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00065,
      "loss": 1.573,
      "step": 57
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00065,
      "loss": 1.5067,
      "step": 58
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00065,
      "loss": 1.5585,
      "step": 59
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00065,
      "loss": 1.4998,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00065,
      "loss": 1.0471,
      "step": 61
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00065,
      "loss": 1.5023,
      "step": 62
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00065,
      "loss": 1.241,
      "step": 63
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00065,
      "loss": 1.2748,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00065,
      "loss": 1.598,
      "step": 65
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00065,
      "loss": 1.7209,
      "step": 66
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00065,
      "loss": 1.4492,
      "step": 67
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00065,
      "loss": 1.6432,
      "step": 68
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00065,
      "loss": 1.4849,
      "step": 69
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00065,
      "loss": 1.3859,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00065,
      "loss": 1.2329,
      "step": 71
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00065,
      "loss": 1.4836,
      "step": 72
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00065,
      "loss": 1.5757,
      "step": 73
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00065,
      "loss": 1.4403,
      "step": 74
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00065,
      "loss": 1.4311,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00065,
      "loss": 1.7698,
      "step": 76
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00065,
      "loss": 1.4067,
      "step": 77
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00065,
      "loss": 1.3548,
      "step": 78
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00065,
      "loss": 1.2219,
      "step": 79
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00065,
      "loss": 1.2774,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00065,
      "loss": 1.5268,
      "step": 81
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00065,
      "loss": 1.6669,
      "step": 82
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00065,
      "loss": 1.4055,
      "step": 83
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00065,
      "loss": 1.6348,
      "step": 84
    },
    {
      "epoch": 0.2,
      "eval_loss": 1.4967617988586426,
      "eval_runtime": 57.7521,
      "eval_samples_per_second": 8.658,
      "eval_steps_per_second": 4.329,
      "step": 84
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00065,
      "loss": 1.4524,
      "step": 85
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00065,
      "loss": 1.7781,
      "step": 86
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00065,
      "loss": 1.4317,
      "step": 87
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00065,
      "loss": 1.5865,
      "step": 88
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00065,
      "loss": 1.465,
      "step": 89
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00065,
      "loss": 1.5601,
      "step": 90
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00065,
      "loss": 1.4393,
      "step": 91
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00065,
      "loss": 1.5499,
      "step": 92
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00065,
      "loss": 1.5289,
      "step": 93
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00065,
      "loss": 1.6562,
      "step": 94
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00065,
      "loss": 1.6702,
      "step": 95
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00065,
      "loss": 1.4044,
      "step": 96
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00065,
      "loss": 1.5733,
      "step": 97
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00065,
      "loss": 1.494,
      "step": 98
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00065,
      "loss": 1.5325,
      "step": 99
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00065,
      "loss": 1.5481,
      "step": 100
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00065,
      "loss": 1.5022,
      "step": 101
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00065,
      "loss": 1.5334,
      "step": 102
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00065,
      "loss": 1.4816,
      "step": 103
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00065,
      "loss": 1.5505,
      "step": 104
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00065,
      "loss": 1.5887,
      "step": 105
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00065,
      "loss": 1.6073,
      "step": 106
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00065,
      "loss": 1.2843,
      "step": 107
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00065,
      "loss": 1.6441,
      "step": 108
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00065,
      "loss": 1.4291,
      "step": 109
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00065,
      "loss": 1.5993,
      "step": 110
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00065,
      "loss": 1.6003,
      "step": 111
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00065,
      "loss": 1.6004,
      "step": 112
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00065,
      "loss": 1.092,
      "step": 113
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00065,
      "loss": 1.6992,
      "step": 114
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00065,
      "loss": 1.5215,
      "step": 115
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00065,
      "loss": 1.6719,
      "step": 116
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00065,
      "loss": 1.5689,
      "step": 117
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00065,
      "loss": 1.5856,
      "step": 118
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00065,
      "loss": 1.5404,
      "step": 119
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00065,
      "loss": 1.2784,
      "step": 120
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00065,
      "loss": 1.7063,
      "step": 121
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00065,
      "loss": 1.518,
      "step": 122
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00065,
      "loss": 1.6195,
      "step": 123
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00065,
      "loss": 1.4,
      "step": 124
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00065,
      "loss": 1.5435,
      "step": 125
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00065,
      "loss": 1.6498,
      "step": 126
    },
    {
      "epoch": 0.3,
      "eval_loss": 1.4962397813796997,
      "eval_runtime": 57.8837,
      "eval_samples_per_second": 8.638,
      "eval_steps_per_second": 4.319,
      "step": 126
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00065,
      "loss": 1.4815,
      "step": 127
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00065,
      "loss": 1.5617,
      "step": 128
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00065,
      "loss": 1.6173,
      "step": 129
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00065,
      "loss": 1.6515,
      "step": 130
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00065,
      "loss": 1.7001,
      "step": 131
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00065,
      "loss": 1.7185,
      "step": 132
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00065,
      "loss": 1.5095,
      "step": 133
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00065,
      "loss": 1.5354,
      "step": 134
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00065,
      "loss": 1.5958,
      "step": 135
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00065,
      "loss": 1.5622,
      "step": 136
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00065,
      "loss": 1.5229,
      "step": 137
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00065,
      "loss": 1.5117,
      "step": 138
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00065,
      "loss": 1.7616,
      "step": 139
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00065,
      "loss": 1.2281,
      "step": 140
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00065,
      "loss": 1.6234,
      "step": 141
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00065,
      "loss": 1.3816,
      "step": 142
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00065,
      "loss": 1.474,
      "step": 143
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00065,
      "loss": 1.4441,
      "step": 144
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00065,
      "loss": 1.602,
      "step": 145
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00065,
      "loss": 1.543,
      "step": 146
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00065,
      "loss": 1.7464,
      "step": 147
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00065,
      "loss": 1.696,
      "step": 148
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00065,
      "loss": 1.6781,
      "step": 149
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00065,
      "loss": 1.4346,
      "step": 150
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00065,
      "loss": 1.5507,
      "step": 151
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00065,
      "loss": 1.5901,
      "step": 152
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00065,
      "loss": 1.4516,
      "step": 153
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00065,
      "loss": 1.4069,
      "step": 154
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00065,
      "loss": 1.5614,
      "step": 155
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00065,
      "loss": 1.4832,
      "step": 156
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00065,
      "loss": 1.4241,
      "step": 157
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00065,
      "loss": 1.4526,
      "step": 158
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00065,
      "loss": 1.1961,
      "step": 159
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00065,
      "loss": 1.4206,
      "step": 160
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00065,
      "loss": 1.6221,
      "step": 161
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00065,
      "loss": 1.5796,
      "step": 162
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00065,
      "loss": 1.7052,
      "step": 163
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00065,
      "loss": 1.6022,
      "step": 164
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00065,
      "loss": 1.4067,
      "step": 165
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00065,
      "loss": 1.4105,
      "step": 166
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00065,
      "loss": 1.3916,
      "step": 167
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00065,
      "loss": 1.5645,
      "step": 168
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.498284101486206,
      "eval_runtime": 57.7262,
      "eval_samples_per_second": 8.662,
      "eval_steps_per_second": 4.331,
      "step": 168
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00065,
      "loss": 1.5244,
      "step": 169
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00065,
      "loss": 1.3781,
      "step": 170
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00065,
      "loss": 1.6621,
      "step": 171
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00065,
      "loss": 1.6337,
      "step": 172
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00065,
      "loss": 1.5208,
      "step": 173
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00065,
      "loss": 1.2743,
      "step": 174
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00065,
      "loss": 1.6341,
      "step": 175
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00065,
      "loss": 1.2578,
      "step": 176
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00065,
      "loss": 1.6975,
      "step": 177
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00065,
      "loss": 1.5663,
      "step": 178
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00065,
      "loss": 1.5621,
      "step": 179
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00065,
      "loss": 1.3063,
      "step": 180
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00065,
      "loss": 1.4776,
      "step": 181
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00065,
      "loss": 1.7046,
      "step": 182
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00065,
      "loss": 1.5946,
      "step": 183
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00065,
      "loss": 1.779,
      "step": 184
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00065,
      "loss": 1.571,
      "step": 185
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00065,
      "loss": 1.5513,
      "step": 186
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00065,
      "loss": 1.4312,
      "step": 187
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00065,
      "loss": 1.4258,
      "step": 188
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00065,
      "loss": 1.5412,
      "step": 189
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00065,
      "loss": 1.6545,
      "step": 190
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00065,
      "loss": 1.5313,
      "step": 191
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00065,
      "loss": 1.5245,
      "step": 192
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00065,
      "loss": 1.41,
      "step": 193
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00065,
      "loss": 1.5677,
      "step": 194
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00065,
      "loss": 1.6269,
      "step": 195
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00065,
      "loss": 1.6669,
      "step": 196
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00065,
      "loss": 1.3903,
      "step": 197
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00065,
      "loss": 1.4535,
      "step": 198
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00065,
      "loss": 1.6028,
      "step": 199
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00065,
      "loss": 1.3562,
      "step": 200
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00065,
      "loss": 1.4644,
      "step": 201
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00065,
      "loss": 1.4645,
      "step": 202
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00065,
      "loss": 1.6715,
      "step": 203
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00065,
      "loss": 1.3685,
      "step": 204
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00065,
      "loss": 1.1695,
      "step": 205
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00065,
      "loss": 1.6035,
      "step": 206
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00065,
      "loss": 1.5142,
      "step": 207
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00065,
      "loss": 1.5223,
      "step": 208
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00065,
      "loss": 1.5144,
      "step": 209
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00065,
      "loss": 1.6487,
      "step": 210
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.4980822801589966,
      "eval_runtime": 57.8018,
      "eval_samples_per_second": 8.65,
      "eval_steps_per_second": 4.325,
      "step": 210
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00065,
      "loss": 1.4847,
      "step": 211
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00065,
      "loss": 1.491,
      "step": 212
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00065,
      "loss": 1.3213,
      "step": 213
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00065,
      "loss": 1.6399,
      "step": 214
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00065,
      "loss": 1.6079,
      "step": 215
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00065,
      "loss": 1.4458,
      "step": 216
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00065,
      "loss": 1.6101,
      "step": 217
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00065,
      "loss": 1.6516,
      "step": 218
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00065,
      "loss": 1.4794,
      "step": 219
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00065,
      "loss": 1.7151,
      "step": 220
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00065,
      "loss": 1.5805,
      "step": 221
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00065,
      "loss": 1.5088,
      "step": 222
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00065,
      "loss": 1.5852,
      "step": 223
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00065,
      "loss": 1.3886,
      "step": 224
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00065,
      "loss": 1.7186,
      "step": 225
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00065,
      "loss": 1.6551,
      "step": 226
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00065,
      "loss": 1.5615,
      "step": 227
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00065,
      "loss": 1.8389,
      "step": 228
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00065,
      "loss": 1.5447,
      "step": 229
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00065,
      "loss": 1.4015,
      "step": 230
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00065,
      "loss": 1.5386,
      "step": 231
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00065,
      "loss": 1.6429,
      "step": 232
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00065,
      "loss": 1.5531,
      "step": 233
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00065,
      "loss": 1.3572,
      "step": 234
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00065,
      "loss": 1.3011,
      "step": 235
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00065,
      "loss": 1.7356,
      "step": 236
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00065,
      "loss": 1.2688,
      "step": 237
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00065,
      "loss": 1.5885,
      "step": 238
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00065,
      "loss": 1.5765,
      "step": 239
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00065,
      "loss": 1.3705,
      "step": 240
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00065,
      "loss": 1.4097,
      "step": 241
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00065,
      "loss": 1.5182,
      "step": 242
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00065,
      "loss": 1.2854,
      "step": 243
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00065,
      "loss": 1.8305,
      "step": 244
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00065,
      "loss": 1.0632,
      "step": 245
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00065,
      "loss": 1.5128,
      "step": 246
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00065,
      "loss": 1.545,
      "step": 247
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00065,
      "loss": 1.4362,
      "step": 248
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00065,
      "loss": 1.093,
      "step": 249
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00065,
      "loss": 1.5286,
      "step": 250
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00065,
      "loss": 1.5218,
      "step": 251
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00065,
      "loss": 1.6147,
      "step": 252
    },
    {
      "epoch": 0.6,
      "eval_loss": 1.4965262413024902,
      "eval_runtime": 57.8272,
      "eval_samples_per_second": 8.646,
      "eval_steps_per_second": 4.323,
      "step": 252
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00065,
      "loss": 1.6172,
      "step": 253
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00065,
      "loss": 1.4856,
      "step": 254
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00065,
      "loss": 1.6167,
      "step": 255
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00065,
      "loss": 1.5882,
      "step": 256
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00065,
      "loss": 1.4952,
      "step": 257
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00065,
      "loss": 1.5929,
      "step": 258
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00065,
      "loss": 1.314,
      "step": 259
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00065,
      "loss": 1.3682,
      "step": 260
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00065,
      "loss": 1.5718,
      "step": 261
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00065,
      "loss": 1.337,
      "step": 262
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00065,
      "loss": 1.7287,
      "step": 263
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00065,
      "loss": 1.685,
      "step": 264
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00065,
      "loss": 1.1973,
      "step": 265
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00065,
      "loss": 1.4037,
      "step": 266
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00065,
      "loss": 1.3741,
      "step": 267
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00065,
      "loss": 1.6339,
      "step": 268
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00065,
      "loss": 1.6981,
      "step": 269
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00065,
      "loss": 1.4383,
      "step": 270
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00065,
      "loss": 1.5721,
      "step": 271
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00065,
      "loss": 1.587,
      "step": 272
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00065,
      "loss": 1.8308,
      "step": 273
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00065,
      "loss": 1.3733,
      "step": 274
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00065,
      "loss": 1.6366,
      "step": 275
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00065,
      "loss": 1.4057,
      "step": 276
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00065,
      "loss": 1.6264,
      "step": 277
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00065,
      "loss": 1.5546,
      "step": 278
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00065,
      "loss": 1.567,
      "step": 279
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00065,
      "loss": 1.312,
      "step": 280
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00065,
      "loss": 1.438,
      "step": 281
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00065,
      "loss": 1.4226,
      "step": 282
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00065,
      "loss": 1.4871,
      "step": 283
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00065,
      "loss": 1.5465,
      "step": 284
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00065,
      "loss": 1.4989,
      "step": 285
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00065,
      "loss": 1.6361,
      "step": 286
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00065,
      "loss": 1.5529,
      "step": 287
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00065,
      "loss": 1.334,
      "step": 288
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00065,
      "loss": 1.6348,
      "step": 289
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00065,
      "loss": 1.6611,
      "step": 290
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00065,
      "loss": 1.3462,
      "step": 291
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00065,
      "loss": 1.3151,
      "step": 292
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00065,
      "loss": 1.4333,
      "step": 293
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00065,
      "loss": 1.3048,
      "step": 294
    },
    {
      "epoch": 0.7,
      "eval_loss": 1.4973247051239014,
      "eval_runtime": 57.7873,
      "eval_samples_per_second": 8.652,
      "eval_steps_per_second": 4.326,
      "step": 294
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00065,
      "loss": 1.5376,
      "step": 295
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00065,
      "loss": 1.5643,
      "step": 296
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00065,
      "loss": 1.6501,
      "step": 297
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00065,
      "loss": 1.3652,
      "step": 298
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00065,
      "loss": 1.5191,
      "step": 299
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00065,
      "loss": 1.5722,
      "step": 300
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00065,
      "loss": 1.5057,
      "step": 301
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00065,
      "loss": 1.3798,
      "step": 302
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00065,
      "loss": 1.3492,
      "step": 303
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00065,
      "loss": 1.3582,
      "step": 304
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00065,
      "loss": 1.5691,
      "step": 305
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00065,
      "loss": 1.6634,
      "step": 306
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00065,
      "loss": 1.6464,
      "step": 307
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00065,
      "loss": 1.4683,
      "step": 308
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00065,
      "loss": 1.5424,
      "step": 309
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00065,
      "loss": 1.5145,
      "step": 310
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00065,
      "loss": 1.6582,
      "step": 311
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00065,
      "loss": 1.3616,
      "step": 312
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00065,
      "loss": 1.5284,
      "step": 313
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00065,
      "loss": 1.1895,
      "step": 314
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00065,
      "loss": 1.6037,
      "step": 315
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00065,
      "loss": 1.5233,
      "step": 316
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00065,
      "loss": 1.6914,
      "step": 317
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00065,
      "loss": 1.4968,
      "step": 318
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00065,
      "loss": 1.2765,
      "step": 319
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00065,
      "loss": 1.6675,
      "step": 320
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00065,
      "loss": 1.723,
      "step": 321
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00065,
      "loss": 1.4832,
      "step": 322
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00065,
      "loss": 1.179,
      "step": 323
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00065,
      "loss": 1.5108,
      "step": 324
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00065,
      "loss": 1.3931,
      "step": 325
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00065,
      "loss": 1.6227,
      "step": 326
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00065,
      "loss": 1.353,
      "step": 327
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00065,
      "loss": 1.5377,
      "step": 328
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00065,
      "loss": 1.6277,
      "step": 329
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00065,
      "loss": 1.4532,
      "step": 330
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00065,
      "loss": 1.6329,
      "step": 331
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00065,
      "loss": 1.6595,
      "step": 332
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00065,
      "loss": 1.4014,
      "step": 333
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00065,
      "loss": 1.4108,
      "step": 334
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00065,
      "loss": 1.5729,
      "step": 335
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00065,
      "loss": 1.6205,
      "step": 336
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.5006886720657349,
      "eval_runtime": 57.756,
      "eval_samples_per_second": 8.657,
      "eval_steps_per_second": 4.329,
      "step": 336
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00065,
      "loss": 1.5595,
      "step": 337
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00065,
      "loss": 1.4389,
      "step": 338
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00065,
      "loss": 1.6702,
      "step": 339
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00065,
      "loss": 1.7348,
      "step": 340
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00065,
      "loss": 1.5383,
      "step": 341
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00065,
      "loss": 1.2777,
      "step": 342
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00065,
      "loss": 1.4466,
      "step": 343
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00065,
      "loss": 1.4665,
      "step": 344
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00065,
      "loss": 1.595,
      "step": 345
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00065,
      "loss": 1.4895,
      "step": 346
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00065,
      "loss": 1.4753,
      "step": 347
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00065,
      "loss": 1.4371,
      "step": 348
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00065,
      "loss": 1.4467,
      "step": 349
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00065,
      "loss": 1.2601,
      "step": 350
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00065,
      "loss": 1.1586,
      "step": 351
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00065,
      "loss": 1.7566,
      "step": 352
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00065,
      "loss": 1.5955,
      "step": 353
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00065,
      "loss": 1.3872,
      "step": 354
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00065,
      "loss": 1.3124,
      "step": 355
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00065,
      "loss": 1.5033,
      "step": 356
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00065,
      "loss": 1.6921,
      "step": 357
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00065,
      "loss": 1.5243,
      "step": 358
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00065,
      "loss": 1.5287,
      "step": 359
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00065,
      "loss": 1.4257,
      "step": 360
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00065,
      "loss": 1.3924,
      "step": 361
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00065,
      "loss": 1.6084,
      "step": 362
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00065,
      "loss": 1.5605,
      "step": 363
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00065,
      "loss": 1.6319,
      "step": 364
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00065,
      "loss": 1.5691,
      "step": 365
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00065,
      "loss": 1.311,
      "step": 366
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00065,
      "loss": 1.4892,
      "step": 367
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00065,
      "loss": 1.3108,
      "step": 368
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00065,
      "loss": 1.6953,
      "step": 369
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00065,
      "loss": 1.5857,
      "step": 370
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00065,
      "loss": 1.4536,
      "step": 371
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00065,
      "loss": 1.4781,
      "step": 372
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00065,
      "loss": 1.5191,
      "step": 373
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00065,
      "loss": 1.5136,
      "step": 374
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00065,
      "loss": 1.5246,
      "step": 375
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00065,
      "loss": 1.022,
      "step": 376
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00065,
      "loss": 1.5182,
      "step": 377
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00065,
      "loss": 1.6045,
      "step": 378
    },
    {
      "epoch": 0.9,
      "eval_loss": 1.5002774000167847,
      "eval_runtime": 57.7872,
      "eval_samples_per_second": 8.652,
      "eval_steps_per_second": 4.326,
      "step": 378
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00065,
      "loss": 1.6214,
      "step": 379
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00065,
      "loss": 1.4893,
      "step": 380
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00065,
      "loss": 1.5942,
      "step": 381
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00065,
      "loss": 1.369,
      "step": 382
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00065,
      "loss": 1.0446,
      "step": 383
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00065,
      "loss": 1.63,
      "step": 384
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00065,
      "loss": 1.5157,
      "step": 385
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00065,
      "loss": 1.4303,
      "step": 386
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00065,
      "loss": 1.539,
      "step": 387
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00065,
      "loss": 1.3132,
      "step": 388
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00065,
      "loss": 1.0668,
      "step": 389
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00065,
      "loss": 1.5303,
      "step": 390
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00065,
      "loss": 1.5204,
      "step": 391
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00065,
      "loss": 1.6575,
      "step": 392
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00065,
      "loss": 1.5325,
      "step": 393
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00065,
      "loss": 1.6132,
      "step": 394
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00065,
      "loss": 1.4253,
      "step": 395
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00065,
      "loss": 1.2638,
      "step": 396
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00065,
      "loss": 1.5054,
      "step": 397
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00065,
      "loss": 1.6769,
      "step": 398
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00065,
      "loss": 1.5845,
      "step": 399
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00065,
      "loss": 1.2866,
      "step": 400
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00065,
      "loss": 1.1569,
      "step": 401
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00065,
      "loss": 1.2087,
      "step": 402
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00065,
      "loss": 1.6248,
      "step": 403
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00065,
      "loss": 1.5012,
      "step": 404
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00065,
      "loss": 1.6551,
      "step": 405
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00065,
      "loss": 1.4988,
      "step": 406
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00065,
      "loss": 1.4565,
      "step": 407
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00065,
      "loss": 1.2717,
      "step": 408
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00065,
      "loss": 1.7323,
      "step": 409
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00065,
      "loss": 1.5811,
      "step": 410
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00065,
      "loss": 1.4139,
      "step": 411
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00065,
      "loss": 1.4657,
      "step": 412
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00065,
      "loss": 1.5507,
      "step": 413
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00065,
      "loss": 1.4202,
      "step": 414
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00065,
      "loss": 1.412,
      "step": 415
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00065,
      "loss": 1.5208,
      "step": 416
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00065,
      "loss": 1.5733,
      "step": 417
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00065,
      "loss": 1.6295,
      "step": 418
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00065,
      "loss": 1.4903,
      "step": 419
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00065,
      "loss": 1.5781,
      "step": 420
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.5013374090194702,
      "eval_runtime": 57.703,
      "eval_samples_per_second": 8.665,
      "eval_steps_per_second": 4.333,
      "step": 420
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00065,
      "loss": 1.6304,
      "step": 421
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00065,
      "loss": 1.6533,
      "step": 422
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00065,
      "loss": 1.3432,
      "step": 423
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00065,
      "loss": 1.5377,
      "step": 424
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00065,
      "loss": 1.6638,
      "step": 425
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00065,
      "loss": 1.5242,
      "step": 426
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00065,
      "loss": 1.3306,
      "step": 427
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00065,
      "loss": 1.3637,
      "step": 428
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00065,
      "loss": 1.4253,
      "step": 429
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00065,
      "loss": 1.49,
      "step": 430
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00065,
      "loss": 1.4924,
      "step": 431
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00065,
      "loss": 0.95,
      "step": 432
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00065,
      "loss": 1.3238,
      "step": 433
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00065,
      "loss": 1.091,
      "step": 434
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00065,
      "loss": 1.344,
      "step": 435
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00065,
      "loss": 1.2361,
      "step": 436
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00065,
      "loss": 1.3262,
      "step": 437
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00065,
      "loss": 1.1314,
      "step": 438
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00065,
      "loss": 1.3437,
      "step": 439
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00065,
      "loss": 1.2767,
      "step": 440
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00065,
      "loss": 0.9201,
      "step": 441
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00065,
      "loss": 1.4971,
      "step": 442
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00065,
      "loss": 1.1516,
      "step": 443
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00065,
      "loss": 1.226,
      "step": 444
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00065,
      "loss": 1.5404,
      "step": 445
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00065,
      "loss": 0.9349,
      "step": 446
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00065,
      "loss": 1.2262,
      "step": 447
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00065,
      "loss": 1.285,
      "step": 448
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00065,
      "loss": 1.3562,
      "step": 449
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00065,
      "loss": 1.1475,
      "step": 450
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00065,
      "loss": 1.2592,
      "step": 451
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00065,
      "loss": 1.2524,
      "step": 452
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00065,
      "loss": 1.2089,
      "step": 453
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00065,
      "loss": 1.154,
      "step": 454
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00065,
      "loss": 1.382,
      "step": 455
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00065,
      "loss": 1.2451,
      "step": 456
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00065,
      "loss": 1.3714,
      "step": 457
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00065,
      "loss": 1.2885,
      "step": 458
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00065,
      "loss": 1.242,
      "step": 459
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00065,
      "loss": 1.1617,
      "step": 460
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00065,
      "loss": 1.1649,
      "step": 461
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00065,
      "loss": 1.4807,
      "step": 462
    },
    {
      "epoch": 1.09,
      "eval_loss": 1.5492066144943237,
      "eval_runtime": 57.7283,
      "eval_samples_per_second": 8.661,
      "eval_steps_per_second": 4.331,
      "step": 462
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00065,
      "loss": 0.9944,
      "step": 463
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00065,
      "loss": 1.3231,
      "step": 464
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00065,
      "loss": 1.1236,
      "step": 465
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00065,
      "loss": 1.2049,
      "step": 466
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00065,
      "loss": 1.1105,
      "step": 467
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00065,
      "loss": 1.3196,
      "step": 468
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00065,
      "loss": 1.2235,
      "step": 469
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00065,
      "loss": 1.2483,
      "step": 470
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00065,
      "loss": 1.3401,
      "step": 471
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00065,
      "loss": 1.288,
      "step": 472
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00065,
      "loss": 1.2532,
      "step": 473
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00065,
      "loss": 1.4223,
      "step": 474
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00065,
      "loss": 1.3564,
      "step": 475
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00065,
      "loss": 1.3718,
      "step": 476
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00065,
      "loss": 1.1161,
      "step": 477
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00065,
      "loss": 1.0945,
      "step": 478
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00065,
      "loss": 1.3445,
      "step": 479
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00065,
      "loss": 1.4793,
      "step": 480
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00065,
      "loss": 0.9494,
      "step": 481
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00065,
      "loss": 1.1057,
      "step": 482
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00065,
      "loss": 1.1983,
      "step": 483
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00065,
      "loss": 1.1323,
      "step": 484
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00065,
      "loss": 1.3516,
      "step": 485
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00065,
      "loss": 1.2307,
      "step": 486
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00065,
      "loss": 0.8255,
      "step": 487
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00065,
      "loss": 1.2039,
      "step": 488
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00065,
      "loss": 0.9115,
      "step": 489
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00065,
      "loss": 1.1368,
      "step": 490
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00065,
      "loss": 1.0338,
      "step": 491
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00065,
      "loss": 1.1342,
      "step": 492
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00065,
      "loss": 1.2698,
      "step": 493
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00065,
      "loss": 0.9189,
      "step": 494
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00065,
      "loss": 1.3934,
      "step": 495
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00065,
      "loss": 1.0178,
      "step": 496
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00065,
      "loss": 1.1283,
      "step": 497
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00065,
      "loss": 1.134,
      "step": 498
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00065,
      "loss": 1.0912,
      "step": 499
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00065,
      "loss": 1.2339,
      "step": 500
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00065,
      "loss": 1.3103,
      "step": 501
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00065,
      "loss": 1.0677,
      "step": 502
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00065,
      "loss": 1.2374,
      "step": 503
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00065,
      "loss": 1.0541,
      "step": 504
    },
    {
      "epoch": 1.19,
      "eval_loss": 1.559614658355713,
      "eval_runtime": 57.6683,
      "eval_samples_per_second": 8.67,
      "eval_steps_per_second": 4.335,
      "step": 504
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00065,
      "loss": 1.1002,
      "step": 505
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00065,
      "loss": 1.1307,
      "step": 506
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00065,
      "loss": 1.5203,
      "step": 507
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00065,
      "loss": 1.2019,
      "step": 508
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00065,
      "loss": 1.1506,
      "step": 509
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00065,
      "loss": 1.2836,
      "step": 510
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00065,
      "loss": 1.2752,
      "step": 511
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00065,
      "loss": 1.1245,
      "step": 512
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00065,
      "loss": 0.9534,
      "step": 513
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00065,
      "loss": 1.1814,
      "step": 514
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00065,
      "loss": 1.2562,
      "step": 515
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00065,
      "loss": 1.1561,
      "step": 516
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00065,
      "loss": 1.3549,
      "step": 517
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00065,
      "loss": 1.0763,
      "step": 518
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00065,
      "loss": 1.2134,
      "step": 519
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00065,
      "loss": 1.2445,
      "step": 520
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00065,
      "loss": 0.976,
      "step": 521
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00065,
      "loss": 1.2341,
      "step": 522
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00065,
      "loss": 1.2847,
      "step": 523
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00065,
      "loss": 1.2537,
      "step": 524
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00065,
      "loss": 1.2653,
      "step": 525
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00065,
      "loss": 1.1949,
      "step": 526
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00065,
      "loss": 0.9586,
      "step": 527
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00065,
      "loss": 1.0875,
      "step": 528
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00065,
      "loss": 0.8407,
      "step": 529
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00065,
      "loss": 1.1969,
      "step": 530
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00065,
      "loss": 1.2271,
      "step": 531
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00065,
      "loss": 1.2104,
      "step": 532
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00065,
      "loss": 1.0545,
      "step": 533
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00065,
      "loss": 1.2407,
      "step": 534
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00065,
      "loss": 1.3342,
      "step": 535
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00065,
      "loss": 1.131,
      "step": 536
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00065,
      "loss": 1.1606,
      "step": 537
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00065,
      "loss": 1.1866,
      "step": 538
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00065,
      "loss": 0.9723,
      "step": 539
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00065,
      "loss": 1.2043,
      "step": 540
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00065,
      "loss": 1.2889,
      "step": 541
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00065,
      "loss": 1.1564,
      "step": 542
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00065,
      "loss": 1.1532,
      "step": 543
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00065,
      "loss": 1.1011,
      "step": 544
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00065,
      "loss": 1.0829,
      "step": 545
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00065,
      "loss": 1.2337,
      "step": 546
    },
    {
      "epoch": 1.29,
      "eval_loss": 1.5788898468017578,
      "eval_runtime": 57.6591,
      "eval_samples_per_second": 8.672,
      "eval_steps_per_second": 4.336,
      "step": 546
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00065,
      "loss": 1.3735,
      "step": 547
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00065,
      "loss": 1.241,
      "step": 548
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00065,
      "loss": 1.4505,
      "step": 549
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00065,
      "loss": 1.2719,
      "step": 550
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00065,
      "loss": 1.2341,
      "step": 551
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00065,
      "loss": 1.1105,
      "step": 552
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00065,
      "loss": 1.0891,
      "step": 553
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00065,
      "loss": 1.1677,
      "step": 554
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00065,
      "loss": 1.341,
      "step": 555
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00065,
      "loss": 1.2119,
      "step": 556
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00065,
      "loss": 1.0217,
      "step": 557
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00065,
      "loss": 1.3831,
      "step": 558
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00065,
      "loss": 1.1828,
      "step": 559
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00065,
      "loss": 1.2138,
      "step": 560
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00065,
      "loss": 1.2737,
      "step": 561
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00065,
      "loss": 1.027,
      "step": 562
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00065,
      "loss": 1.0615,
      "step": 563
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00065,
      "loss": 1.2548,
      "step": 564
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00065,
      "loss": 1.1936,
      "step": 565
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00065,
      "loss": 1.2813,
      "step": 566
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00065,
      "loss": 1.0757,
      "step": 567
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00065,
      "loss": 1.203,
      "step": 568
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00065,
      "loss": 1.1908,
      "step": 569
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00065,
      "loss": 1.1739,
      "step": 570
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00065,
      "loss": 1.1155,
      "step": 571
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00065,
      "loss": 1.2386,
      "step": 572
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00065,
      "loss": 1.0254,
      "step": 573
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00065,
      "loss": 1.1139,
      "step": 574
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00065,
      "loss": 1.382,
      "step": 575
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00065,
      "loss": 1.2854,
      "step": 576
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00065,
      "loss": 1.3669,
      "step": 577
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00065,
      "loss": 1.0083,
      "step": 578
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00065,
      "loss": 1.136,
      "step": 579
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00065,
      "loss": 1.1165,
      "step": 580
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00065,
      "loss": 1.0514,
      "step": 581
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00065,
      "loss": 1.2967,
      "step": 582
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00065,
      "loss": 1.183,
      "step": 583
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00065,
      "loss": 1.186,
      "step": 584
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00065,
      "loss": 1.1914,
      "step": 585
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00065,
      "loss": 1.1845,
      "step": 586
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00065,
      "loss": 1.2612,
      "step": 587
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00065,
      "loss": 0.9719,
      "step": 588
    },
    {
      "epoch": 1.39,
      "eval_loss": 1.5859321355819702,
      "eval_runtime": 57.6415,
      "eval_samples_per_second": 8.674,
      "eval_steps_per_second": 4.337,
      "step": 588
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00065,
      "loss": 1.291,
      "step": 589
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00065,
      "loss": 0.8737,
      "step": 590
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00065,
      "loss": 1.3129,
      "step": 591
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00065,
      "loss": 1.1863,
      "step": 592
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00065,
      "loss": 1.094,
      "step": 593
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00065,
      "loss": 1.3167,
      "step": 594
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00065,
      "loss": 1.1205,
      "step": 595
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00065,
      "loss": 1.1263,
      "step": 596
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00065,
      "loss": 1.0644,
      "step": 597
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00065,
      "loss": 1.2847,
      "step": 598
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00065,
      "loss": 1.1278,
      "step": 599
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00065,
      "loss": 1.0939,
      "step": 600
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00065,
      "loss": 1.1051,
      "step": 601
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00065,
      "loss": 1.1711,
      "step": 602
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00065,
      "loss": 1.4111,
      "step": 603
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00065,
      "loss": 1.1579,
      "step": 604
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00065,
      "loss": 1.2531,
      "step": 605
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00065,
      "loss": 1.2966,
      "step": 606
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00065,
      "loss": 1.2329,
      "step": 607
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00065,
      "loss": 1.1892,
      "step": 608
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00065,
      "loss": 1.3673,
      "step": 609
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00065,
      "loss": 1.0371,
      "step": 610
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00065,
      "loss": 1.3279,
      "step": 611
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00065,
      "loss": 0.9754,
      "step": 612
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00065,
      "loss": 1.097,
      "step": 613
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00065,
      "loss": 1.0986,
      "step": 614
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00065,
      "loss": 1.1958,
      "step": 615
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00065,
      "loss": 1.2261,
      "step": 616
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00065,
      "loss": 1.0797,
      "step": 617
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00065,
      "loss": 1.1249,
      "step": 618
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00065,
      "loss": 1.3726,
      "step": 619
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00065,
      "loss": 0.9819,
      "step": 620
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00065,
      "loss": 1.1712,
      "step": 621
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00065,
      "loss": 1.1711,
      "step": 622
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00065,
      "loss": 1.0783,
      "step": 623
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00065,
      "loss": 1.3031,
      "step": 624
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00065,
      "loss": 1.1674,
      "step": 625
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00065,
      "loss": 1.1693,
      "step": 626
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00065,
      "loss": 1.1413,
      "step": 627
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00065,
      "loss": 1.275,
      "step": 628
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00065,
      "loss": 1.1146,
      "step": 629
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00065,
      "loss": 1.2189,
      "step": 630
    },
    {
      "epoch": 1.49,
      "eval_loss": 1.5958884954452515,
      "eval_runtime": 57.618,
      "eval_samples_per_second": 8.678,
      "eval_steps_per_second": 4.339,
      "step": 630
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00065,
      "loss": 1.1986,
      "step": 631
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00065,
      "loss": 1.3615,
      "step": 632
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00065,
      "loss": 1.4031,
      "step": 633
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00065,
      "loss": 1.4007,
      "step": 634
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00065,
      "loss": 1.463,
      "step": 635
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00065,
      "loss": 0.802,
      "step": 636
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00065,
      "loss": 1.2234,
      "step": 637
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00065,
      "loss": 1.1812,
      "step": 638
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00065,
      "loss": 1.2459,
      "step": 639
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00065,
      "loss": 1.2198,
      "step": 640
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00065,
      "loss": 1.251,
      "step": 641
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00065,
      "loss": 1.0966,
      "step": 642
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00065,
      "loss": 1.0978,
      "step": 643
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00065,
      "loss": 1.3338,
      "step": 644
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00065,
      "loss": 1.3305,
      "step": 645
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00065,
      "loss": 1.2164,
      "step": 646
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00065,
      "loss": 1.1011,
      "step": 647
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00065,
      "loss": 1.0557,
      "step": 648
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00065,
      "loss": 1.1814,
      "step": 649
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00065,
      "loss": 1.3844,
      "step": 650
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00065,
      "loss": 1.1344,
      "step": 651
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00065,
      "loss": 1.1051,
      "step": 652
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00065,
      "loss": 1.2505,
      "step": 653
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00065,
      "loss": 1.2285,
      "step": 654
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00065,
      "loss": 1.1327,
      "step": 655
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00065,
      "loss": 1.021,
      "step": 656
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00065,
      "loss": 1.1479,
      "step": 657
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00065,
      "loss": 1.209,
      "step": 658
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00065,
      "loss": 1.0886,
      "step": 659
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00065,
      "loss": 1.0655,
      "step": 660
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00065,
      "loss": 1.1478,
      "step": 661
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00065,
      "loss": 1.1008,
      "step": 662
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00065,
      "loss": 1.1215,
      "step": 663
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00065,
      "loss": 1.3755,
      "step": 664
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00065,
      "loss": 1.0205,
      "step": 665
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00065,
      "loss": 1.2023,
      "step": 666
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00065,
      "loss": 1.0582,
      "step": 667
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00065,
      "loss": 1.145,
      "step": 668
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00065,
      "loss": 1.1469,
      "step": 669
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00065,
      "loss": 1.1109,
      "step": 670
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00065,
      "loss": 1.0745,
      "step": 671
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00065,
      "loss": 1.2566,
      "step": 672
    },
    {
      "epoch": 1.59,
      "eval_loss": 1.5968223810195923,
      "eval_runtime": 57.7702,
      "eval_samples_per_second": 8.655,
      "eval_steps_per_second": 4.327,
      "step": 672
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00065,
      "loss": 1.2859,
      "step": 673
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00065,
      "loss": 0.8272,
      "step": 674
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00065,
      "loss": 1.2386,
      "step": 675
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00065,
      "loss": 1.0858,
      "step": 676
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00065,
      "loss": 1.4543,
      "step": 677
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00065,
      "loss": 1.3696,
      "step": 678
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00065,
      "loss": 1.0247,
      "step": 679
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00065,
      "loss": 0.8026,
      "step": 680
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00065,
      "loss": 1.1607,
      "step": 681
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00065,
      "loss": 1.1685,
      "step": 682
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00065,
      "loss": 1.307,
      "step": 683
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00065,
      "loss": 1.24,
      "step": 684
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00065,
      "loss": 1.1193,
      "step": 685
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00065,
      "loss": 1.0114,
      "step": 686
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00065,
      "loss": 1.0478,
      "step": 687
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00065,
      "loss": 1.2924,
      "step": 688
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00065,
      "loss": 1.0249,
      "step": 689
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00065,
      "loss": 1.1305,
      "step": 690
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00065,
      "loss": 1.0604,
      "step": 691
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00065,
      "loss": 1.3059,
      "step": 692
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00065,
      "loss": 1.343,
      "step": 693
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00065,
      "loss": 1.2422,
      "step": 694
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00065,
      "loss": 0.9783,
      "step": 695
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00065,
      "loss": 1.1911,
      "step": 696
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00065,
      "loss": 1.0073,
      "step": 697
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00065,
      "loss": 1.2903,
      "step": 698
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00065,
      "loss": 1.1604,
      "step": 699
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00065,
      "loss": 1.1637,
      "step": 700
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00065,
      "loss": 1.1648,
      "step": 701
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00065,
      "loss": 1.3168,
      "step": 702
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00065,
      "loss": 1.2936,
      "step": 703
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00065,
      "loss": 1.2169,
      "step": 704
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00065,
      "loss": 1.312,
      "step": 705
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00065,
      "loss": 1.0459,
      "step": 706
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00065,
      "loss": 1.2515,
      "step": 707
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00065,
      "loss": 1.1142,
      "step": 708
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00065,
      "loss": 0.9709,
      "step": 709
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00065,
      "loss": 1.1636,
      "step": 710
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00065,
      "loss": 1.2273,
      "step": 711
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00065,
      "loss": 1.4015,
      "step": 712
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00065,
      "loss": 1.2383,
      "step": 713
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00065,
      "loss": 0.7049,
      "step": 714
    },
    {
      "epoch": 1.69,
      "eval_loss": 1.5986626148223877,
      "eval_runtime": 57.7067,
      "eval_samples_per_second": 8.665,
      "eval_steps_per_second": 4.332,
      "step": 714
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00065,
      "loss": 1.3247,
      "step": 715
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00065,
      "loss": 1.1937,
      "step": 716
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00065,
      "loss": 1.1404,
      "step": 717
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00065,
      "loss": 0.8771,
      "step": 718
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00065,
      "loss": 1.2544,
      "step": 719
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00065,
      "loss": 1.3652,
      "step": 720
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00065,
      "loss": 1.2582,
      "step": 721
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00065,
      "loss": 1.0112,
      "step": 722
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00065,
      "loss": 1.1113,
      "step": 723
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00065,
      "loss": 1.23,
      "step": 724
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00065,
      "loss": 1.4347,
      "step": 725
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00065,
      "loss": 1.2039,
      "step": 726
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00065,
      "loss": 1.081,
      "step": 727
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00065,
      "loss": 1.1252,
      "step": 728
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00065,
      "loss": 0.9198,
      "step": 729
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00065,
      "loss": 1.3106,
      "step": 730
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00065,
      "loss": 1.3563,
      "step": 731
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00065,
      "loss": 1.0198,
      "step": 732
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00065,
      "loss": 1.2724,
      "step": 733
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00065,
      "loss": 1.292,
      "step": 734
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00065,
      "loss": 1.0309,
      "step": 735
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00065,
      "loss": 1.1085,
      "step": 736
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00065,
      "loss": 1.2547,
      "step": 737
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00065,
      "loss": 1.2698,
      "step": 738
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00065,
      "loss": 1.1547,
      "step": 739
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00065,
      "loss": 1.0792,
      "step": 740
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00065,
      "loss": 1.2426,
      "step": 741
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00065,
      "loss": 1.2593,
      "step": 742
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00065,
      "loss": 0.9767,
      "step": 743
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00065,
      "loss": 1.2165,
      "step": 744
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00065,
      "loss": 1.2162,
      "step": 745
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00065,
      "loss": 1.0064,
      "step": 746
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00065,
      "loss": 1.2363,
      "step": 747
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00065,
      "loss": 0.9385,
      "step": 748
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00065,
      "loss": 0.832,
      "step": 749
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00065,
      "loss": 1.4107,
      "step": 750
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00065,
      "loss": 1.2246,
      "step": 751
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00065,
      "loss": 1.3015,
      "step": 752
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00065,
      "loss": 1.2943,
      "step": 753
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00065,
      "loss": 1.1899,
      "step": 754
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00065,
      "loss": 1.3176,
      "step": 755
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00065,
      "loss": 1.2133,
      "step": 756
    },
    {
      "epoch": 1.79,
      "eval_loss": 1.590731143951416,
      "eval_runtime": 57.6066,
      "eval_samples_per_second": 8.68,
      "eval_steps_per_second": 4.34,
      "step": 756
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00065,
      "loss": 1.4054,
      "step": 757
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00065,
      "loss": 1.0306,
      "step": 758
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00065,
      "loss": 0.9219,
      "step": 759
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00065,
      "loss": 1.3537,
      "step": 760
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00065,
      "loss": 1.1529,
      "step": 761
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00065,
      "loss": 1.1553,
      "step": 762
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00065,
      "loss": 1.1097,
      "step": 763
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00065,
      "loss": 1.2209,
      "step": 764
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00065,
      "loss": 1.2093,
      "step": 765
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00065,
      "loss": 1.1674,
      "step": 766
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00065,
      "loss": 1.1438,
      "step": 767
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00065,
      "loss": 1.5192,
      "step": 768
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00065,
      "loss": 1.1563,
      "step": 769
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00065,
      "loss": 1.3319,
      "step": 770
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00065,
      "loss": 1.2713,
      "step": 771
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00065,
      "loss": 1.0709,
      "step": 772
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00065,
      "loss": 0.9308,
      "step": 773
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00065,
      "loss": 1.3031,
      "step": 774
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00065,
      "loss": 1.1558,
      "step": 775
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00065,
      "loss": 0.9799,
      "step": 776
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00065,
      "loss": 1.1577,
      "step": 777
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00065,
      "loss": 1.1936,
      "step": 778
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00065,
      "loss": 1.266,
      "step": 779
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00065,
      "loss": 1.1129,
      "step": 780
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00065,
      "loss": 1.1319,
      "step": 781
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00065,
      "loss": 1.134,
      "step": 782
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00065,
      "loss": 1.1684,
      "step": 783
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00065,
      "loss": 1.2268,
      "step": 784
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00065,
      "loss": 1.1524,
      "step": 785
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00065,
      "loss": 1.0566,
      "step": 786
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00065,
      "loss": 1.1185,
      "step": 787
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00065,
      "loss": 1.0199,
      "step": 788
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00065,
      "loss": 1.041,
      "step": 789
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00065,
      "loss": 1.2404,
      "step": 790
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00065,
      "loss": 1.2778,
      "step": 791
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00065,
      "loss": 1.1633,
      "step": 792
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00065,
      "loss": 1.181,
      "step": 793
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00065,
      "loss": 1.2332,
      "step": 794
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00065,
      "loss": 1.148,
      "step": 795
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00065,
      "loss": 1.2897,
      "step": 796
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00065,
      "loss": 1.358,
      "step": 797
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00065,
      "loss": 1.0327,
      "step": 798
    },
    {
      "epoch": 1.89,
      "eval_loss": 1.6087443828582764,
      "eval_runtime": 57.7758,
      "eval_samples_per_second": 8.654,
      "eval_steps_per_second": 4.327,
      "step": 798
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00065,
      "loss": 1.3078,
      "step": 799
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00065,
      "loss": 1.2684,
      "step": 800
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00065,
      "loss": 1.3746,
      "step": 801
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00065,
      "loss": 1.2452,
      "step": 802
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00065,
      "loss": 1.2579,
      "step": 803
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00065,
      "loss": 0.9371,
      "step": 804
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00065,
      "loss": 1.2245,
      "step": 805
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00065,
      "loss": 1.1344,
      "step": 806
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00065,
      "loss": 1.3045,
      "step": 807
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00065,
      "loss": 1.1151,
      "step": 808
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00065,
      "loss": 1.1183,
      "step": 809
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00065,
      "loss": 1.1539,
      "step": 810
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00065,
      "loss": 0.8803,
      "step": 811
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00065,
      "loss": 1.0764,
      "step": 812
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00065,
      "loss": 1.2668,
      "step": 813
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00065,
      "loss": 1.2089,
      "step": 814
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00065,
      "loss": 1.2211,
      "step": 815
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00065,
      "loss": 1.301,
      "step": 816
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00065,
      "loss": 1.0924,
      "step": 817
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00065,
      "loss": 1.1627,
      "step": 818
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00065,
      "loss": 1.318,
      "step": 819
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00065,
      "loss": 1.0976,
      "step": 820
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00065,
      "loss": 1.4353,
      "step": 821
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00065,
      "loss": 1.3045,
      "step": 822
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00065,
      "loss": 1.276,
      "step": 823
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00065,
      "loss": 1.0738,
      "step": 824
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00065,
      "loss": 1.0885,
      "step": 825
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00065,
      "loss": 1.1512,
      "step": 826
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00065,
      "loss": 1.2892,
      "step": 827
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00065,
      "loss": 1.195,
      "step": 828
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00065,
      "loss": 1.1476,
      "step": 829
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00065,
      "loss": 1.1692,
      "step": 830
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00065,
      "loss": 1.2677,
      "step": 831
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00065,
      "loss": 1.2011,
      "step": 832
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00065,
      "loss": 1.1611,
      "step": 833
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00065,
      "loss": 1.5293,
      "step": 834
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00065,
      "loss": 1.1689,
      "step": 835
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00065,
      "loss": 1.1902,
      "step": 836
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00065,
      "loss": 1.0793,
      "step": 837
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00065,
      "loss": 1.2446,
      "step": 838
    }
  ],
  "logging_steps": 1,
  "max_steps": 838,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 5.706134946054144e+17,
  "trial_name": null,
  "trial_params": null
}