{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9996640913671482,
  "eval_steps": 100,
  "global_step": 744,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.4925,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.5144,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.3874,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.8667,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.5413,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.3561,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.6307,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.6405,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.5505,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.3125,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.3672,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.5262,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.6935,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.4954,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.4848,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.4264,
      "step": 16
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.473,
      "step": 17
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.4026,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.5937,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.6744,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.3461,
      "step": 21
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.4358,
      "step": 22
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.2995,
      "step": 23
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.4141,
      "step": 24
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.6971,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.4573,
      "step": 26
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.3961,
      "step": 27
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.2911,
      "step": 28
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5642,
      "step": 29
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.6783,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.6658,
      "step": 31
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.6881,
      "step": 32
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5346,
      "step": 33
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.4087,
      "step": 34
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.3902,
      "step": 35
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.5317,
      "step": 36
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.902,
      "step": 37
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.5535,
      "step": 38
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.2245,
      "step": 39
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.5001,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.3615,
      "step": 41
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.3751,
      "step": 42
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.4114,
      "step": 43
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.4872,
      "step": 44
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.1861,
      "step": 45
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.4556,
      "step": 46
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.4738,
      "step": 47
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.5168,
      "step": 48
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.4411,
      "step": 49
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.4251,
      "step": 50
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.2558,
      "step": 51
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.3872,
      "step": 52
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.3716,
      "step": 53
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.2279,
      "step": 54
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.378,
      "step": 55
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.4844,
      "step": 56
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.5299,
      "step": 57
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.5403,
      "step": 58
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.653,
      "step": 59
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.7322,
      "step": 60
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.3715,
      "step": 61
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.5525,
      "step": 62
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.1855,
      "step": 63
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.6929,
      "step": 64
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.3304,
      "step": 65
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.4673,
      "step": 66
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.3078,
      "step": 67
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.5174,
      "step": 68
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.2391,
      "step": 69
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.1477,
      "step": 70
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.5104,
      "step": 71
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.3076,
      "step": 72
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.4435,
      "step": 73
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.622,
      "step": 74
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.5879,
      "step": 75
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.375,
      "step": 76
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.5987,
      "step": 77
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.4196,
      "step": 78
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.291,
      "step": 79
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.3158,
      "step": 80
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.5917,
      "step": 81
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.5557,
      "step": 82
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.6552,
      "step": 83
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.2357,
      "step": 84
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.2287,
      "step": 85
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.4418,
      "step": 86
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.6311,
      "step": 87
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.4767,
      "step": 88
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.5289,
      "step": 89
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.3354,
      "step": 90
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.3328,
      "step": 91
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.319,
      "step": 92
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.382,
      "step": 93
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.6372,
      "step": 94
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.6074,
      "step": 95
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.3375,
      "step": 96
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.3432,
      "step": 97
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.4305,
      "step": 98
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.2407,
      "step": 99
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.5083,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.4049460887908936,
      "eval_runtime": 441.5212,
      "eval_samples_per_second": 1.563,
      "eval_steps_per_second": 0.392,
      "step": 100
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.4292,
      "step": 101
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.3542,
      "step": 102
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.4069,
      "step": 103
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.4706,
      "step": 104
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.3688,
      "step": 105
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.4376,
      "step": 106
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.4636,
      "step": 107
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.5471,
      "step": 108
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.4346,
      "step": 109
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.2338,
      "step": 110
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.4768,
      "step": 111
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.432,
      "step": 112
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.2932,
      "step": 113
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.6056,
      "step": 114
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.2941,
      "step": 115
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.4151,
      "step": 116
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.5091,
      "step": 117
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.3322,
      "step": 118
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.5314,
      "step": 119
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.5164,
      "step": 120
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.7211,
      "step": 121
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.2817,
      "step": 122
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.3317,
      "step": 123
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.5745,
      "step": 124
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.2308,
      "step": 125
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.411,
      "step": 126
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.2042,
      "step": 127
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.4981,
      "step": 128
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.4421,
      "step": 129
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.2531,
      "step": 130
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.1973,
      "step": 131
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.6006,
      "step": 132
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.594,
      "step": 133
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.4344,
      "step": 134
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.554,
      "step": 135
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.2604,
      "step": 136
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.3399,
      "step": 137
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.3839,
      "step": 138
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.4957,
      "step": 139
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.3904,
      "step": 140
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.6935,
      "step": 141
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.1986,
      "step": 142
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.5167,
      "step": 143
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.5019,
      "step": 144
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.3443,
      "step": 145
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.21,
      "step": 146
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.8859,
      "step": 147
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.5173,
      "step": 148
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.2812,
      "step": 149
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.5561,
      "step": 150
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.511,
      "step": 151
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.6042,
      "step": 152
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.2779,
      "step": 153
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.3322,
      "step": 154
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.4381,
      "step": 155
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.6009,
      "step": 156
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.5746,
      "step": 157
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.5367,
      "step": 158
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.586,
      "step": 159
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.3541,
      "step": 160
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.4011,
      "step": 161
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.6345,
      "step": 162
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.691,
      "step": 163
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.5831,
      "step": 164
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.3157,
      "step": 165
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.3137,
      "step": 166
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.0595,
      "step": 167
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.2418,
      "step": 168
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.2534,
      "step": 169
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.3005,
      "step": 170
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.4944,
      "step": 171
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.3034,
      "step": 172
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.4854,
      "step": 173
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.3637,
      "step": 174
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.4306,
      "step": 175
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.6367,
      "step": 176
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.2033,
      "step": 177
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.5012,
      "step": 178
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.4991,
      "step": 179
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.2487,
      "step": 180
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.4416,
      "step": 181
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.3695,
      "step": 182
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.0741,
      "step": 183
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.4816,
      "step": 184
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.3346,
      "step": 185
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.4782,
      "step": 186
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.4808,
      "step": 187
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.4079,
      "step": 188
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.3433,
      "step": 189
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.6758,
      "step": 190
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.3544,
      "step": 191
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.1564,
      "step": 192
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.3612,
      "step": 193
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.3226,
      "step": 194
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.365,
      "step": 195
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.4344,
      "step": 196
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.2987,
      "step": 197
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.3551,
      "step": 198
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.2806,
      "step": 199
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.2726,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.3933924436569214,
      "eval_runtime": 441.7187,
      "eval_samples_per_second": 1.562,
      "eval_steps_per_second": 0.392,
      "step": 200
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.4918,
      "step": 201
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.6278,
      "step": 202
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.2418,
      "step": 203
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.4545,
      "step": 204
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.4311,
      "step": 205
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.294,
      "step": 206
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.3711,
      "step": 207
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.2889,
      "step": 208
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.483,
      "step": 209
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.4393,
      "step": 210
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.45,
      "step": 211
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.1867,
      "step": 212
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.2354,
      "step": 213
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.5312,
      "step": 214
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.2599,
      "step": 215
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.316,
      "step": 216
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.5382,
      "step": 217
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.581,
      "step": 218
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.2455,
      "step": 219
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.6401,
      "step": 220
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.5745,
      "step": 221
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.3209,
      "step": 222
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.5797,
      "step": 223
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.1661,
      "step": 224
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.3139,
      "step": 225
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.5553,
      "step": 226
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.3963,
      "step": 227
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.4288,
      "step": 228
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.621,
      "step": 229
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.3305,
      "step": 230
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.4525,
      "step": 231
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.5967,
      "step": 232
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.2565,
      "step": 233
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.387,
      "step": 234
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.2859,
      "step": 235
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.4987,
      "step": 236
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.3214,
      "step": 237
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.2937,
      "step": 238
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.1512,
      "step": 239
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.621,
      "step": 240
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.4683,
      "step": 241
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.1805,
      "step": 242
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.238,
      "step": 243
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.5211,
      "step": 244
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.4926,
      "step": 245
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.5397,
      "step": 246
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.5255,
      "step": 247
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.4253,
      "step": 248
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.3297,
      "step": 249
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.2316,
      "step": 250
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.429,
      "step": 251
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.2792,
      "step": 252
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.5727,
      "step": 253
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.2032,
      "step": 254
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.4153,
      "step": 255
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.2724,
      "step": 256
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.4178,
      "step": 257
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.3131,
      "step": 258
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.6291,
      "step": 259
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.1144,
      "step": 260
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.425,
      "step": 261
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.5624,
      "step": 262
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.4533,
      "step": 263
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.209,
      "step": 264
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.6137,
      "step": 265
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.2784,
      "step": 266
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.4203,
      "step": 267
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.2836,
      "step": 268
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.4429,
      "step": 269
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.5235,
      "step": 270
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.2781,
      "step": 271
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.2376,
      "step": 272
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.4518,
      "step": 273
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.2264,
      "step": 274
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.3288,
      "step": 275
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.2508,
      "step": 276
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.971,
      "step": 277
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.1255,
      "step": 278
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.6362,
      "step": 279
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.2952,
      "step": 280
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.3496,
      "step": 281
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.2185,
      "step": 282
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.4449,
      "step": 283
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.7358,
      "step": 284
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.3203,
      "step": 285
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.3007,
      "step": 286
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.6082,
      "step": 287
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.2585,
      "step": 288
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.9611,
      "step": 289
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.9947,
      "step": 290
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.4437,
      "step": 291
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.269,
      "step": 292
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.4283,
      "step": 293
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.5007,
      "step": 294
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.3605,
      "step": 295
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.3069,
      "step": 296
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.0557,
      "step": 297
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.2875,
      "step": 298
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.3322,
      "step": 299
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.3506,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.3853427171707153,
      "eval_runtime": 441.2843,
      "eval_samples_per_second": 1.564,
      "eval_steps_per_second": 0.392,
      "step": 300
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.6926,
      "step": 301
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.5522,
      "step": 302
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.3527,
      "step": 303
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.4214,
      "step": 304
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.3068,
      "step": 305
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.5722,
      "step": 306
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.2584,
      "step": 307
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.5793,
      "step": 308
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.3942,
      "step": 309
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.5487,
      "step": 310
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.3595,
      "step": 311
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.271,
      "step": 312
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.6985,
      "step": 313
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.2786,
      "step": 314
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.7656,
      "step": 315
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.5713,
      "step": 316
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.3235,
      "step": 317
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.3829,
      "step": 318
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.4187,
      "step": 319
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.3544,
      "step": 320
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.5638,
      "step": 321
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.269,
      "step": 322
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.4917,
      "step": 323
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.4635,
      "step": 324
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.3772,
      "step": 325
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.3561,
      "step": 326
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.3586,
      "step": 327
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.1845,
      "step": 328
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.4362,
      "step": 329
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.1881,
      "step": 330
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.3098,
      "step": 331
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.4673,
      "step": 332
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.4496,
      "step": 333
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.5788,
      "step": 334
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.2582,
      "step": 335
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.5255,
      "step": 336
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.7017,
      "step": 337
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.7231,
      "step": 338
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.4447,
      "step": 339
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.3386,
      "step": 340
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.3791,
      "step": 341
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.3071,
      "step": 342
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.2949,
      "step": 343
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.3033,
      "step": 344
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.4243,
      "step": 345
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.3747,
      "step": 346
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.427,
      "step": 347
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.8376,
      "step": 348
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.7076,
      "step": 349
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.3889,
      "step": 350
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.4117,
      "step": 351
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.4598,
      "step": 352
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.2908,
      "step": 353
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.4376,
      "step": 354
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.5732,
      "step": 355
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.3376,
      "step": 356
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.3073,
      "step": 357
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.592,
      "step": 358
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.5166,
      "step": 359
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.2739,
      "step": 360
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.3329,
      "step": 361
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.5451,
      "step": 362
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.3675,
      "step": 363
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.1963,
      "step": 364
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.2345,
      "step": 365
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.705,
      "step": 366
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.3867,
      "step": 367
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.3674,
      "step": 368
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.4713,
      "step": 369
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.2732,
      "step": 370
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.3148,
      "step": 371
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.2673,
      "step": 372
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.2504,
      "step": 373
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.4689,
      "step": 374
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.3824,
      "step": 375
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.2314,
      "step": 376
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.6187,
      "step": 377
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.27,
      "step": 378
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.4199,
      "step": 379
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.5226,
      "step": 380
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.4534,
      "step": 381
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.1076,
      "step": 382
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.438,
      "step": 383
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.2989,
      "step": 384
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.2926,
      "step": 385
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.2179,
      "step": 386
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.3079,
      "step": 387
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.3239,
      "step": 388
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.4648,
      "step": 389
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.309,
      "step": 390
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.2591,
      "step": 391
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.2762,
      "step": 392
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.3492,
      "step": 393
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.4163,
      "step": 394
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.6296,
      "step": 395
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.3282,
      "step": 396
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.3957,
      "step": 397
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.4954,
      "step": 398
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.0683,
      "step": 399
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.4019,
      "step": 400
    },
    {
      "epoch": 0.54,
      "eval_loss": 1.3792049884796143,
      "eval_runtime": 441.0954,
      "eval_samples_per_second": 1.564,
      "eval_steps_per_second": 0.392,
      "step": 400
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.4533,
      "step": 401
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.5101,
      "step": 402
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.3062,
      "step": 403
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.4517,
      "step": 404
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.4478,
      "step": 405
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.4938,
      "step": 406
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.3137,
      "step": 407
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.254,
      "step": 408
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.4163,
      "step": 409
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.7432,
      "step": 410
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.5261,
      "step": 411
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.2845,
      "step": 412
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.2449,
      "step": 413
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.68,
      "step": 414
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 2.0014,
      "step": 415
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.3557,
      "step": 416
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.8836,
      "step": 417
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.496,
      "step": 418
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.283,
      "step": 419
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.4569,
      "step": 420
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.455,
      "step": 421
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.4418,
      "step": 422
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.4152,
      "step": 423
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.3991,
      "step": 424
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.194,
      "step": 425
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.4039,
      "step": 426
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.4844,
      "step": 427
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.5439,
      "step": 428
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.3603,
      "step": 429
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.4299,
      "step": 430
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.6496,
      "step": 431
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.447,
      "step": 432
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.1043,
      "step": 433
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.5972,
      "step": 434
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.5962,
      "step": 435
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.4682,
      "step": 436
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.4733,
      "step": 437
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.5552,
      "step": 438
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.3559,
      "step": 439
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.4644,
      "step": 440
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.3019,
      "step": 441
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.3299,
      "step": 442
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.2782,
      "step": 443
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.4651,
      "step": 444
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.3575,
      "step": 445
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.4675,
      "step": 446
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.2348,
      "step": 447
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.3047,
      "step": 448
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.3681,
      "step": 449
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.1474,
      "step": 450
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.328,
      "step": 451
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.5314,
      "step": 452
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.2926,
      "step": 453
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.4488,
      "step": 454
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.5578,
      "step": 455
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.2888,
      "step": 456
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.4423,
      "step": 457
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.5929,
      "step": 458
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.5411,
      "step": 459
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.2644,
      "step": 460
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.3733,
      "step": 461
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.6307,
      "step": 462
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.492,
      "step": 463
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.4052,
      "step": 464
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.2535,
      "step": 465
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.6804,
      "step": 466
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.306,
      "step": 467
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.3982,
      "step": 468
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.3402,
      "step": 469
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.2094,
      "step": 470
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.3615,
      "step": 471
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.3427,
      "step": 472
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.4148,
      "step": 473
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.4688,
      "step": 474
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.2682,
      "step": 475
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.3589,
      "step": 476
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.2851,
      "step": 477
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.3374,
      "step": 478
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.3439,
      "step": 479
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.4842,
      "step": 480
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.5513,
      "step": 481
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.48,
      "step": 482
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.2883,
      "step": 483
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.4636,
      "step": 484
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.4196,
      "step": 485
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.3489,
      "step": 486
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.3909,
      "step": 487
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.2938,
      "step": 488
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.3898,
      "step": 489
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.6946,
      "step": 490
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.528,
      "step": 491
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.4905,
      "step": 492
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.2424,
      "step": 493
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.475,
      "step": 494
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.3993,
      "step": 495
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.3028,
      "step": 496
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.4869,
      "step": 497
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.6581,
      "step": 498
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.4166,
      "step": 499
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.9966,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.3746258020401,
      "eval_runtime": 440.7359,
      "eval_samples_per_second": 1.566,
      "eval_steps_per_second": 0.393,
      "step": 500
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.2995,
      "step": 501
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.2557,
      "step": 502
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.2462,
      "step": 503
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.5088,
      "step": 504
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.6118,
      "step": 505
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.1935,
      "step": 506
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.4858,
      "step": 507
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.6135,
      "step": 508
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.329,
      "step": 509
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.6557,
      "step": 510
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.5889,
      "step": 511
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.3667,
      "step": 512
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.7799,
      "step": 513
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.3817,
      "step": 514
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.4662,
      "step": 515
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.4186,
      "step": 516
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.4437,
      "step": 517
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.3603,
      "step": 518
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.6023,
      "step": 519
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.6167,
      "step": 520
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.5113,
      "step": 521
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.3075,
      "step": 522
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.5514,
      "step": 523
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.6074,
      "step": 524
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.3738,
      "step": 525
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.766,
      "step": 526
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.1326,
      "step": 527
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.6338,
      "step": 528
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.3261,
      "step": 529
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.4421,
      "step": 530
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.1819,
      "step": 531
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.3441,
      "step": 532
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.2674,
      "step": 533
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.0905,
      "step": 534
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.7163,
      "step": 535
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.4708,
      "step": 536
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.2213,
      "step": 537
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.4032,
      "step": 538
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.4613,
      "step": 539
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.1315,
      "step": 540
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.4049,
      "step": 541
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.2075,
      "step": 542
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.2874,
      "step": 543
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.9946,
      "step": 544
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.2956,
      "step": 545
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.5638,
      "step": 546
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.4105,
      "step": 547
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.2435,
      "step": 548
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.3654,
      "step": 549
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.7154,
      "step": 550
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.2973,
      "step": 551
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.2755,
      "step": 552
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.5998,
      "step": 553
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.4952,
      "step": 554
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.0843,
      "step": 555
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.4332,
      "step": 556
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.3382,
      "step": 557
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.6568,
      "step": 558
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.4465,
      "step": 559
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.7039,
      "step": 560
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.3814,
      "step": 561
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.3159,
      "step": 562
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.2362,
      "step": 563
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.3358,
      "step": 564
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.5882,
      "step": 565
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.4905,
      "step": 566
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.2225,
      "step": 567
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.8351,
      "step": 568
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.6711,
      "step": 569
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.3793,
      "step": 570
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.6333,
      "step": 571
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.3526,
      "step": 572
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.6924,
      "step": 573
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.3053,
      "step": 574
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.0704,
      "step": 575
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.2368,
      "step": 576
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.2332,
      "step": 577
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.4293,
      "step": 578
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.4907,
      "step": 579
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.7018,
      "step": 580
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.4077,
      "step": 581
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.3053,
      "step": 582
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.3998,
      "step": 583
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.2415,
      "step": 584
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.3822,
      "step": 585
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.3607,
      "step": 586
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.483,
      "step": 587
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.6341,
      "step": 588
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.5254,
      "step": 589
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.5788,
      "step": 590
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.3189,
      "step": 591
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.4361,
      "step": 592
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.3071,
      "step": 593
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.4418,
      "step": 594
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.4925,
      "step": 595
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.4968,
      "step": 596
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.6274,
      "step": 597
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.7317,
      "step": 598
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.3714,
      "step": 599
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.3965,
      "step": 600
    },
    {
      "epoch": 0.81,
      "eval_loss": 1.3718293905258179,
      "eval_runtime": 440.6925,
      "eval_samples_per_second": 1.566,
      "eval_steps_per_second": 0.393,
      "step": 600
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.5125,
      "step": 601
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.3987,
      "step": 602
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.3577,
      "step": 603
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.3159,
      "step": 604
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.197,
      "step": 605
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.2876,
      "step": 606
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.3119,
      "step": 607
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.6125,
      "step": 608
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.2761,
      "step": 609
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.7309,
      "step": 610
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.4789,
      "step": 611
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.3247,
      "step": 612
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.3337,
      "step": 613
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.5705,
      "step": 614
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.3059,
      "step": 615
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.4452,
      "step": 616
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.6685,
      "step": 617
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.3522,
      "step": 618
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.1878,
      "step": 619
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.294,
      "step": 620
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.613,
      "step": 621
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.3739,
      "step": 622
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.4221,
      "step": 623
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.5149,
      "step": 624
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.3332,
      "step": 625
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.6892,
      "step": 626
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.1803,
      "step": 627
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.4843,
      "step": 628
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.5341,
      "step": 629
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.2203,
      "step": 630
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.4969,
      "step": 631
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.5029,
      "step": 632
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.2501,
      "step": 633
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.5621,
      "step": 634
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.4174,
      "step": 635
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.3022,
      "step": 636
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.4917,
      "step": 637
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.4227,
      "step": 638
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.6772,
      "step": 639
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.4155,
      "step": 640
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.4245,
      "step": 641
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.3916,
      "step": 642
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.2547,
      "step": 643
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.6559,
      "step": 644
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.3959,
      "step": 645
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.6932,
      "step": 646
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.412,
      "step": 647
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.4734,
      "step": 648
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.4544,
      "step": 649
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.3993,
      "step": 650
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.4305,
      "step": 651
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.4364,
      "step": 652
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.481,
      "step": 653
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.3716,
      "step": 654
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.4739,
      "step": 655
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.2871,
      "step": 656
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.3972,
      "step": 657
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.1626,
      "step": 658
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.7518,
      "step": 659
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.5674,
      "step": 660
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.5055,
      "step": 661
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.1769,
      "step": 662
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.4755,
      "step": 663
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.4907,
      "step": 664
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.3265,
      "step": 665
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.3154,
      "step": 666
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.3409,
      "step": 667
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.378,
      "step": 668
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.4048,
      "step": 669
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.4964,
      "step": 670
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.6212,
      "step": 671
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.3127,
      "step": 672
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.4169,
      "step": 673
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.2498,
      "step": 674
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.4045,
      "step": 675
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.5758,
      "step": 676
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.3823,
      "step": 677
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.6601,
      "step": 678
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.5562,
      "step": 679
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.1358,
      "step": 680
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.1325,
      "step": 681
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.4813,
      "step": 682
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.335,
      "step": 683
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.614,
      "step": 684
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.448,
      "step": 685
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.3724,
      "step": 686
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.4873,
      "step": 687
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.4579,
      "step": 688
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.4331,
      "step": 689
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.6089,
      "step": 690
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.4011,
      "step": 691
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.3296,
      "step": 692
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.4143,
      "step": 693
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.4736,
      "step": 694
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.406,
      "step": 695
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.5285,
      "step": 696
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.2369,
      "step": 697
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.3969,
      "step": 698
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.4348,
      "step": 699
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.5787,
      "step": 700
    },
    {
      "epoch": 0.94,
      "eval_loss": 1.3678728342056274,
      "eval_runtime": 440.729,
      "eval_samples_per_second": 1.566,
      "eval_steps_per_second": 0.393,
      "step": 700
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.3193,
      "step": 701
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.2932,
      "step": 702
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.4183,
      "step": 703
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.5328,
      "step": 704
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.4639,
      "step": 705
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.3475,
      "step": 706
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.3079,
      "step": 707
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.2619,
      "step": 708
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.5947,
      "step": 709
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.1239,
      "step": 710
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.129,
      "step": 711
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.4643,
      "step": 712
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.5388,
      "step": 713
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.4328,
      "step": 714
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.4876,
      "step": 715
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.7079,
      "step": 716
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.4483,
      "step": 717
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.4254,
      "step": 718
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 1.5946,
      "step": 719
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 1.5887,
      "step": 720
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 1.2913,
      "step": 721
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 1.612,
      "step": 722
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 1.2837,
      "step": 723
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 1.3668,
      "step": 724
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 1.3397,
      "step": 725
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.5159,
      "step": 726
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.7313,
      "step": 727
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.3203,
      "step": 728
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.3875,
      "step": 729
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.4126,
      "step": 730
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.5195,
      "step": 731
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.5687,
      "step": 732
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.7246,
      "step": 733
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 1.392,
      "step": 734
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 1.3392,
      "step": 735
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 1.1387,
      "step": 736
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 1.4896,
      "step": 737
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 1.5993,
      "step": 738
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 1.4317,
      "step": 739
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 1.0769,
      "step": 740
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.7145,
      "step": 741
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.4863,
      "step": 742
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.1356,
      "step": 743
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.3969,
      "step": 744
    }
  ],
  "logging_steps": 1,
  "max_steps": 1488,
  "num_train_epochs": 2,
  "save_steps": 250,
  "total_flos": 5.095548469787443e+16,
  "trial_name": null,
  "trial_params": null
}