{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9993281827342964,
  "eval_steps": 100,
  "global_step": 1488,
  "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
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.2919,
      "step": 745
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.5433,
      "step": 746
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.5083,
      "step": 747
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 1.334,
      "step": 748
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 1.5422,
      "step": 749
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 1.319,
      "step": 750
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 1.4018,
      "step": 751
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 1.2832,
      "step": 752
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 1.2947,
      "step": 753
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 1.5817,
      "step": 754
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 1.4975,
      "step": 755
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.2444,
      "step": 756
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.2996,
      "step": 757
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.1947,
      "step": 758
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.3727,
      "step": 759
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.3889,
      "step": 760
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.2024,
      "step": 761
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.2316,
      "step": 762
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 1.2697,
      "step": 763
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 1.523,
      "step": 764
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 1.3076,
      "step": 765
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 1.3052,
      "step": 766
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 1.3359,
      "step": 767
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 1.3051,
      "step": 768
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 1.3357,
      "step": 769
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 1.6156,
      "step": 770
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 1.5586,
      "step": 771
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 1.3806,
      "step": 772
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 1.1378,
      "step": 773
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 1.1616,
      "step": 774
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 1.4602,
      "step": 775
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 1.534,
      "step": 776
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 1.4488,
      "step": 777
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.2256,
      "step": 778
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.3261,
      "step": 779
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.1014,
      "step": 780
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.2217,
      "step": 781
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.2161,
      "step": 782
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.2762,
      "step": 783
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.4702,
      "step": 784
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.2699,
      "step": 785
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 1.1117,
      "step": 786
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 1.312,
      "step": 787
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 1.365,
      "step": 788
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 1.5535,
      "step": 789
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 1.2214,
      "step": 790
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 1.3806,
      "step": 791
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 1.1784,
      "step": 792
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.2476,
      "step": 793
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.5246,
      "step": 794
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.3372,
      "step": 795
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.4609,
      "step": 796
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.285,
      "step": 797
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.1798,
      "step": 798
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.306,
      "step": 799
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.15,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.3677575588226318,
      "eval_runtime": 440.7099,
      "eval_samples_per_second": 1.566,
      "eval_steps_per_second": 0.393,
      "step": 800
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 1.1947,
      "step": 801
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 1.0357,
      "step": 802
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 1.4778,
      "step": 803
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 1.7511,
      "step": 804
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 1.4218,
      "step": 805
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 1.6177,
      "step": 806
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 1.3376,
      "step": 807
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.2762,
      "step": 808
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.3848,
      "step": 809
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.2592,
      "step": 810
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.3915,
      "step": 811
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.431,
      "step": 812
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.1514,
      "step": 813
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.3343,
      "step": 814
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.2062,
      "step": 815
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.4357,
      "step": 816
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.2402,
      "step": 817
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.2887,
      "step": 818
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.2743,
      "step": 819
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.1048,
      "step": 820
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.1726,
      "step": 821
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.221,
      "step": 822
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 1.602,
      "step": 823
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 1.4228,
      "step": 824
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 2.0065,
      "step": 825
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 1.458,
      "step": 826
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 1.1873,
      "step": 827
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 1.4971,
      "step": 828
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 1.3096,
      "step": 829
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 1.11,
      "step": 830
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 1.3198,
      "step": 831
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 1.3915,
      "step": 832
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 1.3006,
      "step": 833
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 1.0331,
      "step": 834
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 1.2421,
      "step": 835
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 1.5308,
      "step": 836
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 1.2836,
      "step": 837
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.2247,
      "step": 838
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.2224,
      "step": 839
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.5872,
      "step": 840
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.0371,
      "step": 841
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.4302,
      "step": 842
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.3575,
      "step": 843
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.3146,
      "step": 844
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.2627,
      "step": 845
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.076,
      "step": 846
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.2724,
      "step": 847
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.2437,
      "step": 848
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.3553,
      "step": 849
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.2449,
      "step": 850
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.1405,
      "step": 851
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.4259,
      "step": 852
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.5813,
      "step": 853
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.3361,
      "step": 854
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.3625,
      "step": 855
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.4001,
      "step": 856
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.1658,
      "step": 857
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.5966,
      "step": 858
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.5088,
      "step": 859
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.5277,
      "step": 860
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.2261,
      "step": 861
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.4808,
      "step": 862
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.1739,
      "step": 863
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.4502,
      "step": 864
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.1911,
      "step": 865
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.1881,
      "step": 866
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.0674,
      "step": 867
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 1.1532,
      "step": 868
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 1.2834,
      "step": 869
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 1.5217,
      "step": 870
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 1.1844,
      "step": 871
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 1.2429,
      "step": 872
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 1.0879,
      "step": 873
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 1.1683,
      "step": 874
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 1.2037,
      "step": 875
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 1.2618,
      "step": 876
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 1.3206,
      "step": 877
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 1.2809,
      "step": 878
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 1.365,
      "step": 879
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 1.3073,
      "step": 880
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 1.2345,
      "step": 881
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.6275,
      "step": 882
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.5066,
      "step": 883
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.1937,
      "step": 884
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.3564,
      "step": 885
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.6352,
      "step": 886
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.1704,
      "step": 887
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.2581,
      "step": 888
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.0633,
      "step": 889
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.5518,
      "step": 890
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.2453,
      "step": 891
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.31,
      "step": 892
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.3263,
      "step": 893
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.5132,
      "step": 894
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.3313,
      "step": 895
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.2608,
      "step": 896
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.5914,
      "step": 897
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.153,
      "step": 898
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.2786,
      "step": 899
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.3718,
      "step": 900
    },
    {
      "epoch": 1.21,
      "eval_loss": 1.3679090738296509,
      "eval_runtime": 441.1195,
      "eval_samples_per_second": 1.564,
      "eval_steps_per_second": 0.392,
      "step": 900
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.3794,
      "step": 901
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.5578,
      "step": 902
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.1767,
      "step": 903
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.315,
      "step": 904
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.1859,
      "step": 905
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.2052,
      "step": 906
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.7529,
      "step": 907
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.1169,
      "step": 908
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.1596,
      "step": 909
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.3811,
      "step": 910
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.4279,
      "step": 911
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.0845,
      "step": 912
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.2444,
      "step": 913
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.384,
      "step": 914
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.1581,
      "step": 915
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.2748,
      "step": 916
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.6437,
      "step": 917
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.0892,
      "step": 918
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.2908,
      "step": 919
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.4642,
      "step": 920
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.4623,
      "step": 921
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.2658,
      "step": 922
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.4,
      "step": 923
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.1611,
      "step": 924
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.2565,
      "step": 925
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.3349,
      "step": 926
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.3631,
      "step": 927
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.2696,
      "step": 928
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.3536,
      "step": 929
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.4947,
      "step": 930
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.2843,
      "step": 931
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.4436,
      "step": 932
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.1468,
      "step": 933
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.5863,
      "step": 934
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.5449,
      "step": 935
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.2751,
      "step": 936
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.5183,
      "step": 937
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.4504,
      "step": 938
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.5116,
      "step": 939
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.2952,
      "step": 940
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.3791,
      "step": 941
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 1.4946,
      "step": 942
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 1.4403,
      "step": 943
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 1.4425,
      "step": 944
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 1.3892,
      "step": 945
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 1.3044,
      "step": 946
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 1.4824,
      "step": 947
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 1.4054,
      "step": 948
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.3686,
      "step": 949
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.2041,
      "step": 950
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.121,
      "step": 951
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.44,
      "step": 952
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.4409,
      "step": 953
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.2504,
      "step": 954
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.2117,
      "step": 955
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.7155,
      "step": 956
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 1.3399,
      "step": 957
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 1.7042,
      "step": 958
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 1.4062,
      "step": 959
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 1.1611,
      "step": 960
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 1.4469,
      "step": 961
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 1.3797,
      "step": 962
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 1.5105,
      "step": 963
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 1.4865,
      "step": 964
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 1.387,
      "step": 965
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 1.3679,
      "step": 966
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 1.1424,
      "step": 967
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 1.4388,
      "step": 968
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 1.3942,
      "step": 969
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 1.6341,
      "step": 970
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 1.39,
      "step": 971
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 1.1767,
      "step": 972
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 1.2075,
      "step": 973
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 1.3053,
      "step": 974
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 1.4537,
      "step": 975
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 1.4113,
      "step": 976
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 1.3142,
      "step": 977
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 1.4174,
      "step": 978
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 1.5839,
      "step": 979
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 1.2971,
      "step": 980
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 1.2725,
      "step": 981
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 1.47,
      "step": 982
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 1.3588,
      "step": 983
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 1.3894,
      "step": 984
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 1.3939,
      "step": 985
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 1.4603,
      "step": 986
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.2585,
      "step": 987
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.2395,
      "step": 988
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.2421,
      "step": 989
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.1592,
      "step": 990
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.2667,
      "step": 991
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.4541,
      "step": 992
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.6057,
      "step": 993
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 1.1897,
      "step": 994
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 1.509,
      "step": 995
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 1.4522,
      "step": 996
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 1.2399,
      "step": 997
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 1.1635,
      "step": 998
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 1.1552,
      "step": 999
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 1.4418,
      "step": 1000
    },
    {
      "epoch": 1.34,
      "eval_loss": 1.3678088188171387,
      "eval_runtime": 441.4739,
      "eval_samples_per_second": 1.563,
      "eval_steps_per_second": 0.392,
      "step": 1000
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 1.1923,
      "step": 1001
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 1.3366,
      "step": 1002
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 1.1317,
      "step": 1003
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 1.4476,
      "step": 1004
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 1.3219,
      "step": 1005
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 1.369,
      "step": 1006
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 1.371,
      "step": 1007
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 1.2578,
      "step": 1008
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 1.1183,
      "step": 1009
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 1.3804,
      "step": 1010
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 1.4636,
      "step": 1011
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 1.3415,
      "step": 1012
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 1.1886,
      "step": 1013
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 1.4885,
      "step": 1014
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 1.3055,
      "step": 1015
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 1.4117,
      "step": 1016
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 1.2618,
      "step": 1017
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 1.1925,
      "step": 1018
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 1.3595,
      "step": 1019
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 1.2616,
      "step": 1020
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 1.1189,
      "step": 1021
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 1.3254,
      "step": 1022
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 1.2167,
      "step": 1023
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 1.2809,
      "step": 1024
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 1.3476,
      "step": 1025
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 1.4129,
      "step": 1026
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 1.2267,
      "step": 1027
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 1.6052,
      "step": 1028
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 1.4775,
      "step": 1029
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 1.187,
      "step": 1030
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 1.3698,
      "step": 1031
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 1.1717,
      "step": 1032
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 1.8402,
      "step": 1033
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 1.1976,
      "step": 1034
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 1.347,
      "step": 1035
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 1.2805,
      "step": 1036
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 1.4477,
      "step": 1037
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 1.3046,
      "step": 1038
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 1.4053,
      "step": 1039
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 1.3046,
      "step": 1040
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 1.2518,
      "step": 1041
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 1.431,
      "step": 1042
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 1.429,
      "step": 1043
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 1.4043,
      "step": 1044
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 1.1474,
      "step": 1045
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 1.3556,
      "step": 1046
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 1.647,
      "step": 1047
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 1.1849,
      "step": 1048
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 1.2761,
      "step": 1049
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 1.3782,
      "step": 1050
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 1.2982,
      "step": 1051
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 1.1622,
      "step": 1052
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 1.4396,
      "step": 1053
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 1.378,
      "step": 1054
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 1.2696,
      "step": 1055
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 1.2721,
      "step": 1056
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 1.4046,
      "step": 1057
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 1.319,
      "step": 1058
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 1.178,
      "step": 1059
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 1.238,
      "step": 1060
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 1.115,
      "step": 1061
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 1.4159,
      "step": 1062
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 1.154,
      "step": 1063
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 1.3699,
      "step": 1064
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 1.079,
      "step": 1065
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 1.2242,
      "step": 1066
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 1.5618,
      "step": 1067
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 1.3733,
      "step": 1068
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 1.2149,
      "step": 1069
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 1.1893,
      "step": 1070
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 1.152,
      "step": 1071
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 1.3562,
      "step": 1072
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 1.4011,
      "step": 1073
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 1.5402,
      "step": 1074
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 1.3716,
      "step": 1075
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 1.5009,
      "step": 1076
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 1.4116,
      "step": 1077
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 1.2414,
      "step": 1078
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 1.6161,
      "step": 1079
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 1.355,
      "step": 1080
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 1.3738,
      "step": 1081
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 1.1093,
      "step": 1082
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 1.3203,
      "step": 1083
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 1.4463,
      "step": 1084
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 1.5392,
      "step": 1085
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 1.5114,
      "step": 1086
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 1.3433,
      "step": 1087
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 1.2575,
      "step": 1088
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 1.4886,
      "step": 1089
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 1.3443,
      "step": 1090
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.2855,
      "step": 1091
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.3652,
      "step": 1092
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.2876,
      "step": 1093
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.582,
      "step": 1094
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.5643,
      "step": 1095
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.3285,
      "step": 1096
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.4023,
      "step": 1097
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 1.3256,
      "step": 1098
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 1.2932,
      "step": 1099
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 1.4116,
      "step": 1100
    },
    {
      "epoch": 1.48,
      "eval_loss": 1.366713523864746,
      "eval_runtime": 441.6222,
      "eval_samples_per_second": 1.562,
      "eval_steps_per_second": 0.392,
      "step": 1100
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 1.3854,
      "step": 1101
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 1.4304,
      "step": 1102
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 1.2662,
      "step": 1103
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 1.1873,
      "step": 1104
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 1.3238,
      "step": 1105
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 1.2375,
      "step": 1106
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 1.3789,
      "step": 1107
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 1.5468,
      "step": 1108
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 1.4378,
      "step": 1109
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 1.0873,
      "step": 1110
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 1.3495,
      "step": 1111
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 1.55,
      "step": 1112
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 1.0154,
      "step": 1113
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 1.2741,
      "step": 1114
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 1.4508,
      "step": 1115
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 1.3113,
      "step": 1116
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 1.001,
      "step": 1117
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 1.4628,
      "step": 1118
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 1.4548,
      "step": 1119
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 1.2382,
      "step": 1120
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 1.3629,
      "step": 1121
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 1.4278,
      "step": 1122
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 1.2683,
      "step": 1123
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 1.3811,
      "step": 1124
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 1.1942,
      "step": 1125
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 1.4691,
      "step": 1126
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 1.4708,
      "step": 1127
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 1.4375,
      "step": 1128
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 1.6294,
      "step": 1129
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 1.2594,
      "step": 1130
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 1.094,
      "step": 1131
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 1.1028,
      "step": 1132
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 1.4801,
      "step": 1133
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 1.3524,
      "step": 1134
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 1.1655,
      "step": 1135
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 1.3726,
      "step": 1136
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 1.099,
      "step": 1137
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 1.4167,
      "step": 1138
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 1.6674,
      "step": 1139
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 1.2804,
      "step": 1140
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 1.2747,
      "step": 1141
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 1.6699,
      "step": 1142
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 1.5432,
      "step": 1143
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 1.3967,
      "step": 1144
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 1.2392,
      "step": 1145
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 1.2819,
      "step": 1146
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 1.2096,
      "step": 1147
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 1.4438,
      "step": 1148
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 1.2571,
      "step": 1149
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 1.1108,
      "step": 1150
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 1.6043,
      "step": 1151
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 1.2859,
      "step": 1152
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 1.6353,
      "step": 1153
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 1.2665,
      "step": 1154
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 1.1586,
      "step": 1155
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 1.3269,
      "step": 1156
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 1.3011,
      "step": 1157
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 1.3226,
      "step": 1158
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 1.4054,
      "step": 1159
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 1.1375,
      "step": 1160
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 1.0832,
      "step": 1161
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 1.4406,
      "step": 1162
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 1.5139,
      "step": 1163
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 1.3346,
      "step": 1164
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.2322,
      "step": 1165
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.2631,
      "step": 1166
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.5667,
      "step": 1167
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.2506,
      "step": 1168
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.1989,
      "step": 1169
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.4693,
      "step": 1170
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.1439,
      "step": 1171
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.3093,
      "step": 1172
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 1.1475,
      "step": 1173
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 1.3426,
      "step": 1174
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 1.273,
      "step": 1175
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 1.4933,
      "step": 1176
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 1.0848,
      "step": 1177
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 1.266,
      "step": 1178
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 1.2462,
      "step": 1179
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 1.4393,
      "step": 1180
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 1.0765,
      "step": 1181
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 1.0781,
      "step": 1182
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 1.5541,
      "step": 1183
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 1.3001,
      "step": 1184
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 1.6095,
      "step": 1185
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 1.1145,
      "step": 1186
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 1.3039,
      "step": 1187
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 1.2537,
      "step": 1188
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 1.3291,
      "step": 1189
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 1.3981,
      "step": 1190
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 1.2078,
      "step": 1191
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 1.2698,
      "step": 1192
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 1.288,
      "step": 1193
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 1.1577,
      "step": 1194
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 1.4555,
      "step": 1195
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 1.431,
      "step": 1196
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 1.3303,
      "step": 1197
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 1.4296,
      "step": 1198
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 1.0688,
      "step": 1199
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 1.4646,
      "step": 1200
    },
    {
      "epoch": 1.61,
      "eval_loss": 1.3646005392074585,
      "eval_runtime": 458.0769,
      "eval_samples_per_second": 1.506,
      "eval_steps_per_second": 0.378,
      "step": 1200
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 1.3529,
      "step": 1201
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 1.5106,
      "step": 1202
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 1.35,
      "step": 1203
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 1.3215,
      "step": 1204
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 1.1218,
      "step": 1205
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 1.2604,
      "step": 1206
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 1.5523,
      "step": 1207
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 1.4502,
      "step": 1208
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 1.3089,
      "step": 1209
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 1.5012,
      "step": 1210
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 1.3997,
      "step": 1211
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 1.3015,
      "step": 1212
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 1.2877,
      "step": 1213
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 1.0542,
      "step": 1214
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 1.6449,
      "step": 1215
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 1.4792,
      "step": 1216
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 1.1791,
      "step": 1217
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 1.313,
      "step": 1218
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 1.3372,
      "step": 1219
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 1.4908,
      "step": 1220
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 1.4044,
      "step": 1221
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 1.3076,
      "step": 1222
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 1.2453,
      "step": 1223
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 1.3764,
      "step": 1224
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 1.4333,
      "step": 1225
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 1.2057,
      "step": 1226
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 1.5548,
      "step": 1227
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 1.4485,
      "step": 1228
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 1.2993,
      "step": 1229
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 1.2919,
      "step": 1230
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 1.265,
      "step": 1231
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 1.2168,
      "step": 1232
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 1.4568,
      "step": 1233
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 1.5195,
      "step": 1234
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 1.4479,
      "step": 1235
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 1.4315,
      "step": 1236
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 1.5051,
      "step": 1237
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 1.3603,
      "step": 1238
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 1.3522,
      "step": 1239
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 1.4996,
      "step": 1240
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 1.2714,
      "step": 1241
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 1.1106,
      "step": 1242
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 1.1931,
      "step": 1243
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 1.3915,
      "step": 1244
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 1.4785,
      "step": 1245
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 1.3409,
      "step": 1246
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 1.1554,
      "step": 1247
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 1.2965,
      "step": 1248
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 1.1372,
      "step": 1249
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 1.6669,
      "step": 1250
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 1.36,
      "step": 1251
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 1.1162,
      "step": 1252
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 0.9747,
      "step": 1253
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 1.6499,
      "step": 1254
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 1.7024,
      "step": 1255
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 1.0353,
      "step": 1256
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 1.4354,
      "step": 1257
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 1.2642,
      "step": 1258
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 1.177,
      "step": 1259
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 1.3294,
      "step": 1260
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 1.3614,
      "step": 1261
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 1.3363,
      "step": 1262
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 1.3276,
      "step": 1263
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 1.158,
      "step": 1264
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 1.3777,
      "step": 1265
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 1.2625,
      "step": 1266
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 1.2622,
      "step": 1267
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 1.2931,
      "step": 1268
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 1.0584,
      "step": 1269
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 1.8738,
      "step": 1270
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 1.328,
      "step": 1271
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 1.6109,
      "step": 1272
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 1.3256,
      "step": 1273
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 1.3741,
      "step": 1274
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 1.2444,
      "step": 1275
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 1.5534,
      "step": 1276
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 1.4242,
      "step": 1277
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 1.2567,
      "step": 1278
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 1.2987,
      "step": 1279
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 1.2516,
      "step": 1280
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 1.3461,
      "step": 1281
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 1.4501,
      "step": 1282
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 1.6492,
      "step": 1283
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 1.2754,
      "step": 1284
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 1.3003,
      "step": 1285
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 1.4799,
      "step": 1286
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 1.3873,
      "step": 1287
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 1.2283,
      "step": 1288
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 1.5091,
      "step": 1289
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 1.305,
      "step": 1290
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 1.2521,
      "step": 1291
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 1.7945,
      "step": 1292
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 1.3589,
      "step": 1293
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 1.5213,
      "step": 1294
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 1.4369,
      "step": 1295
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 1.1006,
      "step": 1296
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 1.4044,
      "step": 1297
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 1.1263,
      "step": 1298
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.449,
      "step": 1299
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.3049,
      "step": 1300
    },
    {
      "epoch": 1.75,
      "eval_loss": 1.361443281173706,
      "eval_runtime": 452.1862,
      "eval_samples_per_second": 1.526,
      "eval_steps_per_second": 0.383,
      "step": 1300
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.3181,
      "step": 1301
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.6142,
      "step": 1302
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.2711,
      "step": 1303
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.441,
      "step": 1304
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.4645,
      "step": 1305
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.4088,
      "step": 1306
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 1.2154,
      "step": 1307
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 1.1357,
      "step": 1308
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 1.6021,
      "step": 1309
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 1.1831,
      "step": 1310
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 1.569,
      "step": 1311
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 1.6119,
      "step": 1312
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 1.2171,
      "step": 1313
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 1.2171,
      "step": 1314
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 1.3153,
      "step": 1315
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 1.3561,
      "step": 1316
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 1.34,
      "step": 1317
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 1.2953,
      "step": 1318
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 1.1492,
      "step": 1319
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 1.2423,
      "step": 1320
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 1.274,
      "step": 1321
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 1.1931,
      "step": 1322
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 1.7063,
      "step": 1323
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 1.0895,
      "step": 1324
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 1.5808,
      "step": 1325
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 1.3314,
      "step": 1326
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 1.3782,
      "step": 1327
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 1.2877,
      "step": 1328
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 1.1229,
      "step": 1329
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 1.3798,
      "step": 1330
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 1.368,
      "step": 1331
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 1.7692,
      "step": 1332
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 1.1537,
      "step": 1333
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 1.558,
      "step": 1334
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 1.3157,
      "step": 1335
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 1.0476,
      "step": 1336
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 1.4725,
      "step": 1337
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 1.0862,
      "step": 1338
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 1.3327,
      "step": 1339
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 1.166,
      "step": 1340
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 1.3451,
      "step": 1341
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 1.6674,
      "step": 1342
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 1.3245,
      "step": 1343
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 1.7514,
      "step": 1344
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 1.3815,
      "step": 1345
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 1.1391,
      "step": 1346
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 1.5978,
      "step": 1347
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 1.4358,
      "step": 1348
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 1.0719,
      "step": 1349
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 1.5374,
      "step": 1350
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 1.4566,
      "step": 1351
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 1.1065,
      "step": 1352
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 1.2867,
      "step": 1353
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 1.4251,
      "step": 1354
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 1.2628,
      "step": 1355
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 1.3982,
      "step": 1356
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 1.2746,
      "step": 1357
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 1.1867,
      "step": 1358
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 1.2146,
      "step": 1359
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 1.4831,
      "step": 1360
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 1.3234,
      "step": 1361
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 1.3043,
      "step": 1362
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 1.2377,
      "step": 1363
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 1.1159,
      "step": 1364
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 1.3733,
      "step": 1365
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 1.2781,
      "step": 1366
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 1.2702,
      "step": 1367
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 1.1332,
      "step": 1368
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 1.2572,
      "step": 1369
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 1.3232,
      "step": 1370
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 1.1923,
      "step": 1371
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 1.5049,
      "step": 1372
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 1.5557,
      "step": 1373
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 1.4804,
      "step": 1374
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 1.2622,
      "step": 1375
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 1.1332,
      "step": 1376
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 1.3601,
      "step": 1377
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 1.3051,
      "step": 1378
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 1.0931,
      "step": 1379
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 1.4038,
      "step": 1380
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 1.7695,
      "step": 1381
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 1.0896,
      "step": 1382
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 1.4577,
      "step": 1383
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 1.5547,
      "step": 1384
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 1.2716,
      "step": 1385
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 1.2028,
      "step": 1386
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 1.5158,
      "step": 1387
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 1.334,
      "step": 1388
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 1.3411,
      "step": 1389
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 1.3114,
      "step": 1390
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 1.2883,
      "step": 1391
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 1.145,
      "step": 1392
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 1.3585,
      "step": 1393
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 1.2597,
      "step": 1394
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 1.6144,
      "step": 1395
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 1.4775,
      "step": 1396
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 1.4114,
      "step": 1397
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 1.336,
      "step": 1398
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 1.22,
      "step": 1399
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 1.2788,
      "step": 1400
    },
    {
      "epoch": 1.88,
      "eval_loss": 1.360325574874878,
      "eval_runtime": 454.5581,
      "eval_samples_per_second": 1.518,
      "eval_steps_per_second": 0.381,
      "step": 1400
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 1.1328,
      "step": 1401
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 1.4448,
      "step": 1402
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 1.5488,
      "step": 1403
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 1.1268,
      "step": 1404
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 1.1313,
      "step": 1405
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 1.5281,
      "step": 1406
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 1.2445,
      "step": 1407
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 1.3553,
      "step": 1408
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 1.6369,
      "step": 1409
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 1.5902,
      "step": 1410
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 1.2592,
      "step": 1411
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 1.4342,
      "step": 1412
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 1.2916,
      "step": 1413
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 1.3716,
      "step": 1414
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 1.5936,
      "step": 1415
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 1.5406,
      "step": 1416
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 1.4875,
      "step": 1417
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 1.4572,
      "step": 1418
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 1.3704,
      "step": 1419
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 1.5078,
      "step": 1420
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 1.568,
      "step": 1421
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 1.3408,
      "step": 1422
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 1.2534,
      "step": 1423
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 1.3976,
      "step": 1424
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 1.3251,
      "step": 1425
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 1.2646,
      "step": 1426
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 1.3025,
      "step": 1427
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 1.2908,
      "step": 1428
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 1.301,
      "step": 1429
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 1.4023,
      "step": 1430
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 1.3245,
      "step": 1431
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 1.1896,
      "step": 1432
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 1.3692,
      "step": 1433
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 1.4506,
      "step": 1434
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 1.4893,
      "step": 1435
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 1.5193,
      "step": 1436
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 1.1378,
      "step": 1437
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 1.1414,
      "step": 1438
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 1.4361,
      "step": 1439
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 1.3751,
      "step": 1440
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 1.2463,
      "step": 1441
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 1.5982,
      "step": 1442
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 1.4145,
      "step": 1443
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 1.1395,
      "step": 1444
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 1.2661,
      "step": 1445
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 1.1822,
      "step": 1446
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 1.3323,
      "step": 1447
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 1.2896,
      "step": 1448
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 1.2449,
      "step": 1449
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 1.4948,
      "step": 1450
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 1.4295,
      "step": 1451
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 1.4366,
      "step": 1452
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 1.4089,
      "step": 1453
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 1.1987,
      "step": 1454
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 1.228,
      "step": 1455
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 1.4474,
      "step": 1456
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 1.1373,
      "step": 1457
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 1.4181,
      "step": 1458
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 1.2706,
      "step": 1459
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 1.4088,
      "step": 1460
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 1.6813,
      "step": 1461
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 1.4659,
      "step": 1462
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 1.0265,
      "step": 1463
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 1.1451,
      "step": 1464
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 1.2497,
      "step": 1465
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 1.3511,
      "step": 1466
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 1.2546,
      "step": 1467
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 1.3855,
      "step": 1468
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 1.286,
      "step": 1469
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 1.2015,
      "step": 1470
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 1.3267,
      "step": 1471
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 1.3493,
      "step": 1472
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 1.1064,
      "step": 1473
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 1.4252,
      "step": 1474
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 1.5712,
      "step": 1475
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 1.329,
      "step": 1476
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 1.406,
      "step": 1477
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002,
      "loss": 1.3303,
      "step": 1478
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002,
      "loss": 1.2491,
      "step": 1479
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002,
      "loss": 1.3464,
      "step": 1480
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002,
      "loss": 1.5351,
      "step": 1481
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002,
      "loss": 1.5893,
      "step": 1482
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002,
      "loss": 1.202,
      "step": 1483
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002,
      "loss": 1.1958,
      "step": 1484
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 1.1439,
      "step": 1485
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 1.2844,
      "step": 1486
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 1.2657,
      "step": 1487
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 1.3416,
      "step": 1488
    }
  ],
  "logging_steps": 1,
  "max_steps": 1488,
  "num_train_epochs": 2,
  "save_steps": 250,
  "total_flos": 1.02174494658859e+17,
  "trial_name": null,
  "trial_params": null
}