{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.63,
  "global_step": 378,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.1255,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.1879,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.26,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.2976,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.0941,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.0327,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.0108,
      "step": 7
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.0169,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.9465,
      "step": 9
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7617,
      "step": 10
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7485,
      "step": 11
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.8165,
      "step": 12
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.9355,
      "step": 13
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7963,
      "step": 14
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7975,
      "step": 15
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.8134,
      "step": 16
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.8831,
      "step": 17
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.951,
      "step": 18
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.8587,
      "step": 19
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7893,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.8785,
      "step": 21
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7122,
      "step": 22
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7702,
      "step": 23
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7804,
      "step": 24
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.8752,
      "step": 25
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.8381,
      "step": 26
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7391,
      "step": 27
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.8153,
      "step": 28
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.8272,
      "step": 29
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7685,
      "step": 30
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.8642,
      "step": 31
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.8064,
      "step": 32
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.0248,
      "step": 33
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.6896,
      "step": 34
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.6497,
      "step": 35
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7008,
      "step": 36
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.8231,
      "step": 37
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.6382,
      "step": 38
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.722,
      "step": 39
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.8071,
      "step": 40
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.7008,
      "step": 41
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.6241,
      "step": 42
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.6722,
      "step": 43
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.6536,
      "step": 44
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.7829,
      "step": 45
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.7562,
      "step": 46
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.5762,
      "step": 47
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.6127,
      "step": 48
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.6264,
      "step": 49
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.6476,
      "step": 50
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.6598,
      "step": 51
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.6765,
      "step": 52
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.9637,
      "step": 53
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.6426,
      "step": 54
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.6282,
      "step": 55
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.6501,
      "step": 56
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.6815,
      "step": 57
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.5453,
      "step": 58
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.6611,
      "step": 59
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.7393,
      "step": 60
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.6785,
      "step": 61
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.6949,
      "step": 62
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.6793,
      "step": 63
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.642,
      "step": 64
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.5686,
      "step": 65
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.6669,
      "step": 66
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.6506,
      "step": 67
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.5483,
      "step": 68
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.8149,
      "step": 69
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.7043,
      "step": 70
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.615,
      "step": 71
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.8279,
      "step": 72
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.6085,
      "step": 73
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.6171,
      "step": 74
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.8868,
      "step": 75
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.4776,
      "step": 76
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.595,
      "step": 77
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.6242,
      "step": 78
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.841,
      "step": 79
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.6395,
      "step": 80
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.7629,
      "step": 81
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.5896,
      "step": 82
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.7116,
      "step": 83
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.683,
      "step": 84
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.7552,
      "step": 85
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.5942,
      "step": 86
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.648,
      "step": 87
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.7186,
      "step": 88
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.6341,
      "step": 89
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.6313,
      "step": 90
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.58,
      "step": 91
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.5223,
      "step": 92
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.6629,
      "step": 93
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.6688,
      "step": 94
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.6339,
      "step": 95
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.5909,
      "step": 96
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.765,
      "step": 97
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.6004,
      "step": 98
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.6039,
      "step": 99
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.5865,
      "step": 100
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.5076,
      "step": 101
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.7506,
      "step": 102
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.7036,
      "step": 103
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.5451,
      "step": 104
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.6748,
      "step": 105
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.519,
      "step": 106
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.5924,
      "step": 107
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.5532,
      "step": 108
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.636,
      "step": 109
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.5604,
      "step": 110
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.5401,
      "step": 111
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.592,
      "step": 112
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.4686,
      "step": 113
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.6278,
      "step": 114
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.0048,
      "step": 115
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.6044,
      "step": 116
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.5042,
      "step": 117
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.6284,
      "step": 118
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.4466,
      "step": 119
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.6476,
      "step": 120
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.6212,
      "step": 121
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.7524,
      "step": 122
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.4032,
      "step": 123
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.5073,
      "step": 124
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.5638,
      "step": 125
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.4889,
      "step": 126
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.5198,
      "step": 127
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.6574,
      "step": 128
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.4384,
      "step": 129
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.5509,
      "step": 130
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.6807,
      "step": 131
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.6007,
      "step": 132
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.4981,
      "step": 133
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.6221,
      "step": 134
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.6888,
      "step": 135
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 0.566,
      "step": 136
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 0.5356,
      "step": 137
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.5181,
      "step": 138
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.6253,
      "step": 139
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.7483,
      "step": 140
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.5515,
      "step": 141
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.6673,
      "step": 142
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.5707,
      "step": 143
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.5274,
      "step": 144
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.5036,
      "step": 145
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.4617,
      "step": 146
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.4047,
      "step": 147
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.437,
      "step": 148
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.4967,
      "step": 149
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.448,
      "step": 150
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.492,
      "step": 151
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.501,
      "step": 152
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.5787,
      "step": 153
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.4248,
      "step": 154
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.4383,
      "step": 155
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.5408,
      "step": 156
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.423,
      "step": 157
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.4396,
      "step": 158
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.7786,
      "step": 159
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.461,
      "step": 160
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.6476,
      "step": 161
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.6539,
      "step": 162
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 0.4485,
      "step": 163
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 0.4632,
      "step": 164
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.4498,
      "step": 165
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.5024,
      "step": 166
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.572,
      "step": 167
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.6172,
      "step": 168
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.5672,
      "step": 169
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.5047,
      "step": 170
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.753,
      "step": 171
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.4519,
      "step": 172
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.5,
      "step": 173
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.3306,
      "step": 174
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.3823,
      "step": 175
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.6123,
      "step": 176
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.4076,
      "step": 177
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.5976,
      "step": 178
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.6273,
      "step": 179
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.4142,
      "step": 180
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.5026,
      "step": 181
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 0.405,
      "step": 182
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 0.5714,
      "step": 183
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 0.4095,
      "step": 184
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 0.6111,
      "step": 185
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.3799,
      "step": 186
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.4255,
      "step": 187
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 0.3993,
      "step": 188
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 0.5139,
      "step": 189
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.4591,
      "step": 190
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.4029,
      "step": 191
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.5223,
      "step": 192
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.5679,
      "step": 193
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 0.626,
      "step": 194
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 0.3685,
      "step": 195
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 0.4113,
      "step": 196
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 0.3667,
      "step": 197
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 0.4222,
      "step": 198
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 0.2758,
      "step": 199
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 0.4047,
      "step": 200
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.4728,
      "step": 201
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.4553,
      "step": 202
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 0.4315,
      "step": 203
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 0.5367,
      "step": 204
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 0.4195,
      "step": 205
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 0.4322,
      "step": 206
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 0.4155,
      "step": 207
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 0.4814,
      "step": 208
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 0.3398,
      "step": 209
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 0.491,
      "step": 210
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 0.4541,
      "step": 211
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 0.4775,
      "step": 212
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 0.292,
      "step": 213
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 0.4084,
      "step": 214
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 0.451,
      "step": 215
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 0.5295,
      "step": 216
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 0.4284,
      "step": 217
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 0.4822,
      "step": 218
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 0.5749,
      "step": 219
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 0.4108,
      "step": 220
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 0.4421,
      "step": 221
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 0.4888,
      "step": 222
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 0.4299,
      "step": 223
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 0.3362,
      "step": 224
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 0.4508,
      "step": 225
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 0.4972,
      "step": 226
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 0.4901,
      "step": 227
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 0.3824,
      "step": 228
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 0.476,
      "step": 229
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 0.454,
      "step": 230
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 0.649,
      "step": 231
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 0.4295,
      "step": 232
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 0.3785,
      "step": 233
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 0.4358,
      "step": 234
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 0.327,
      "step": 235
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 0.4491,
      "step": 236
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 0.3768,
      "step": 237
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 0.5719,
      "step": 238
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 0.5428,
      "step": 239
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.5184,
      "step": 240
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.5022,
      "step": 241
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 0.4506,
      "step": 242
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 0.3221,
      "step": 243
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 0.3739,
      "step": 244
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 0.4093,
      "step": 245
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 0.4323,
      "step": 246
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 0.33,
      "step": 247
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 0.5782,
      "step": 248
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 0.3786,
      "step": 249
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.5689,
      "step": 250
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.4258,
      "step": 251
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 0.4883,
      "step": 252
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 0.5522,
      "step": 253
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0002,
      "loss": 0.2941,
      "step": 254
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0002,
      "loss": 0.3574,
      "step": 255
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0002,
      "loss": 0.431,
      "step": 256
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0002,
      "loss": 0.2933,
      "step": 257
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0002,
      "loss": 0.2837,
      "step": 258
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0002,
      "loss": 0.3547,
      "step": 259
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0002,
      "loss": 0.361,
      "step": 260
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0002,
      "loss": 0.3533,
      "step": 261
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0002,
      "loss": 0.3594,
      "step": 262
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0002,
      "loss": 0.3018,
      "step": 263
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0002,
      "loss": 0.4084,
      "step": 264
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0002,
      "loss": 0.3323,
      "step": 265
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0002,
      "loss": 0.4895,
      "step": 266
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0002,
      "loss": 0.3182,
      "step": 267
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0002,
      "loss": 0.418,
      "step": 268
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0002,
      "loss": 0.418,
      "step": 269
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0002,
      "loss": 0.437,
      "step": 270
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0002,
      "loss": 0.4276,
      "step": 271
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0002,
      "loss": 0.288,
      "step": 272
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0002,
      "loss": 0.3729,
      "step": 273
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002,
      "loss": 0.3004,
      "step": 274
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0002,
      "loss": 0.2358,
      "step": 275
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0002,
      "loss": 0.5081,
      "step": 276
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0002,
      "loss": 0.4543,
      "step": 277
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0002,
      "loss": 0.3584,
      "step": 278
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0002,
      "loss": 0.2461,
      "step": 279
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0002,
      "loss": 0.3846,
      "step": 280
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0002,
      "loss": 0.3133,
      "step": 281
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0002,
      "loss": 0.2515,
      "step": 282
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0002,
      "loss": 0.3321,
      "step": 283
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0002,
      "loss": 0.3493,
      "step": 284
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0002,
      "loss": 0.2791,
      "step": 285
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0002,
      "loss": 0.2172,
      "step": 286
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0002,
      "loss": 0.3179,
      "step": 287
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0002,
      "loss": 0.2794,
      "step": 288
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0002,
      "loss": 0.2054,
      "step": 289
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0002,
      "loss": 0.3072,
      "step": 290
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0002,
      "loss": 0.3127,
      "step": 291
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0002,
      "loss": 0.3024,
      "step": 292
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0002,
      "loss": 0.2717,
      "step": 293
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0002,
      "loss": 0.43,
      "step": 294
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0002,
      "loss": 0.4119,
      "step": 295
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0002,
      "loss": 0.4684,
      "step": 296
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0002,
      "loss": 0.3498,
      "step": 297
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0002,
      "loss": 0.4309,
      "step": 298
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0002,
      "loss": 0.3586,
      "step": 299
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0002,
      "loss": 0.3077,
      "step": 300
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0002,
      "loss": 0.4247,
      "step": 301
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0002,
      "loss": 0.3006,
      "step": 302
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0002,
      "loss": 0.4604,
      "step": 303
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0002,
      "loss": 0.3939,
      "step": 304
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0002,
      "loss": 0.42,
      "step": 305
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0002,
      "loss": 0.3002,
      "step": 306
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0002,
      "loss": 0.2967,
      "step": 307
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0002,
      "loss": 0.3722,
      "step": 308
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0002,
      "loss": 0.3473,
      "step": 309
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0002,
      "loss": 0.3237,
      "step": 310
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0002,
      "loss": 0.2927,
      "step": 311
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0002,
      "loss": 0.2799,
      "step": 312
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0002,
      "loss": 0.2681,
      "step": 313
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0002,
      "loss": 0.1985,
      "step": 314
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0002,
      "loss": 0.3829,
      "step": 315
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0002,
      "loss": 0.4166,
      "step": 316
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0002,
      "loss": 0.2772,
      "step": 317
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0002,
      "loss": 0.2005,
      "step": 318
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0002,
      "loss": 0.3751,
      "step": 319
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0002,
      "loss": 0.2485,
      "step": 320
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0002,
      "loss": 0.3472,
      "step": 321
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0002,
      "loss": 0.2503,
      "step": 322
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0002,
      "loss": 0.3336,
      "step": 323
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0002,
      "loss": 0.4596,
      "step": 324
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0002,
      "loss": 0.2793,
      "step": 325
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0002,
      "loss": 0.34,
      "step": 326
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0002,
      "loss": 0.2007,
      "step": 327
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0002,
      "loss": 0.2267,
      "step": 328
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0002,
      "loss": 0.2611,
      "step": 329
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0002,
      "loss": 0.3311,
      "step": 330
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0002,
      "loss": 0.2828,
      "step": 331
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0002,
      "loss": 0.355,
      "step": 332
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0002,
      "loss": 0.3062,
      "step": 333
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0002,
      "loss": 0.3167,
      "step": 334
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0002,
      "loss": 0.2785,
      "step": 335
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0002,
      "loss": 0.3294,
      "step": 336
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0002,
      "loss": 0.2853,
      "step": 337
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0002,
      "loss": 0.2247,
      "step": 338
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0002,
      "loss": 0.386,
      "step": 339
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0002,
      "loss": 0.3849,
      "step": 340
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0002,
      "loss": 0.3715,
      "step": 341
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0002,
      "loss": 0.2804,
      "step": 342
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0002,
      "loss": 0.2496,
      "step": 343
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0002,
      "loss": 0.2867,
      "step": 344
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0002,
      "loss": 0.2996,
      "step": 345
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0002,
      "loss": 0.3231,
      "step": 346
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0002,
      "loss": 0.2543,
      "step": 347
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0002,
      "loss": 0.3494,
      "step": 348
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0002,
      "loss": 0.3353,
      "step": 349
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0002,
      "loss": 0.259,
      "step": 350
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0002,
      "loss": 0.3683,
      "step": 351
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0002,
      "loss": 0.2743,
      "step": 352
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0002,
      "loss": 0.2564,
      "step": 353
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0002,
      "loss": 0.2913,
      "step": 354
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0002,
      "loss": 0.1972,
      "step": 355
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0002,
      "loss": 0.2731,
      "step": 356
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0002,
      "loss": 0.2797,
      "step": 357
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0002,
      "loss": 0.3052,
      "step": 358
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0002,
      "loss": 0.219,
      "step": 359
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0002,
      "loss": 0.3572,
      "step": 360
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0002,
      "loss": 0.2863,
      "step": 361
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0002,
      "loss": 0.3066,
      "step": 362
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0002,
      "loss": 0.3074,
      "step": 363
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0002,
      "loss": 0.2419,
      "step": 364
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0002,
      "loss": 0.2544,
      "step": 365
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0002,
      "loss": 0.2255,
      "step": 366
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0002,
      "loss": 0.2283,
      "step": 367
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0002,
      "loss": 0.358,
      "step": 368
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0002,
      "loss": 0.2953,
      "step": 369
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0002,
      "loss": 0.4018,
      "step": 370
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0002,
      "loss": 0.3957,
      "step": 371
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0002,
      "loss": 0.3215,
      "step": 372
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0002,
      "loss": 0.2765,
      "step": 373
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0002,
      "loss": 0.2696,
      "step": 374
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0002,
      "loss": 0.2313,
      "step": 375
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0002,
      "loss": 0.2586,
      "step": 376
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0002,
      "loss": 0.3114,
      "step": 377
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0002,
      "loss": 0.2457,
      "step": 378
    }
  ],
  "max_steps": 600,
  "num_train_epochs": 3,
  "total_flos": 9.483591692058624e+16,
  "trial_name": null,
  "trial_params": null
}