{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9922178988326849,
  "global_step": 256,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 1.4922,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.666666666666668e-06,
      "loss": 1.0138,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.0566416671474378e-05,
      "loss": 1.0831,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.3333333333333337e-05,
      "loss": 0.9965,
      "step": 4
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.5479520632582417e-05,
      "loss": 0.8603,
      "step": 5
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.7233083338141044e-05,
      "loss": 0.8166,
      "step": 6
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.8715699480384028e-05,
      "loss": 0.8419,
      "step": 7
    },
    {
      "epoch": 0.06,
      "learning_rate": 2e-05,
      "loss": 0.7712,
      "step": 8
    },
    {
      "epoch": 0.07,
      "learning_rate": 2e-05,
      "loss": 0.9215,
      "step": 9
    },
    {
      "epoch": 0.08,
      "learning_rate": 2e-05,
      "loss": 0.8538,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 2e-05,
      "loss": 0.8062,
      "step": 11
    },
    {
      "epoch": 0.09,
      "learning_rate": 2e-05,
      "loss": 0.7634,
      "step": 12
    },
    {
      "epoch": 0.1,
      "learning_rate": 2e-05,
      "loss": 0.7684,
      "step": 13
    },
    {
      "epoch": 0.11,
      "learning_rate": 2e-05,
      "loss": 0.7637,
      "step": 14
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.736,
      "step": 15
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.7413,
      "step": 16
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 0.7545,
      "step": 17
    },
    {
      "epoch": 0.14,
      "learning_rate": 2e-05,
      "loss": 0.755,
      "step": 18
    },
    {
      "epoch": 0.15,
      "learning_rate": 2e-05,
      "loss": 0.735,
      "step": 19
    },
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 0.6857,
      "step": 20
    },
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 0.7337,
      "step": 21
    },
    {
      "epoch": 0.17,
      "learning_rate": 2e-05,
      "loss": 0.6873,
      "step": 22
    },
    {
      "epoch": 0.18,
      "learning_rate": 2e-05,
      "loss": 0.7926,
      "step": 23
    },
    {
      "epoch": 0.19,
      "learning_rate": 2e-05,
      "loss": 0.6819,
      "step": 24
    },
    {
      "epoch": 0.19,
      "learning_rate": 2e-05,
      "loss": 0.7363,
      "step": 25
    },
    {
      "epoch": 0.2,
      "learning_rate": 2e-05,
      "loss": 0.7271,
      "step": 26
    },
    {
      "epoch": 0.21,
      "learning_rate": 2e-05,
      "loss": 0.6867,
      "step": 27
    },
    {
      "epoch": 0.22,
      "learning_rate": 2e-05,
      "loss": 0.7242,
      "step": 28
    },
    {
      "epoch": 0.23,
      "learning_rate": 2e-05,
      "loss": 0.705,
      "step": 29
    },
    {
      "epoch": 0.23,
      "learning_rate": 2e-05,
      "loss": 0.7395,
      "step": 30
    },
    {
      "epoch": 0.24,
      "learning_rate": 2e-05,
      "loss": 0.6885,
      "step": 31
    },
    {
      "epoch": 0.25,
      "learning_rate": 2e-05,
      "loss": 0.7007,
      "step": 32
    },
    {
      "epoch": 0.26,
      "learning_rate": 2e-05,
      "loss": 0.6984,
      "step": 33
    },
    {
      "epoch": 0.26,
      "learning_rate": 2e-05,
      "loss": 0.6817,
      "step": 34
    },
    {
      "epoch": 0.27,
      "learning_rate": 2e-05,
      "loss": 0.662,
      "step": 35
    },
    {
      "epoch": 0.28,
      "learning_rate": 2e-05,
      "loss": 0.6485,
      "step": 36
    },
    {
      "epoch": 0.29,
      "learning_rate": 2e-05,
      "loss": 0.7167,
      "step": 37
    },
    {
      "epoch": 0.3,
      "learning_rate": 2e-05,
      "loss": 0.7376,
      "step": 38
    },
    {
      "epoch": 0.3,
      "learning_rate": 2e-05,
      "loss": 0.6573,
      "step": 39
    },
    {
      "epoch": 0.31,
      "learning_rate": 2e-05,
      "loss": 0.6474,
      "step": 40
    },
    {
      "epoch": 0.32,
      "learning_rate": 2e-05,
      "loss": 0.6876,
      "step": 41
    },
    {
      "epoch": 0.33,
      "learning_rate": 2e-05,
      "loss": 0.6643,
      "step": 42
    },
    {
      "epoch": 0.33,
      "learning_rate": 2e-05,
      "loss": 0.6877,
      "step": 43
    },
    {
      "epoch": 0.34,
      "learning_rate": 2e-05,
      "loss": 0.6713,
      "step": 44
    },
    {
      "epoch": 0.35,
      "learning_rate": 2e-05,
      "loss": 0.6401,
      "step": 45
    },
    {
      "epoch": 0.36,
      "learning_rate": 2e-05,
      "loss": 0.6451,
      "step": 46
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 0.658,
      "step": 47
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 0.6804,
      "step": 48
    },
    {
      "epoch": 0.38,
      "learning_rate": 2e-05,
      "loss": 0.6878,
      "step": 49
    },
    {
      "epoch": 0.39,
      "learning_rate": 2e-05,
      "loss": 0.6956,
      "step": 50
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 0.6407,
      "step": 51
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 0.6577,
      "step": 52
    },
    {
      "epoch": 0.41,
      "learning_rate": 2e-05,
      "loss": 0.6489,
      "step": 53
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 0.6158,
      "step": 54
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 0.638,
      "step": 55
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 0.6507,
      "step": 56
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 0.6362,
      "step": 57
    },
    {
      "epoch": 0.45,
      "learning_rate": 2e-05,
      "loss": 0.6539,
      "step": 58
    },
    {
      "epoch": 0.46,
      "learning_rate": 2e-05,
      "loss": 0.6781,
      "step": 59
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 0.6522,
      "step": 60
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 0.635,
      "step": 61
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.6589,
      "step": 62
    },
    {
      "epoch": 0.49,
      "learning_rate": 2e-05,
      "loss": 0.6794,
      "step": 63
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 0.6171,
      "step": 64
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 0.5971,
      "step": 65
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 0.6599,
      "step": 66
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 0.6268,
      "step": 67
    },
    {
      "epoch": 0.53,
      "learning_rate": 2e-05,
      "loss": 0.604,
      "step": 68
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 0.6271,
      "step": 69
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 0.6459,
      "step": 70
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-05,
      "loss": 0.635,
      "step": 71
    },
    {
      "epoch": 0.56,
      "learning_rate": 2e-05,
      "loss": 0.6297,
      "step": 72
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 0.6918,
      "step": 73
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 0.5938,
      "step": 74
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 0.6175,
      "step": 75
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 0.6754,
      "step": 76
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 0.6518,
      "step": 77
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 0.6732,
      "step": 78
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 0.6129,
      "step": 79
    },
    {
      "epoch": 0.62,
      "learning_rate": 2e-05,
      "loss": 0.595,
      "step": 80
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 0.6553,
      "step": 81
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-05,
      "loss": 0.6458,
      "step": 82
    },
    {
      "epoch": 0.65,
      "learning_rate": 2e-05,
      "loss": 0.6104,
      "step": 83
    },
    {
      "epoch": 0.65,
      "learning_rate": 2e-05,
      "loss": 0.6008,
      "step": 84
    },
    {
      "epoch": 0.66,
      "learning_rate": 2e-05,
      "loss": 0.6184,
      "step": 85
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 0.5895,
      "step": 86
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 0.6401,
      "step": 87
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 0.598,
      "step": 88
    },
    {
      "epoch": 0.69,
      "learning_rate": 2e-05,
      "loss": 0.6253,
      "step": 89
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 0.6551,
      "step": 90
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 0.6046,
      "step": 91
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 0.6335,
      "step": 92
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 0.5888,
      "step": 93
    },
    {
      "epoch": 0.73,
      "learning_rate": 2e-05,
      "loss": 0.6358,
      "step": 94
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 0.6073,
      "step": 95
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 0.627,
      "step": 96
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 0.6363,
      "step": 97
    },
    {
      "epoch": 0.76,
      "learning_rate": 2e-05,
      "loss": 0.6647,
      "step": 98
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 0.656,
      "step": 99
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 0.5971,
      "step": 100
    },
    {
      "epoch": 0.79,
      "learning_rate": 2e-05,
      "loss": 0.6493,
      "step": 101
    },
    {
      "epoch": 0.79,
      "learning_rate": 2e-05,
      "loss": 0.6221,
      "step": 102
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 0.6398,
      "step": 103
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 0.6225,
      "step": 104
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 0.5955,
      "step": 105
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 0.625,
      "step": 106
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 0.6363,
      "step": 107
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 0.6265,
      "step": 108
    },
    {
      "epoch": 0.85,
      "learning_rate": 2e-05,
      "loss": 0.6145,
      "step": 109
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 0.6072,
      "step": 110
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 0.6306,
      "step": 111
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 0.6334,
      "step": 112
    },
    {
      "epoch": 0.88,
      "learning_rate": 2e-05,
      "loss": 0.5787,
      "step": 113
    },
    {
      "epoch": 0.89,
      "learning_rate": 2e-05,
      "loss": 0.6629,
      "step": 114
    },
    {
      "epoch": 0.89,
      "learning_rate": 2e-05,
      "loss": 0.6595,
      "step": 115
    },
    {
      "epoch": 0.9,
      "learning_rate": 2e-05,
      "loss": 0.6184,
      "step": 116
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 0.5994,
      "step": 117
    },
    {
      "epoch": 0.92,
      "learning_rate": 2e-05,
      "loss": 0.5996,
      "step": 118
    },
    {
      "epoch": 0.93,
      "learning_rate": 2e-05,
      "loss": 0.577,
      "step": 119
    },
    {
      "epoch": 0.93,
      "learning_rate": 2e-05,
      "loss": 0.6204,
      "step": 120
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 0.5943,
      "step": 121
    },
    {
      "epoch": 0.95,
      "learning_rate": 2e-05,
      "loss": 0.6243,
      "step": 122
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 0.6363,
      "step": 123
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 0.6157,
      "step": 124
    },
    {
      "epoch": 0.97,
      "learning_rate": 2e-05,
      "loss": 0.6022,
      "step": 125
    },
    {
      "epoch": 0.98,
      "learning_rate": 2e-05,
      "loss": 0.5602,
      "step": 126
    },
    {
      "epoch": 0.99,
      "learning_rate": 2e-05,
      "loss": 0.6367,
      "step": 127
    },
    {
      "epoch": 1.0,
      "learning_rate": 2e-05,
      "loss": 0.6383,
      "step": 128
    },
    {
      "epoch": 1.0,
      "learning_rate": 2e-05,
      "loss": 0.5849,
      "step": 129
    },
    {
      "epoch": 1.01,
      "learning_rate": 2e-05,
      "loss": 0.5089,
      "step": 130
    },
    {
      "epoch": 1.02,
      "learning_rate": 2e-05,
      "loss": 0.5414,
      "step": 131
    },
    {
      "epoch": 1.03,
      "learning_rate": 2e-05,
      "loss": 0.5293,
      "step": 132
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 0.5541,
      "step": 133
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 0.5498,
      "step": 134
    },
    {
      "epoch": 1.05,
      "learning_rate": 2e-05,
      "loss": 0.5697,
      "step": 135
    },
    {
      "epoch": 1.06,
      "learning_rate": 2e-05,
      "loss": 0.5419,
      "step": 136
    },
    {
      "epoch": 1.07,
      "learning_rate": 2e-05,
      "loss": 0.5385,
      "step": 137
    },
    {
      "epoch": 1.07,
      "learning_rate": 2e-05,
      "loss": 0.5478,
      "step": 138
    },
    {
      "epoch": 1.08,
      "learning_rate": 2e-05,
      "loss": 0.5664,
      "step": 139
    },
    {
      "epoch": 1.09,
      "learning_rate": 2e-05,
      "loss": 0.543,
      "step": 140
    },
    {
      "epoch": 1.1,
      "learning_rate": 2e-05,
      "loss": 0.5056,
      "step": 141
    },
    {
      "epoch": 1.11,
      "learning_rate": 2e-05,
      "loss": 0.5539,
      "step": 142
    },
    {
      "epoch": 1.11,
      "learning_rate": 2e-05,
      "loss": 0.4854,
      "step": 143
    },
    {
      "epoch": 1.12,
      "learning_rate": 2e-05,
      "loss": 0.527,
      "step": 144
    },
    {
      "epoch": 1.13,
      "learning_rate": 2e-05,
      "loss": 0.5485,
      "step": 145
    },
    {
      "epoch": 1.14,
      "learning_rate": 2e-05,
      "loss": 0.5416,
      "step": 146
    },
    {
      "epoch": 1.14,
      "learning_rate": 2e-05,
      "loss": 0.5163,
      "step": 147
    },
    {
      "epoch": 1.15,
      "learning_rate": 2e-05,
      "loss": 0.5473,
      "step": 148
    },
    {
      "epoch": 1.16,
      "learning_rate": 2e-05,
      "loss": 0.5551,
      "step": 149
    },
    {
      "epoch": 1.17,
      "learning_rate": 2e-05,
      "loss": 0.5351,
      "step": 150
    },
    {
      "epoch": 1.18,
      "learning_rate": 2e-05,
      "loss": 0.5065,
      "step": 151
    },
    {
      "epoch": 1.18,
      "learning_rate": 2e-05,
      "loss": 0.5224,
      "step": 152
    },
    {
      "epoch": 1.19,
      "learning_rate": 2e-05,
      "loss": 0.5451,
      "step": 153
    },
    {
      "epoch": 1.2,
      "learning_rate": 2e-05,
      "loss": 0.5321,
      "step": 154
    },
    {
      "epoch": 1.21,
      "learning_rate": 2e-05,
      "loss": 0.5473,
      "step": 155
    },
    {
      "epoch": 1.21,
      "learning_rate": 2e-05,
      "loss": 0.5418,
      "step": 156
    },
    {
      "epoch": 1.22,
      "learning_rate": 2e-05,
      "loss": 0.5086,
      "step": 157
    },
    {
      "epoch": 1.23,
      "learning_rate": 2e-05,
      "loss": 0.5692,
      "step": 158
    },
    {
      "epoch": 1.24,
      "learning_rate": 2e-05,
      "loss": 0.5434,
      "step": 159
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 0.5126,
      "step": 160
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 0.5089,
      "step": 161
    },
    {
      "epoch": 1.26,
      "learning_rate": 2e-05,
      "loss": 0.5275,
      "step": 162
    },
    {
      "epoch": 1.27,
      "learning_rate": 2e-05,
      "loss": 0.5306,
      "step": 163
    },
    {
      "epoch": 1.28,
      "learning_rate": 2e-05,
      "loss": 0.5396,
      "step": 164
    },
    {
      "epoch": 1.28,
      "learning_rate": 2e-05,
      "loss": 0.5148,
      "step": 165
    },
    {
      "epoch": 1.29,
      "learning_rate": 2e-05,
      "loss": 0.5059,
      "step": 166
    },
    {
      "epoch": 1.3,
      "learning_rate": 2e-05,
      "loss": 0.5349,
      "step": 167
    },
    {
      "epoch": 1.31,
      "learning_rate": 2e-05,
      "loss": 0.5193,
      "step": 168
    },
    {
      "epoch": 1.32,
      "learning_rate": 2e-05,
      "loss": 0.5643,
      "step": 169
    },
    {
      "epoch": 1.32,
      "learning_rate": 2e-05,
      "loss": 0.5293,
      "step": 170
    },
    {
      "epoch": 1.33,
      "learning_rate": 2e-05,
      "loss": 0.5647,
      "step": 171
    },
    {
      "epoch": 1.34,
      "learning_rate": 2e-05,
      "loss": 0.5342,
      "step": 172
    },
    {
      "epoch": 1.35,
      "learning_rate": 2e-05,
      "loss": 0.5346,
      "step": 173
    },
    {
      "epoch": 1.35,
      "learning_rate": 2e-05,
      "loss": 0.5275,
      "step": 174
    },
    {
      "epoch": 1.36,
      "learning_rate": 2e-05,
      "loss": 0.5518,
      "step": 175
    },
    {
      "epoch": 1.37,
      "learning_rate": 2e-05,
      "loss": 0.562,
      "step": 176
    },
    {
      "epoch": 1.38,
      "learning_rate": 2e-05,
      "loss": 0.4995,
      "step": 177
    },
    {
      "epoch": 1.39,
      "learning_rate": 2e-05,
      "loss": 0.5166,
      "step": 178
    },
    {
      "epoch": 1.39,
      "learning_rate": 2e-05,
      "loss": 0.5492,
      "step": 179
    },
    {
      "epoch": 1.4,
      "learning_rate": 2e-05,
      "loss": 0.5453,
      "step": 180
    },
    {
      "epoch": 1.41,
      "learning_rate": 2e-05,
      "loss": 0.5394,
      "step": 181
    },
    {
      "epoch": 1.42,
      "learning_rate": 2e-05,
      "loss": 0.5348,
      "step": 182
    },
    {
      "epoch": 1.42,
      "learning_rate": 2e-05,
      "loss": 0.5143,
      "step": 183
    },
    {
      "epoch": 1.43,
      "learning_rate": 2e-05,
      "loss": 0.527,
      "step": 184
    },
    {
      "epoch": 1.44,
      "learning_rate": 2e-05,
      "loss": 0.5288,
      "step": 185
    },
    {
      "epoch": 1.45,
      "learning_rate": 2e-05,
      "loss": 0.5494,
      "step": 186
    },
    {
      "epoch": 1.46,
      "learning_rate": 2e-05,
      "loss": 0.5521,
      "step": 187
    },
    {
      "epoch": 1.46,
      "learning_rate": 2e-05,
      "loss": 0.513,
      "step": 188
    },
    {
      "epoch": 1.47,
      "learning_rate": 2e-05,
      "loss": 0.494,
      "step": 189
    },
    {
      "epoch": 1.48,
      "learning_rate": 2e-05,
      "loss": 0.553,
      "step": 190
    },
    {
      "epoch": 1.49,
      "learning_rate": 2e-05,
      "loss": 0.5503,
      "step": 191
    },
    {
      "epoch": 1.49,
      "learning_rate": 2e-05,
      "loss": 0.5559,
      "step": 192
    },
    {
      "epoch": 1.5,
      "learning_rate": 2e-05,
      "loss": 0.5523,
      "step": 193
    },
    {
      "epoch": 1.51,
      "learning_rate": 2e-05,
      "loss": 0.5116,
      "step": 194
    },
    {
      "epoch": 1.52,
      "learning_rate": 2e-05,
      "loss": 0.5899,
      "step": 195
    },
    {
      "epoch": 1.53,
      "learning_rate": 2e-05,
      "loss": 0.5456,
      "step": 196
    },
    {
      "epoch": 1.53,
      "learning_rate": 2e-05,
      "loss": 0.4926,
      "step": 197
    },
    {
      "epoch": 1.54,
      "learning_rate": 2e-05,
      "loss": 0.5622,
      "step": 198
    },
    {
      "epoch": 1.55,
      "learning_rate": 2e-05,
      "loss": 0.5448,
      "step": 199
    },
    {
      "epoch": 1.56,
      "learning_rate": 2e-05,
      "loss": 0.5361,
      "step": 200
    },
    {
      "epoch": 1.56,
      "learning_rate": 2e-05,
      "loss": 0.5764,
      "step": 201
    },
    {
      "epoch": 1.57,
      "learning_rate": 2e-05,
      "loss": 0.4958,
      "step": 202
    },
    {
      "epoch": 1.58,
      "learning_rate": 2e-05,
      "loss": 0.5375,
      "step": 203
    },
    {
      "epoch": 1.59,
      "learning_rate": 2e-05,
      "loss": 0.5555,
      "step": 204
    },
    {
      "epoch": 1.6,
      "learning_rate": 2e-05,
      "loss": 0.5412,
      "step": 205
    },
    {
      "epoch": 1.6,
      "learning_rate": 2e-05,
      "loss": 0.579,
      "step": 206
    },
    {
      "epoch": 1.61,
      "learning_rate": 2e-05,
      "loss": 0.5535,
      "step": 207
    },
    {
      "epoch": 1.62,
      "learning_rate": 2e-05,
      "loss": 0.5243,
      "step": 208
    },
    {
      "epoch": 1.63,
      "learning_rate": 2e-05,
      "loss": 0.5401,
      "step": 209
    },
    {
      "epoch": 1.63,
      "learning_rate": 2e-05,
      "loss": 0.5584,
      "step": 210
    },
    {
      "epoch": 1.64,
      "learning_rate": 2e-05,
      "loss": 0.527,
      "step": 211
    },
    {
      "epoch": 1.65,
      "learning_rate": 2e-05,
      "loss": 0.5394,
      "step": 212
    },
    {
      "epoch": 1.66,
      "learning_rate": 2e-05,
      "loss": 0.5316,
      "step": 213
    },
    {
      "epoch": 1.67,
      "learning_rate": 2e-05,
      "loss": 0.5354,
      "step": 214
    },
    {
      "epoch": 1.67,
      "learning_rate": 2e-05,
      "loss": 0.5659,
      "step": 215
    },
    {
      "epoch": 1.68,
      "learning_rate": 2e-05,
      "loss": 0.5067,
      "step": 216
    },
    {
      "epoch": 1.69,
      "learning_rate": 2e-05,
      "loss": 0.5488,
      "step": 217
    },
    {
      "epoch": 1.7,
      "learning_rate": 2e-05,
      "loss": 0.5642,
      "step": 218
    },
    {
      "epoch": 1.7,
      "learning_rate": 2e-05,
      "loss": 0.518,
      "step": 219
    },
    {
      "epoch": 1.71,
      "learning_rate": 2e-05,
      "loss": 0.5351,
      "step": 220
    },
    {
      "epoch": 1.72,
      "learning_rate": 2e-05,
      "loss": 0.5426,
      "step": 221
    },
    {
      "epoch": 1.73,
      "learning_rate": 2e-05,
      "loss": 0.5141,
      "step": 222
    },
    {
      "epoch": 1.74,
      "learning_rate": 2e-05,
      "loss": 0.5311,
      "step": 223
    },
    {
      "epoch": 1.74,
      "learning_rate": 2e-05,
      "loss": 0.5549,
      "step": 224
    },
    {
      "epoch": 1.75,
      "learning_rate": 2e-05,
      "loss": 0.5635,
      "step": 225
    },
    {
      "epoch": 1.76,
      "learning_rate": 2e-05,
      "loss": 0.5269,
      "step": 226
    },
    {
      "epoch": 1.77,
      "learning_rate": 2e-05,
      "loss": 0.5967,
      "step": 227
    },
    {
      "epoch": 1.77,
      "learning_rate": 2e-05,
      "loss": 0.5615,
      "step": 228
    },
    {
      "epoch": 1.78,
      "learning_rate": 2e-05,
      "loss": 0.5695,
      "step": 229
    },
    {
      "epoch": 1.79,
      "learning_rate": 2e-05,
      "loss": 0.562,
      "step": 230
    },
    {
      "epoch": 1.8,
      "learning_rate": 2e-05,
      "loss": 0.5537,
      "step": 231
    },
    {
      "epoch": 1.81,
      "learning_rate": 2e-05,
      "loss": 0.5566,
      "step": 232
    },
    {
      "epoch": 1.81,
      "learning_rate": 2e-05,
      "loss": 0.5354,
      "step": 233
    },
    {
      "epoch": 1.82,
      "learning_rate": 2e-05,
      "loss": 0.5091,
      "step": 234
    },
    {
      "epoch": 1.83,
      "learning_rate": 2e-05,
      "loss": 0.5523,
      "step": 235
    },
    {
      "epoch": 1.84,
      "learning_rate": 2e-05,
      "loss": 0.5343,
      "step": 236
    },
    {
      "epoch": 1.84,
      "learning_rate": 2e-05,
      "loss": 0.5351,
      "step": 237
    },
    {
      "epoch": 1.85,
      "learning_rate": 2e-05,
      "loss": 0.5576,
      "step": 238
    },
    {
      "epoch": 1.86,
      "learning_rate": 2e-05,
      "loss": 0.5375,
      "step": 239
    },
    {
      "epoch": 1.87,
      "learning_rate": 2e-05,
      "loss": 0.5407,
      "step": 240
    },
    {
      "epoch": 1.88,
      "learning_rate": 2e-05,
      "loss": 0.5172,
      "step": 241
    },
    {
      "epoch": 1.88,
      "learning_rate": 2e-05,
      "loss": 0.5273,
      "step": 242
    },
    {
      "epoch": 1.89,
      "learning_rate": 2e-05,
      "loss": 0.539,
      "step": 243
    },
    {
      "epoch": 1.9,
      "learning_rate": 2e-05,
      "loss": 0.5369,
      "step": 244
    },
    {
      "epoch": 1.91,
      "learning_rate": 2e-05,
      "loss": 0.5166,
      "step": 245
    },
    {
      "epoch": 1.91,
      "learning_rate": 2e-05,
      "loss": 0.5286,
      "step": 246
    },
    {
      "epoch": 1.92,
      "learning_rate": 2e-05,
      "loss": 0.5319,
      "step": 247
    },
    {
      "epoch": 1.93,
      "learning_rate": 2e-05,
      "loss": 0.5798,
      "step": 248
    },
    {
      "epoch": 1.94,
      "learning_rate": 2e-05,
      "loss": 0.5527,
      "step": 249
    },
    {
      "epoch": 1.95,
      "learning_rate": 2e-05,
      "loss": 0.5296,
      "step": 250
    },
    {
      "epoch": 1.95,
      "learning_rate": 2e-05,
      "loss": 0.5473,
      "step": 251
    },
    {
      "epoch": 1.96,
      "learning_rate": 2e-05,
      "loss": 0.5458,
      "step": 252
    },
    {
      "epoch": 1.97,
      "learning_rate": 2e-05,
      "loss": 0.5037,
      "step": 253
    },
    {
      "epoch": 1.98,
      "learning_rate": 2e-05,
      "loss": 0.5448,
      "step": 254
    },
    {
      "epoch": 1.98,
      "learning_rate": 2e-05,
      "loss": 0.5801,
      "step": 255
    },
    {
      "epoch": 1.99,
      "learning_rate": 2e-05,
      "loss": 0.5468,
      "step": 256
    },
    {
      "epoch": 1.99,
      "step": 256,
      "total_flos": 2639400744779776.0,
      "train_loss": 0.6092639155685902,
      "train_runtime": 16252.0378,
      "train_samples_per_second": 2.017,
      "train_steps_per_second": 0.016
    }
  ],
  "max_steps": 256,
  "num_train_epochs": 2,
  "total_flos": 2639400744779776.0,
  "trial_name": null,
  "trial_params": null
}