{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9425981873111784,
  "global_step": 160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 6e-05,
      "loss": 2.2136,
      "step": 2
    },
    {
      "epoch": 0.05,
      "learning_rate": 6e-05,
      "loss": 2.1745,
      "step": 4
    },
    {
      "epoch": 0.07,
      "learning_rate": 6e-05,
      "loss": 2.2121,
      "step": 6
    },
    {
      "epoch": 0.1,
      "learning_rate": 6e-05,
      "loss": 2.1942,
      "step": 8
    },
    {
      "epoch": 0.12,
      "learning_rate": 6e-05,
      "loss": 2.213,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 6e-05,
      "loss": 2.1835,
      "step": 12
    },
    {
      "epoch": 0.17,
      "learning_rate": 6e-05,
      "loss": 2.2074,
      "step": 14
    },
    {
      "epoch": 0.19,
      "learning_rate": 6e-05,
      "loss": 2.2165,
      "step": 16
    },
    {
      "epoch": 0.22,
      "learning_rate": 6e-05,
      "loss": 2.1942,
      "step": 18
    },
    {
      "epoch": 0.24,
      "learning_rate": 6e-05,
      "loss": 2.1919,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 6e-05,
      "loss": 2.1598,
      "step": 22
    },
    {
      "epoch": 0.29,
      "learning_rate": 6e-05,
      "loss": 2.2082,
      "step": 24
    },
    {
      "epoch": 0.31,
      "learning_rate": 6e-05,
      "loss": 2.1798,
      "step": 26
    },
    {
      "epoch": 0.34,
      "learning_rate": 6e-05,
      "loss": 2.1878,
      "step": 28
    },
    {
      "epoch": 0.36,
      "learning_rate": 6e-05,
      "loss": 2.198,
      "step": 30
    },
    {
      "epoch": 0.39,
      "learning_rate": 6e-05,
      "loss": 2.1458,
      "step": 32
    },
    {
      "epoch": 0.41,
      "learning_rate": 6e-05,
      "loss": 2.1913,
      "step": 34
    },
    {
      "epoch": 0.44,
      "learning_rate": 6e-05,
      "loss": 2.1581,
      "step": 36
    },
    {
      "epoch": 0.46,
      "learning_rate": 6e-05,
      "loss": 2.1761,
      "step": 38
    },
    {
      "epoch": 0.48,
      "learning_rate": 6e-05,
      "loss": 2.1474,
      "step": 40
    },
    {
      "epoch": 0.51,
      "learning_rate": 6e-05,
      "loss": 2.1736,
      "step": 42
    },
    {
      "epoch": 0.53,
      "learning_rate": 6e-05,
      "loss": 2.1988,
      "step": 44
    },
    {
      "epoch": 0.56,
      "learning_rate": 6e-05,
      "loss": 2.1796,
      "step": 46
    },
    {
      "epoch": 0.58,
      "learning_rate": 6e-05,
      "loss": 2.2004,
      "step": 48
    },
    {
      "epoch": 0.6,
      "learning_rate": 6e-05,
      "loss": 2.2067,
      "step": 50
    },
    {
      "epoch": 0.63,
      "learning_rate": 6e-05,
      "loss": 2.1998,
      "step": 52
    },
    {
      "epoch": 0.65,
      "learning_rate": 6e-05,
      "loss": 2.2015,
      "step": 54
    },
    {
      "epoch": 0.68,
      "learning_rate": 6e-05,
      "loss": 2.2152,
      "step": 56
    },
    {
      "epoch": 0.7,
      "learning_rate": 6e-05,
      "loss": 2.1614,
      "step": 58
    },
    {
      "epoch": 0.73,
      "learning_rate": 6e-05,
      "loss": 2.1996,
      "step": 60
    },
    {
      "epoch": 0.75,
      "learning_rate": 6e-05,
      "loss": 2.1909,
      "step": 62
    },
    {
      "epoch": 0.77,
      "learning_rate": 6e-05,
      "loss": 2.208,
      "step": 64
    },
    {
      "epoch": 0.8,
      "learning_rate": 6e-05,
      "loss": 2.1879,
      "step": 66
    },
    {
      "epoch": 0.82,
      "learning_rate": 6e-05,
      "loss": 2.1759,
      "step": 68
    },
    {
      "epoch": 0.85,
      "learning_rate": 6e-05,
      "loss": 2.1351,
      "step": 70
    },
    {
      "epoch": 0.87,
      "learning_rate": 6e-05,
      "loss": 2.1713,
      "step": 72
    },
    {
      "epoch": 0.89,
      "learning_rate": 6e-05,
      "loss": 2.1473,
      "step": 74
    },
    {
      "epoch": 0.92,
      "learning_rate": 6e-05,
      "loss": 2.1646,
      "step": 76
    },
    {
      "epoch": 0.94,
      "learning_rate": 6e-05,
      "loss": 2.1772,
      "step": 78
    },
    {
      "epoch": 0.97,
      "learning_rate": 6e-05,
      "loss": 2.1615,
      "step": 80
    },
    {
      "epoch": 0.99,
      "learning_rate": 6e-05,
      "loss": 2.1634,
      "step": 82
    },
    {
      "epoch": 1.02,
      "learning_rate": 6e-05,
      "loss": 3.03,
      "step": 84
    },
    {
      "epoch": 1.05,
      "learning_rate": 6e-05,
      "loss": 2.1659,
      "step": 86
    },
    {
      "epoch": 1.07,
      "learning_rate": 6e-05,
      "loss": 2.147,
      "step": 88
    },
    {
      "epoch": 1.1,
      "learning_rate": 6e-05,
      "loss": 2.1871,
      "step": 90
    },
    {
      "epoch": 1.12,
      "learning_rate": 6e-05,
      "loss": 2.1916,
      "step": 92
    },
    {
      "epoch": 1.15,
      "learning_rate": 6e-05,
      "loss": 2.1893,
      "step": 94
    },
    {
      "epoch": 1.17,
      "learning_rate": 6e-05,
      "loss": 2.17,
      "step": 96
    },
    {
      "epoch": 1.19,
      "learning_rate": 6e-05,
      "loss": 2.1516,
      "step": 98
    },
    {
      "epoch": 1.22,
      "learning_rate": 6e-05,
      "loss": 2.1433,
      "step": 100
    },
    {
      "epoch": 1.24,
      "learning_rate": 6e-05,
      "loss": 2.1705,
      "step": 102
    },
    {
      "epoch": 1.27,
      "learning_rate": 6e-05,
      "loss": 2.2087,
      "step": 104
    },
    {
      "epoch": 1.29,
      "learning_rate": 6e-05,
      "loss": 2.2392,
      "step": 106
    },
    {
      "epoch": 1.31,
      "learning_rate": 6e-05,
      "loss": 2.221,
      "step": 108
    },
    {
      "epoch": 1.34,
      "learning_rate": 6e-05,
      "loss": 2.1764,
      "step": 110
    },
    {
      "epoch": 1.36,
      "learning_rate": 6e-05,
      "loss": 2.1441,
      "step": 112
    },
    {
      "epoch": 1.39,
      "learning_rate": 6e-05,
      "loss": 2.2088,
      "step": 114
    },
    {
      "epoch": 1.41,
      "learning_rate": 6e-05,
      "loss": 2.137,
      "step": 116
    },
    {
      "epoch": 1.44,
      "learning_rate": 6e-05,
      "loss": 2.143,
      "step": 118
    },
    {
      "epoch": 1.46,
      "learning_rate": 6e-05,
      "loss": 2.1853,
      "step": 120
    },
    {
      "epoch": 1.48,
      "learning_rate": 6e-05,
      "loss": 2.1816,
      "step": 122
    },
    {
      "epoch": 1.51,
      "learning_rate": 6e-05,
      "loss": 2.1805,
      "step": 124
    },
    {
      "epoch": 1.53,
      "learning_rate": 6e-05,
      "loss": 2.2074,
      "step": 126
    },
    {
      "epoch": 1.56,
      "learning_rate": 6e-05,
      "loss": 2.1545,
      "step": 128
    },
    {
      "epoch": 1.58,
      "learning_rate": 6e-05,
      "loss": 2.1655,
      "step": 130
    },
    {
      "epoch": 1.6,
      "learning_rate": 6e-05,
      "loss": 2.1827,
      "step": 132
    },
    {
      "epoch": 1.63,
      "learning_rate": 6e-05,
      "loss": 2.1936,
      "step": 134
    },
    {
      "epoch": 1.65,
      "learning_rate": 6e-05,
      "loss": 2.1696,
      "step": 136
    },
    {
      "epoch": 1.68,
      "learning_rate": 6e-05,
      "loss": 2.2112,
      "step": 138
    },
    {
      "epoch": 1.7,
      "learning_rate": 6e-05,
      "loss": 2.2027,
      "step": 140
    },
    {
      "epoch": 1.73,
      "learning_rate": 6e-05,
      "loss": 2.1224,
      "step": 142
    },
    {
      "epoch": 1.75,
      "learning_rate": 6e-05,
      "loss": 2.2016,
      "step": 144
    },
    {
      "epoch": 1.77,
      "learning_rate": 6e-05,
      "loss": 2.1465,
      "step": 146
    },
    {
      "epoch": 1.8,
      "learning_rate": 6e-05,
      "loss": 2.1658,
      "step": 148
    },
    {
      "epoch": 1.82,
      "learning_rate": 6e-05,
      "loss": 2.188,
      "step": 150
    },
    {
      "epoch": 1.85,
      "learning_rate": 6e-05,
      "loss": 2.1806,
      "step": 152
    },
    {
      "epoch": 1.87,
      "learning_rate": 6e-05,
      "loss": 2.221,
      "step": 154
    },
    {
      "epoch": 1.89,
      "learning_rate": 6e-05,
      "loss": 2.1824,
      "step": 156
    },
    {
      "epoch": 1.92,
      "learning_rate": 6e-05,
      "loss": 2.147,
      "step": 158
    },
    {
      "epoch": 1.94,
      "learning_rate": 6e-05,
      "loss": 2.1873,
      "step": 160
    }
  ],
  "max_steps": 164,
  "num_train_epochs": 2,
  "total_flos": 7.131255647638651e+17,
  "trial_name": null,
  "trial_params": null
}