{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.998109640831758,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 6.25e-07,
      "loss": 0.2195,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.25e-06,
      "loss": 0.2205,
      "step": 2
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.8750000000000003e-06,
      "loss": 0.22,
      "step": 3
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.5e-06,
      "loss": 0.2206,
      "step": 4
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.125e-06,
      "loss": 0.2181,
      "step": 5
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.2178,
      "step": 6
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.3750000000000005e-06,
      "loss": 0.218,
      "step": 7
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-06,
      "loss": 0.2159,
      "step": 8
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.625e-06,
      "loss": 0.2109,
      "step": 9
    },
    {
      "epoch": 0.1,
      "learning_rate": 6.25e-06,
      "loss": 0.2079,
      "step": 10
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.20295506715774536,
      "eval_runtime": 7.6664,
      "eval_samples_per_second": 124.439,
      "eval_steps_per_second": 15.653,
      "step": 10
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.875e-06,
      "loss": 0.2063,
      "step": 11
    },
    {
      "epoch": 0.12,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.201,
      "step": 12
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.125000000000001e-06,
      "loss": 0.2004,
      "step": 13
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.750000000000001e-06,
      "loss": 0.196,
      "step": 14
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.375000000000001e-06,
      "loss": 0.1929,
      "step": 15
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 0.1892,
      "step": 16
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.681174353198687e-06,
      "loss": 0.1894,
      "step": 17
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.765357330018056e-06,
      "loss": 0.1845,
      "step": 18
    },
    {
      "epoch": 0.19,
      "learning_rate": 7.369343312364994e-06,
      "loss": 0.1832,
      "step": 19
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.671166329088278e-06,
      "loss": 0.1823,
      "step": 20
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.18013226985931396,
      "eval_runtime": 7.9493,
      "eval_samples_per_second": 120.011,
      "eval_steps_per_second": 15.096,
      "step": 20
    },
    {
      "epoch": 0.21,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.182,
      "step": 21
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.245515092739488e-06,
      "loss": 0.1818,
      "step": 22
    },
    {
      "epoch": 0.23,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.1828,
      "step": 23
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.801856965207338e-07,
      "loss": 0.1803,
      "step": 24
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.012853002380466e-08,
      "loss": 0.181,
      "step": 25
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.951556604879043e-07,
      "loss": 0.1796,
      "step": 26
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.5446867550656763e-06,
      "loss": 0.1838,
      "step": 27
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.0348748417303813e-06,
      "loss": 0.1815,
      "step": 28
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.775675848247425e-06,
      "loss": 0.1799,
      "step": 29
    },
    {
      "epoch": 0.3,
      "learning_rate": 6.545084971874737e-06,
      "loss": 0.1816,
      "step": 30
    },
    {
      "epoch": 0.3,
      "eval_loss": 0.17906256020069122,
      "eval_runtime": 7.8801,
      "eval_samples_per_second": 121.065,
      "eval_steps_per_second": 15.228,
      "step": 30
    },
    {
      "epoch": 0.31,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.18,
      "step": 31
    },
    {
      "epoch": 0.32,
      "learning_rate": 9.292243968009332e-06,
      "loss": 0.1797,
      "step": 32
    },
    {
      "epoch": 0.33,
      "learning_rate": 9.91964794299315e-06,
      "loss": 0.1809,
      "step": 33
    },
    {
      "epoch": 0.34,
      "learning_rate": 9.91964794299315e-06,
      "loss": 0.1782,
      "step": 34
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.292243968009333e-06,
      "loss": 0.1781,
      "step": 35
    },
    {
      "epoch": 0.36,
      "learning_rate": 8.11744900929367e-06,
      "loss": 0.1759,
      "step": 36
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.545084971874739e-06,
      "loss": 0.1752,
      "step": 37
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.775675848247427e-06,
      "loss": 0.1786,
      "step": 38
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.0348748417303834e-06,
      "loss": 0.1757,
      "step": 39
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.544686755065678e-06,
      "loss": 0.1755,
      "step": 40
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.17424167692661285,
      "eval_runtime": 7.7899,
      "eval_samples_per_second": 122.466,
      "eval_steps_per_second": 15.405,
      "step": 40
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.951556604879054e-07,
      "loss": 0.1749,
      "step": 41
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.0128530023805216e-08,
      "loss": 0.1763,
      "step": 42
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.8018569652073326e-07,
      "loss": 0.1761,
      "step": 43
    },
    {
      "epoch": 0.44,
      "learning_rate": 9.549150281252616e-07,
      "loss": 0.1782,
      "step": 44
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.245515092739486e-06,
      "loss": 0.176,
      "step": 45
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.887395330218426e-06,
      "loss": 0.1769,
      "step": 46
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.671166329088275e-06,
      "loss": 0.1768,
      "step": 47
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.369343312364992e-06,
      "loss": 0.1751,
      "step": 48
    },
    {
      "epoch": 0.49,
      "learning_rate": 8.765357330018054e-06,
      "loss": 0.1744,
      "step": 49
    },
    {
      "epoch": 0.5,
      "learning_rate": 9.681174353198685e-06,
      "loss": 0.1751,
      "step": 50
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.17338795959949493,
      "eval_runtime": 7.6323,
      "eval_samples_per_second": 124.995,
      "eval_steps_per_second": 15.723,
      "step": 50
    },
    {
      "epoch": 0.51,
      "learning_rate": 1e-05,
      "loss": 0.1758,
      "step": 51
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.68117435319869e-06,
      "loss": 0.1768,
      "step": 52
    },
    {
      "epoch": 0.53,
      "learning_rate": 8.765357330018058e-06,
      "loss": 0.1752,
      "step": 53
    },
    {
      "epoch": 0.54,
      "learning_rate": 7.369343312365004e-06,
      "loss": 0.1746,
      "step": 54
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.6711663290882805e-06,
      "loss": 0.1722,
      "step": 55
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.887395330218431e-06,
      "loss": 0.1735,
      "step": 56
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.24551509273949e-06,
      "loss": 0.1727,
      "step": 57
    },
    {
      "epoch": 0.58,
      "learning_rate": 9.549150281252646e-07,
      "loss": 0.1713,
      "step": 58
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.8018569652073214e-07,
      "loss": 0.1732,
      "step": 59
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.012853002380466e-08,
      "loss": 0.1738,
      "step": 60
    },
    {
      "epoch": 0.6,
      "eval_loss": 0.1722276508808136,
      "eval_runtime": 7.8157,
      "eval_samples_per_second": 122.061,
      "eval_steps_per_second": 15.354,
      "step": 60
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.951556604879032e-07,
      "loss": 0.1744,
      "step": 61
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.5446867550656746e-06,
      "loss": 0.1741,
      "step": 62
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.034874841730379e-06,
      "loss": 0.1749,
      "step": 63
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.775675848247422e-06,
      "loss": 0.1745,
      "step": 64
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.545084971874734e-06,
      "loss": 0.1751,
      "step": 65
    },
    {
      "epoch": 0.67,
      "learning_rate": 8.117449009293666e-06,
      "loss": 0.1751,
      "step": 66
    },
    {
      "epoch": 0.68,
      "learning_rate": 9.292243968009328e-06,
      "loss": 0.1757,
      "step": 67
    },
    {
      "epoch": 0.69,
      "learning_rate": 9.91964794299315e-06,
      "loss": 0.174,
      "step": 68
    },
    {
      "epoch": 0.7,
      "learning_rate": 9.91964794299315e-06,
      "loss": 0.1723,
      "step": 69
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.292243968009333e-06,
      "loss": 0.1734,
      "step": 70
    },
    {
      "epoch": 0.71,
      "eval_loss": 0.17138364911079407,
      "eval_runtime": 7.8154,
      "eval_samples_per_second": 122.067,
      "eval_steps_per_second": 15.354,
      "step": 70
    },
    {
      "epoch": 0.72,
      "learning_rate": 8.117449009293671e-06,
      "loss": 0.1725,
      "step": 71
    },
    {
      "epoch": 0.73,
      "learning_rate": 6.545084971874741e-06,
      "loss": 0.1738,
      "step": 72
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.77567584824743e-06,
      "loss": 0.1728,
      "step": 73
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.034874841730386e-06,
      "loss": 0.1723,
      "step": 74
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.5446867550656797e-06,
      "loss": 0.1757,
      "step": 75
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.951556604879059e-07,
      "loss": 0.174,
      "step": 76
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.0128530023805216e-08,
      "loss": 0.1739,
      "step": 77
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.8018569652073214e-07,
      "loss": 0.1728,
      "step": 78
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.549150281252605e-07,
      "loss": 0.1723,
      "step": 79
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.2455150927394835e-06,
      "loss": 0.1727,
      "step": 80
    },
    {
      "epoch": 0.81,
      "eval_loss": 0.17097879946231842,
      "eval_runtime": 7.8584,
      "eval_samples_per_second": 121.399,
      "eval_steps_per_second": 15.27,
      "step": 80
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.8873953302184244e-06,
      "loss": 0.1725,
      "step": 81
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.671166329088274e-06,
      "loss": 0.1725,
      "step": 82
    },
    {
      "epoch": 0.84,
      "learning_rate": 7.369343312364989e-06,
      "loss": 0.1728,
      "step": 83
    },
    {
      "epoch": 0.85,
      "learning_rate": 8.765357330018051e-06,
      "loss": 0.1724,
      "step": 84
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.681174353198685e-06,
      "loss": 0.171,
      "step": 85
    },
    {
      "epoch": 0.87,
      "learning_rate": 1e-05,
      "loss": 0.1717,
      "step": 86
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.681174353198689e-06,
      "loss": 0.174,
      "step": 87
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.76535733001807e-06,
      "loss": 0.1716,
      "step": 88
    },
    {
      "epoch": 0.9,
      "learning_rate": 7.369343312364998e-06,
      "loss": 0.1715,
      "step": 89
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.671166329088282e-06,
      "loss": 0.1712,
      "step": 90
    },
    {
      "epoch": 0.91,
      "eval_loss": 0.17013530433177948,
      "eval_runtime": 7.7133,
      "eval_samples_per_second": 123.683,
      "eval_steps_per_second": 15.558,
      "step": 90
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.887395330218433e-06,
      "loss": 0.1729,
      "step": 91
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.245515092739507e-06,
      "loss": 0.1731,
      "step": 92
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.549150281252557e-07,
      "loss": 0.1726,
      "step": 93
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.8018569652073492e-07,
      "loss": 0.1724,
      "step": 94
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.0128530023804104e-08,
      "loss": 0.1695,
      "step": 95
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.951556604879021e-07,
      "loss": 0.1711,
      "step": 96
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.5446867550656852e-06,
      "loss": 0.1726,
      "step": 97
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.034874841730377e-06,
      "loss": 0.1722,
      "step": 98
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.7756758482474195e-06,
      "loss": 0.171,
      "step": 99
    },
    {
      "epoch": 1.0,
      "step": 99,
      "total_flos": 6.416685198968095e+18,
      "train_loss": 0.18111299429879044,
      "train_runtime": 16732.1456,
      "train_samples_per_second": 48.562,
      "train_steps_per_second": 0.006
    }
  ],
  "max_steps": 99,
  "num_train_epochs": 1,
  "total_flos": 6.416685198968095e+18,
  "trial_name": null,
  "trial_params": null
}