{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0482994566311129,
  "global_step": 120,
  "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": 3.9383,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 4.297,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 4.4497,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 4.1237,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 3.9559,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 3.437,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.5411,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.796,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.3798,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.3777,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 3.0632,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.553,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.6332,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.2341,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.4234,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1505,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.6074,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1098,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.4064,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.0261,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.3355,
      "step": 21
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.2424,
      "step": 22
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9745,
      "step": 23
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1781,
      "step": 24
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9489,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.0495,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.13,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.7854,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.2759,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.8816,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9239,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.963,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9837,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.2882,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.501,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.2086,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.8153,
      "step": 37
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.906,
      "step": 38
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2252,
      "step": 39
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.1101,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.9331,
      "step": 41
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2006,
      "step": 42
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0551,
      "step": 43
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.8635,
      "step": 44
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.7884,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.8641,
      "step": 46
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.9707,
      "step": 47
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.638,
      "step": 48
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.6951,
      "step": 49
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.6499,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 4.0906,
      "step": 51
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.8166,
      "step": 52
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.2648,
      "step": 53
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.8758,
      "step": 54
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.4187,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.366,
      "step": 56
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.9111,
      "step": 57
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.1172,
      "step": 58
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2097,
      "step": 59
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.214,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2931,
      "step": 61
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.3941,
      "step": 62
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.0872,
      "step": 63
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.9758,
      "step": 64
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1443,
      "step": 65
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.8564,
      "step": 66
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.2959,
      "step": 67
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.111,
      "step": 68
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.3046,
      "step": 69
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.7973,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.2716,
      "step": 71
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.0394,
      "step": 72
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.3104,
      "step": 73
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.2478,
      "step": 74
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.9765,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.3162,
      "step": 76
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1498,
      "step": 77
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.9034,
      "step": 78
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1262,
      "step": 79
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1205,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.7249,
      "step": 81
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.0516,
      "step": 82
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.6536,
      "step": 83
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1003,
      "step": 84
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.9858,
      "step": 85
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.9845,
      "step": 86
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1915,
      "step": 87
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.9285,
      "step": 88
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.7922,
      "step": 89
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0684,
      "step": 91
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5623,
      "step": 92
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.6741,
      "step": 93
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.9877,
      "step": 94
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.8461,
      "step": 95
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.7781,
      "step": 96
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.6342,
      "step": 97
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5765,
      "step": 98
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.7775,
      "step": 99
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.7932,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 3.0298,
      "step": 101
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.9655,
      "step": 102
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.8451,
      "step": 103
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.5459,
      "step": 104
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.3641,
      "step": 105
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1216,
      "step": 106
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1987,
      "step": 107
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.9505,
      "step": 108
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.6535,
      "step": 109
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.2628,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0268,
      "step": 111
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.0586,
      "step": 112
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.1307,
      "step": 113
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.9611,
      "step": 114
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.3489,
      "step": 115
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.73,
      "step": 116
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.1855,
      "step": 117
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.138,
      "step": 118
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.0705,
      "step": 119
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.8792,
      "step": 120
    }
  ],
  "max_steps": 120,
  "num_train_epochs": 1,
  "total_flos": 479793488348160.0,
  "trial_name": null,
  "trial_params": null
}