{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 500,
  "global_step": 125,
  "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": 1.6896,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.7143,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.6969,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.6016,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.4545,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.3691,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.2808,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.2052,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.0442,
      "step": 9
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.9511,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.8863,
      "step": 11
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7961,
      "step": 12
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.72,
      "step": 13
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6786,
      "step": 14
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6351,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5312,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5145,
      "step": 17
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6165,
      "step": 18
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5138,
      "step": 19
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5425,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5166,
      "step": 21
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4996,
      "step": 22
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5757,
      "step": 23
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5183,
      "step": 24
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5349,
      "step": 25
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4842,
      "step": 26
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.4626,
      "step": 27
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.4677,
      "step": 28
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.4644,
      "step": 29
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.4195,
      "step": 30
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.498,
      "step": 31
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.4685,
      "step": 32
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.4256,
      "step": 33
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.4406,
      "step": 34
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.3847,
      "step": 35
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.4039,
      "step": 36
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.3879,
      "step": 37
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.3924,
      "step": 38
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4439,
      "step": 39
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4041,
      "step": 40
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.3852,
      "step": 41
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.3492,
      "step": 42
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.3613,
      "step": 43
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.381,
      "step": 44
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.3581,
      "step": 45
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.3238,
      "step": 46
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.3031,
      "step": 47
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.265,
      "step": 48
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.3163,
      "step": 49
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.3281,
      "step": 50
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.6814,
      "step": 51
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.6904,
      "step": 52
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.6387,
      "step": 53
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.6075,
      "step": 54
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.5507,
      "step": 55
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.5008,
      "step": 56
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.5305,
      "step": 57
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.4997,
      "step": 58
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.4824,
      "step": 59
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.5156,
      "step": 60
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.4761,
      "step": 61
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.5306,
      "step": 62
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.4929,
      "step": 63
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.4895,
      "step": 64
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.5044,
      "step": 65
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.5326,
      "step": 66
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.5032,
      "step": 67
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.4838,
      "step": 68
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.4525,
      "step": 69
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.4486,
      "step": 70
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.4566,
      "step": 71
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.4455,
      "step": 72
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.4226,
      "step": 73
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.4411,
      "step": 74
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.4551,
      "step": 75
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.4208,
      "step": 76
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.4548,
      "step": 77
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.4259,
      "step": 78
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.4031,
      "step": 79
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.3806,
      "step": 80
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.4023,
      "step": 81
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.4011,
      "step": 82
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.4161,
      "step": 83
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.3832,
      "step": 84
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.3898,
      "step": 85
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.3118,
      "step": 86
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.3989,
      "step": 87
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.4115,
      "step": 88
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.3554,
      "step": 89
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.3859,
      "step": 90
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.3187,
      "step": 91
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.3141,
      "step": 92
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.3413,
      "step": 93
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.3262,
      "step": 94
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.3795,
      "step": 95
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.2989,
      "step": 96
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.2695,
      "step": 97
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.2995,
      "step": 98
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.2987,
      "step": 99
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.3816,
      "step": 100
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.6736,
      "step": 101
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.5777,
      "step": 102
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.567,
      "step": 103
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.5903,
      "step": 104
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.5656,
      "step": 105
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.5903,
      "step": 106
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.5514,
      "step": 107
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.5188,
      "step": 108
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.4504,
      "step": 109
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.4714,
      "step": 110
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.5389,
      "step": 111
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.4501,
      "step": 112
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.5058,
      "step": 113
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.5037,
      "step": 114
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.506,
      "step": 115
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.4237,
      "step": 116
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.505,
      "step": 117
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.4254,
      "step": 118
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.4155,
      "step": 119
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.4948,
      "step": 120
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.4181,
      "step": 121
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.4383,
      "step": 122
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.3929,
      "step": 123
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.4445,
      "step": 124
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.4266,
      "step": 125
    }
  ],
  "logging_steps": 1,
  "max_steps": 250,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 9948052490158080.0,
  "trial_name": null,
  "trial_params": null
}