{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 0.0,
      "loss": 6.3097,
      "step": 1
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-06,
      "loss": 6.2197,
      "step": 2
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.5849625007211562e-06,
      "loss": 6.235,
      "step": 3
    },
    {
      "epoch": 0.36,
      "learning_rate": 2e-06,
      "loss": 5.9965,
      "step": 4
    },
    {
      "epoch": 0.45,
      "learning_rate": 2e-06,
      "loss": 4.9695,
      "step": 5
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-06,
      "loss": 4.3271,
      "step": 6
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-06,
      "loss": 1.8078,
      "step": 7
    },
    {
      "epoch": 0.73,
      "learning_rate": 2e-06,
      "loss": 1.0825,
      "step": 8
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-06,
      "loss": 0.6882,
      "step": 9
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-06,
      "loss": 0.5505,
      "step": 10
    },
    {
      "epoch": 1.0,
      "learning_rate": 2e-06,
      "loss": 0.3077,
      "step": 11
    },
    {
      "epoch": 1.09,
      "learning_rate": 2e-06,
      "loss": 0.3388,
      "step": 12
    },
    {
      "epoch": 1.18,
      "learning_rate": 2e-06,
      "loss": 0.3057,
      "step": 13
    },
    {
      "epoch": 1.27,
      "learning_rate": 2e-06,
      "loss": 0.29,
      "step": 14
    },
    {
      "epoch": 1.36,
      "learning_rate": 2e-06,
      "loss": 0.2837,
      "step": 15
    },
    {
      "epoch": 1.45,
      "learning_rate": 2e-06,
      "loss": 0.2941,
      "step": 16
    },
    {
      "epoch": 1.55,
      "learning_rate": 2e-06,
      "loss": 0.2905,
      "step": 17
    },
    {
      "epoch": 1.64,
      "learning_rate": 2e-06,
      "loss": 0.3125,
      "step": 18
    },
    {
      "epoch": 1.73,
      "learning_rate": 2e-06,
      "loss": 0.2781,
      "step": 19
    },
    {
      "epoch": 1.82,
      "learning_rate": 2e-06,
      "loss": 0.2785,
      "step": 20
    },
    {
      "epoch": 1.91,
      "learning_rate": 2e-06,
      "loss": 0.2979,
      "step": 21
    },
    {
      "epoch": 2.0,
      "learning_rate": 2e-06,
      "loss": 0.2613,
      "step": 22
    },
    {
      "epoch": 2.09,
      "learning_rate": 2e-06,
      "loss": 0.2672,
      "step": 23
    },
    {
      "epoch": 2.18,
      "learning_rate": 2e-06,
      "loss": 0.2744,
      "step": 24
    },
    {
      "epoch": 2.27,
      "learning_rate": 2e-06,
      "loss": 0.2552,
      "step": 25
    },
    {
      "epoch": 2.36,
      "learning_rate": 2e-06,
      "loss": 0.2093,
      "step": 26
    },
    {
      "epoch": 2.45,
      "learning_rate": 2e-06,
      "loss": 0.2445,
      "step": 27
    },
    {
      "epoch": 2.55,
      "learning_rate": 2e-06,
      "loss": 0.2397,
      "step": 28
    },
    {
      "epoch": 2.64,
      "learning_rate": 2e-06,
      "loss": 0.2134,
      "step": 29
    },
    {
      "epoch": 2.73,
      "learning_rate": 2e-06,
      "loss": 0.1786,
      "step": 30
    },
    {
      "epoch": 2.82,
      "learning_rate": 2e-06,
      "loss": 0.2645,
      "step": 31
    },
    {
      "epoch": 2.91,
      "learning_rate": 2e-06,
      "loss": 0.2503,
      "step": 32
    },
    {
      "epoch": 3.0,
      "learning_rate": 2e-06,
      "loss": 0.1944,
      "step": 33
    },
    {
      "epoch": 3.09,
      "learning_rate": 2e-06,
      "loss": 0.155,
      "step": 34
    },
    {
      "epoch": 3.18,
      "learning_rate": 2e-06,
      "loss": 0.1626,
      "step": 35
    },
    {
      "epoch": 3.27,
      "learning_rate": 2e-06,
      "loss": 0.1659,
      "step": 36
    },
    {
      "epoch": 3.36,
      "learning_rate": 2e-06,
      "loss": 0.2184,
      "step": 37
    },
    {
      "epoch": 3.45,
      "learning_rate": 2e-06,
      "loss": 0.1362,
      "step": 38
    },
    {
      "epoch": 3.55,
      "learning_rate": 2e-06,
      "loss": 0.1553,
      "step": 39
    },
    {
      "epoch": 3.64,
      "learning_rate": 2e-06,
      "loss": 0.1637,
      "step": 40
    },
    {
      "epoch": 3.73,
      "learning_rate": 2e-06,
      "loss": 0.148,
      "step": 41
    },
    {
      "epoch": 3.82,
      "learning_rate": 2e-06,
      "loss": 0.146,
      "step": 42
    },
    {
      "epoch": 3.91,
      "learning_rate": 2e-06,
      "loss": 0.1595,
      "step": 43
    },
    {
      "epoch": 4.0,
      "learning_rate": 2e-06,
      "loss": 0.1222,
      "step": 44
    },
    {
      "epoch": 4.09,
      "learning_rate": 2e-06,
      "loss": 0.1031,
      "step": 45
    },
    {
      "epoch": 4.18,
      "learning_rate": 2e-06,
      "loss": 0.0905,
      "step": 46
    },
    {
      "epoch": 4.27,
      "learning_rate": 2e-06,
      "loss": 0.0814,
      "step": 47
    },
    {
      "epoch": 4.36,
      "learning_rate": 2e-06,
      "loss": 0.0868,
      "step": 48
    },
    {
      "epoch": 4.45,
      "learning_rate": 2e-06,
      "loss": 0.0742,
      "step": 49
    },
    {
      "epoch": 4.55,
      "learning_rate": 2e-06,
      "loss": 0.0694,
      "step": 50
    },
    {
      "epoch": 4.64,
      "learning_rate": 2e-06,
      "loss": 0.091,
      "step": 51
    },
    {
      "epoch": 4.73,
      "learning_rate": 2e-06,
      "loss": 0.1032,
      "step": 52
    },
    {
      "epoch": 4.82,
      "learning_rate": 2e-06,
      "loss": 0.097,
      "step": 53
    },
    {
      "epoch": 4.91,
      "learning_rate": 2e-06,
      "loss": 0.0609,
      "step": 54
    },
    {
      "epoch": 5.0,
      "learning_rate": 2e-06,
      "loss": 0.078,
      "step": 55
    },
    {
      "epoch": 5.09,
      "learning_rate": 2e-06,
      "loss": 0.0203,
      "step": 56
    },
    {
      "epoch": 5.18,
      "learning_rate": 2e-06,
      "loss": 0.0806,
      "step": 57
    },
    {
      "epoch": 5.27,
      "learning_rate": 2e-06,
      "loss": 0.0413,
      "step": 58
    },
    {
      "epoch": 5.36,
      "learning_rate": 2e-06,
      "loss": 0.0682,
      "step": 59
    },
    {
      "epoch": 5.45,
      "learning_rate": 2e-06,
      "loss": 0.0339,
      "step": 60
    },
    {
      "epoch": 5.55,
      "learning_rate": 2e-06,
      "loss": 0.0209,
      "step": 61
    },
    {
      "epoch": 5.64,
      "learning_rate": 2e-06,
      "loss": 0.035,
      "step": 62
    },
    {
      "epoch": 5.73,
      "learning_rate": 2e-06,
      "loss": 0.0646,
      "step": 63
    },
    {
      "epoch": 5.82,
      "learning_rate": 2e-06,
      "loss": 0.0421,
      "step": 64
    },
    {
      "epoch": 5.91,
      "learning_rate": 2e-06,
      "loss": 0.0404,
      "step": 65
    },
    {
      "epoch": 6.0,
      "learning_rate": 2e-06,
      "loss": 0.0243,
      "step": 66
    },
    {
      "epoch": 6.09,
      "learning_rate": 2e-06,
      "loss": 0.0266,
      "step": 67
    },
    {
      "epoch": 6.18,
      "learning_rate": 2e-06,
      "loss": 0.0221,
      "step": 68
    },
    {
      "epoch": 6.27,
      "learning_rate": 2e-06,
      "loss": 0.015,
      "step": 69
    },
    {
      "epoch": 6.36,
      "learning_rate": 2e-06,
      "loss": 0.0341,
      "step": 70
    },
    {
      "epoch": 6.45,
      "learning_rate": 2e-06,
      "loss": 0.0437,
      "step": 71
    },
    {
      "epoch": 6.55,
      "learning_rate": 2e-06,
      "loss": 0.0179,
      "step": 72
    },
    {
      "epoch": 6.64,
      "learning_rate": 2e-06,
      "loss": 0.0424,
      "step": 73
    },
    {
      "epoch": 6.73,
      "learning_rate": 2e-06,
      "loss": 0.043,
      "step": 74
    },
    {
      "epoch": 6.82,
      "learning_rate": 2e-06,
      "loss": 0.0203,
      "step": 75
    },
    {
      "epoch": 6.91,
      "learning_rate": 2e-06,
      "loss": 0.0204,
      "step": 76
    },
    {
      "epoch": 7.0,
      "learning_rate": 2e-06,
      "loss": 0.0286,
      "step": 77
    },
    {
      "epoch": 7.09,
      "learning_rate": 2e-06,
      "loss": 0.0094,
      "step": 78
    },
    {
      "epoch": 7.18,
      "learning_rate": 2e-06,
      "loss": 0.0245,
      "step": 79
    },
    {
      "epoch": 7.27,
      "learning_rate": 2e-06,
      "loss": 0.0267,
      "step": 80
    },
    {
      "epoch": 7.36,
      "learning_rate": 2e-06,
      "loss": 0.0034,
      "step": 81
    },
    {
      "epoch": 7.45,
      "learning_rate": 2e-06,
      "loss": 0.02,
      "step": 82
    },
    {
      "epoch": 7.55,
      "learning_rate": 2e-06,
      "loss": 0.0287,
      "step": 83
    },
    {
      "epoch": 7.64,
      "learning_rate": 2e-06,
      "loss": 0.016,
      "step": 84
    },
    {
      "epoch": 7.73,
      "learning_rate": 2e-06,
      "loss": 0.0204,
      "step": 85
    },
    {
      "epoch": 7.82,
      "learning_rate": 2e-06,
      "loss": 0.0084,
      "step": 86
    },
    {
      "epoch": 7.91,
      "learning_rate": 2e-06,
      "loss": 0.0328,
      "step": 87
    },
    {
      "epoch": 8.0,
      "learning_rate": 2e-06,
      "loss": 0.0038,
      "step": 88
    },
    {
      "epoch": 8.09,
      "learning_rate": 2e-06,
      "loss": 0.0028,
      "step": 89
    },
    {
      "epoch": 8.18,
      "learning_rate": 2e-06,
      "loss": 0.0007,
      "step": 90
    },
    {
      "epoch": 8.27,
      "learning_rate": 2e-06,
      "loss": 0.0025,
      "step": 91
    },
    {
      "epoch": 8.36,
      "learning_rate": 2e-06,
      "loss": 0.0021,
      "step": 92
    },
    {
      "epoch": 8.45,
      "learning_rate": 2e-06,
      "loss": 0.0227,
      "step": 93
    },
    {
      "epoch": 8.55,
      "learning_rate": 2e-06,
      "loss": 0.0049,
      "step": 94
    },
    {
      "epoch": 8.64,
      "learning_rate": 2e-06,
      "loss": 0.0144,
      "step": 95
    },
    {
      "epoch": 8.73,
      "learning_rate": 2e-06,
      "loss": 0.0057,
      "step": 96
    },
    {
      "epoch": 8.82,
      "learning_rate": 2e-06,
      "loss": 0.0002,
      "step": 97
    },
    {
      "epoch": 8.91,
      "learning_rate": 2e-06,
      "loss": 0.1342,
      "step": 98
    },
    {
      "epoch": 9.0,
      "learning_rate": 2e-06,
      "loss": 0.0287,
      "step": 99
    },
    {
      "epoch": 9.09,
      "learning_rate": 2e-06,
      "loss": 0.0003,
      "step": 100
    },
    {
      "epoch": 9.18,
      "learning_rate": 2e-06,
      "loss": 0.0073,
      "step": 101
    },
    {
      "epoch": 9.27,
      "learning_rate": 2e-06,
      "loss": 0.0001,
      "step": 102
    },
    {
      "epoch": 9.36,
      "learning_rate": 2e-06,
      "loss": 0.0052,
      "step": 103
    },
    {
      "epoch": 9.45,
      "learning_rate": 2e-06,
      "loss": 0.0031,
      "step": 104
    },
    {
      "epoch": 9.55,
      "learning_rate": 2e-06,
      "loss": 0.001,
      "step": 105
    },
    {
      "epoch": 9.64,
      "learning_rate": 2e-06,
      "loss": 0.035,
      "step": 106
    },
    {
      "epoch": 9.73,
      "learning_rate": 2e-06,
      "loss": 0.0291,
      "step": 107
    },
    {
      "epoch": 9.82,
      "learning_rate": 2e-06,
      "loss": 0.0303,
      "step": 108
    },
    {
      "epoch": 9.91,
      "learning_rate": 2e-06,
      "loss": 0.0034,
      "step": 109
    },
    {
      "epoch": 10.0,
      "learning_rate": 2e-06,
      "loss": 0.0051,
      "step": 110
    },
    {
      "epoch": 10.0,
      "step": 110,
      "total_flos": 3159825776640.0,
      "train_loss": 0.4391266070077439,
      "train_runtime": 3835.8947,
      "train_samples_per_second": 3.452,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 50000,
  "total_flos": 3159825776640.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}