{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 112,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.2162,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.3762,
      "step": 4
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 2.2032,
      "step": 6
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.194,
      "step": 8
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001666666666666667,
      "loss": 2.1206,
      "step": 10
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 2.0957,
      "step": 12
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000196,
      "loss": 1.9569,
      "step": 14
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000192,
      "loss": 1.8578,
      "step": 16
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000188,
      "loss": 1.9662,
      "step": 18
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.9337,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018,
      "loss": 1.9318,
      "step": 22
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.9165,
      "step": 24
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000172,
      "loss": 1.8915,
      "step": 26
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000168,
      "loss": 1.9173,
      "step": 28
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000164,
      "loss": 1.8664,
      "step": 30
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016,
      "loss": 1.889,
      "step": 32
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.8596,
      "step": 34
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000152,
      "loss": 1.8794,
      "step": 36
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000148,
      "loss": 1.7943,
      "step": 38
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000144,
      "loss": 1.845,
      "step": 40
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014,
      "loss": 1.8562,
      "step": 42
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.8272,
      "step": 44
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000132,
      "loss": 1.7889,
      "step": 46
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.9758,
      "step": 48
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000124,
      "loss": 1.8208,
      "step": 50
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00012,
      "loss": 1.8818,
      "step": 52
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000116,
      "loss": 1.787,
      "step": 54
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.772,
      "step": 56
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.9647,
      "step": 58
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.8582,
      "step": 60
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 1.7461,
      "step": 62
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.6e-05,
      "loss": 1.9042,
      "step": 64
    },
    {
      "epoch": 0.59,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.8402,
      "step": 66
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.8639,
      "step": 68
    },
    {
      "epoch": 0.62,
      "learning_rate": 8.4e-05,
      "loss": 1.8673,
      "step": 70
    },
    {
      "epoch": 0.64,
      "learning_rate": 8e-05,
      "loss": 1.9321,
      "step": 72
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.6e-05,
      "loss": 1.836,
      "step": 74
    },
    {
      "epoch": 0.68,
      "learning_rate": 7.2e-05,
      "loss": 1.8173,
      "step": 76
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.7188,
      "step": 78
    },
    {
      "epoch": 0.71,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.7957,
      "step": 80
    },
    {
      "epoch": 0.73,
      "learning_rate": 6e-05,
      "loss": 1.8139,
      "step": 82
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.811,
      "step": 84
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.7955,
      "step": 86
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.8e-05,
      "loss": 1.9184,
      "step": 88
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.8547,
      "step": 90
    },
    {
      "epoch": 0.82,
      "learning_rate": 4e-05,
      "loss": 1.7657,
      "step": 92
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.6e-05,
      "loss": 1.9175,
      "step": 94
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.7922,
      "step": 96
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.896,
      "step": 98
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.4e-05,
      "loss": 1.8632,
      "step": 100
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 1.881,
      "step": 102
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.7914,
      "step": 104
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2e-05,
      "loss": 1.7627,
      "step": 106
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.7977,
      "step": 108
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.8781,
      "step": 110
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.7793,
      "step": 112
    }
  ],
  "logging_steps": 2,
  "max_steps": 112,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 2.9635038387634176e+16,
  "trial_name": null,
  "trial_params": null
}