{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 24.0,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6,
      "learning_rate": 0.0013333333333333333,
      "loss": 1.2231,
      "step": 4
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0019259259259259258,
      "loss": 0.8597,
      "step": 8
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.001814814814814815,
      "loss": 0.5499,
      "step": 12
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.0016666666666666668,
      "loss": 0.3504,
      "step": 16
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.0015185185185185187,
      "loss": 0.1719,
      "step": 20
    },
    {
      "epoch": 9.6,
      "learning_rate": 0.0013703703703703705,
      "loss": 0.0797,
      "step": 24
    },
    {
      "epoch": 11.2,
      "learning_rate": 0.0012222222222222224,
      "loss": 0.0412,
      "step": 28
    },
    {
      "epoch": 12.8,
      "learning_rate": 0.0010740740740740743,
      "loss": 0.031,
      "step": 32
    },
    {
      "epoch": 14.4,
      "learning_rate": 0.000925925925925926,
      "loss": 0.0202,
      "step": 36
    },
    {
      "epoch": 16.0,
      "learning_rate": 0.0008148148148148148,
      "loss": 0.0126,
      "step": 40
    },
    {
      "epoch": 17.6,
      "learning_rate": 0.0006666666666666666,
      "loss": 0.0105,
      "step": 44
    },
    {
      "epoch": 19.2,
      "learning_rate": 0.0005185185185185185,
      "loss": 0.0075,
      "step": 48
    },
    {
      "epoch": 20.8,
      "learning_rate": 0.00037037037037037035,
      "loss": 0.0048,
      "step": 52
    },
    {
      "epoch": 22.4,
      "learning_rate": 0.0002222222222222222,
      "loss": 0.0053,
      "step": 56
    },
    {
      "epoch": 24.0,
      "learning_rate": 7.407407407407407e-05,
      "loss": 0.004,
      "step": 60
    }
  ],
  "logging_steps": 4,
  "max_steps": 60,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 2.0990290751913984e+16,
  "trial_name": null,
  "trial_params": null
}