{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.997849462365592,
  "eval_steps": 500,
  "global_step": 5810,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 0.0405,
      "step": 500
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.892270320001786e-05,
      "loss": 0.0701,
      "step": 1000
    },
    {
      "epoch": 1.29,
      "learning_rate": 4.5767203472630947e-05,
      "loss": 0.0582,
      "step": 1500
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.080760885882176e-05,
      "loss": 0.0539,
      "step": 2000
    },
    {
      "epoch": 2.15,
      "learning_rate": 3.447477078705983e-05,
      "loss": 0.0445,
      "step": 2500
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.731883751379496e-05,
      "loss": 0.0347,
      "step": 3000
    },
    {
      "epoch": 3.01,
      "learning_rate": 1.9975949771515295e-05,
      "loss": 0.0298,
      "step": 3500
    },
    {
      "epoch": 3.44,
      "learning_rate": 1.3054786108686476e-05,
      "loss": 0.0187,
      "step": 4000
    },
    {
      "epoch": 3.87,
      "learning_rate": 7.171330740426066e-06,
      "loss": 0.0163,
      "step": 4500
    },
    {
      "epoch": 4.3,
      "learning_rate": 2.8366930107707358e-06,
      "loss": 0.0119,
      "step": 5000
    },
    {
      "epoch": 4.73,
      "learning_rate": 4.3016059323062464e-07,
      "loss": 0.0088,
      "step": 5500
    }
  ],
  "logging_steps": 500,
  "max_steps": 5810,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4.924819960273306e+16,
  "trial_name": null,
  "trial_params": null
}