{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.658385093167702,
  "eval_steps": 500,
  "global_step": 4500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.52,
      "learning_rate": 1.7929606625258798e-05,
      "loss": 0.3435,
      "step": 500
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.58592132505176e-05,
      "loss": 0.2441,
      "step": 1000
    },
    {
      "epoch": 1.55,
      "learning_rate": 1.3788819875776398e-05,
      "loss": 0.2039,
      "step": 1500
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.1718426501035198e-05,
      "loss": 0.1928,
      "step": 2000
    },
    {
      "epoch": 2.59,
      "learning_rate": 9.648033126293997e-06,
      "loss": 0.1636,
      "step": 2500
    },
    {
      "epoch": 3.11,
      "learning_rate": 7.577639751552796e-06,
      "loss": 0.1526,
      "step": 3000
    },
    {
      "epoch": 3.62,
      "learning_rate": 5.507246376811595e-06,
      "loss": 0.1317,
      "step": 3500
    },
    {
      "epoch": 4.14,
      "learning_rate": 3.436853002070394e-06,
      "loss": 0.1307,
      "step": 4000
    },
    {
      "epoch": 4.66,
      "learning_rate": 1.3664596273291927e-06,
      "loss": 0.1115,
      "step": 4500
    }
  ],
  "logging_steps": 500,
  "max_steps": 4830,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.893924389455872e+16,
  "trial_name": null,
  "trial_params": null
}