{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6666666666666666,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 1.0571,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003414213562373095,
      "loss": 0.7728,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.7006,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.857864376269051e-05,
      "loss": 0.6199,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0,
      "loss": 0.6004,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 500,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 3.57875933184e+16,
  "trial_name": null,
  "trial_params": null
}