{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1259,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 2.674315975286849e-05,
      "loss": 1.2179,
      "step": 251
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.009708737864078e-05,
      "loss": 0.9696,
      "step": 502
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.3451015004413064e-05,
      "loss": 0.9012,
      "step": 753
    },
    {
      "epoch": 0.8,
      "learning_rate": 6.804942630185349e-06,
      "loss": 0.9003,
      "step": 1004
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.588702559576346e-07,
      "loss": 0.8934,
      "step": 1255
    }
  ],
  "logging_steps": 251,
  "max_steps": 1259,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 2.558733934657536e+16,
  "trial_name": null,
  "trial_params": null
}