{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.919499105545617,
  "eval_steps": 500,
  "global_step": 102,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.86,
      "learning_rate": 2e-05,
      "loss": 0.9902,
      "step": 100
    },
    {
      "epoch": 2.92,
      "step": 102,
      "total_flos": 472843687034880.0,
      "train_loss": 0.9878635780484069,
      "train_runtime": 16261.9174,
      "train_samples_per_second": 26.381,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 100,
  "max_steps": 102,
  "num_train_epochs": 3,
  "save_steps": 50,
  "total_flos": 472843687034880.0,
  "trial_name": null,
  "trial_params": null
}