trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.33,
      "learning_rate": 1e-05,
      "loss": 12.2131,
      "step": 1
    },
    {
      "epoch": 0.67,
      "learning_rate": 1e-05,
      "loss": 7.8697,
      "step": 2
    },
    {
      "epoch": 1.0,
      "learning_rate": 1e-05,
      "loss": 9.3525,
      "step": 3
    },
    {
      "epoch": 1.0,
      "step": 3,
      "total_flos": 1433420755200000.0,
      "train_loss": 9.811760266621908,
      "train_runtime": 50.4209,
      "train_samples_per_second": 0.059,
      "train_steps_per_second": 0.059
    }
  ],
  "logging_steps": 1,
  "max_steps": 3,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "total_flos": 1433420755200000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}