trainer_state.json

{
  "best_metric": 832.680419921875,
  "best_model_checkpoint": "./finetuned_qa11\\checkpoint-61",
  "epoch": 0.9908629441624366,
  "eval_steps": 500,
  "global_step": 61,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.81,
      "grad_norm": 7.192448616027832,
      "learning_rate": 2.4221311475409835e-06,
      "loss": 3.5889,
      "step": 50
    },
    {
      "epoch": 0.99,
      "eval_loss": 2.146763801574707,
      "eval_perplexity": 832.680419921875,
      "eval_runtime": 349.8385,
      "eval_samples_per_second": 1.103,
      "eval_steps_per_second": 0.071,
      "step": 61
    }
  ],
  "logging_steps": 50,
  "max_steps": 244,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 1028902699008000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}