trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.959322033898305,
  "global_step": 292,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.99,
      "eval_accuracy": 0.6217125382262997,
      "eval_loss": 0.7307831645011902,
      "eval_runtime": 20.3283,
      "eval_samples_per_second": 160.859,
      "eval_steps_per_second": 5.067,
      "step": 73
    },
    {
      "epoch": 1.99,
      "eval_accuracy": 0.6159021406727829,
      "eval_loss": 0.6529456377029419,
      "eval_runtime": 20.3385,
      "eval_samples_per_second": 160.779,
      "eval_steps_per_second": 5.064,
      "step": 147
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6844036697247706,
      "eval_loss": 0.6294939517974854,
      "eval_runtime": 20.3517,
      "eval_samples_per_second": 160.674,
      "eval_steps_per_second": 5.061,
      "step": 221
    },
    {
      "epoch": 3.96,
      "eval_accuracy": 0.6743119266055045,
      "eval_loss": 0.8184447884559631,
      "eval_runtime": 20.3635,
      "eval_samples_per_second": 160.582,
      "eval_steps_per_second": 5.058,
      "step": 292
    },
    {
      "epoch": 3.96,
      "step": 292,
      "total_flos": 3.4795051274993664e+16,
      "train_loss": 0.5905772692536655,
      "train_runtime": 808.3468,
      "train_samples_per_second": 46.648,
      "train_steps_per_second": 0.361
    }
  ],
  "max_steps": 292,
  "num_train_epochs": 4,
  "total_flos": 3.4795051274993664e+16,
  "trial_name": null,
  "trial_params": null
}