trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6722408026755853,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.67,
      "learning_rate": 3.885172798216277e-05,
      "loss": 0.2789,
      "step": 200
    },
    {
      "epoch": 0.67,
      "eval_accuracy": 0.9005498446091322,
      "eval_loss": 0.25626140832901,
      "eval_runtime": 39.2999,
      "eval_samples_per_second": 106.438,
      "eval_steps_per_second": 2.545,
      "step": 200
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.770345596432553e-05,
      "loss": 0.1738,
      "step": 400
    },
    {
      "epoch": 1.34,
      "eval_accuracy": 0.9029404733444896,
      "eval_loss": 0.2461186647415161,
      "eval_runtime": 39.2722,
      "eval_samples_per_second": 106.513,
      "eval_steps_per_second": 2.546,
      "step": 400
    }
  ],
  "max_steps": 897,
  "num_train_epochs": 3,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}