trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.73972602739726,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6820040899795501,
      "eval_loss": 0.7493410706520081,
      "eval_runtime": 6.4955,
      "eval_samples_per_second": 301.132,
      "eval_steps_per_second": 37.718,
      "step": 365
    },
    {
      "epoch": 1.37,
      "grad_norm": 20.02265739440918,
      "learning_rate": 2.71689497716895e-05,
      "loss": 0.7495,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7055214723926381,
      "eval_loss": 0.7625377774238586,
      "eval_runtime": 6.586,
      "eval_samples_per_second": 296.992,
      "eval_steps_per_second": 37.2,
      "step": 730
    },
    {
      "epoch": 2.74,
      "grad_norm": 15.491150856018066,
      "learning_rate": 4.337899543378996e-06,
      "loss": 0.4253,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1095,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 410505404868000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}