trainer_state.json

{
  "best_global_step": 56,
  "best_metric": 0.0,
  "best_model_checkpoint": "./results/checkpoint-56",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 224,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.00856983382254839,
      "learning_rate": 3.948598130841122e-05,
      "loss": 0.1088,
      "step": 56
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9914869466515324,
      "eval_eer": 0.0,
      "eval_f1": 0.9939491730536507,
      "eval_loss": 0.06050656735897064,
      "eval_precision": 1.0,
      "eval_recall": 0.9879711307137129,
      "eval_runtime": 100.8612,
      "eval_samples_per_second": 17.47,
      "eval_steps_per_second": 0.278,
      "step": 56
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.007643812336027622,
      "learning_rate": 2.6401869158878506e-05,
      "loss": 0.0306,
      "step": 112
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9971623155505108,
      "eval_eer": 0.0,
      "eval_f1": 0.9979991996798719,
      "eval_loss": 0.018800094723701477,
      "eval_precision": 0.9960063897763578,
      "eval_recall": 1.0,
      "eval_runtime": 100.5792,
      "eval_samples_per_second": 17.519,
      "eval_steps_per_second": 0.278,
      "step": 112
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.009354319423437119,
      "learning_rate": 1.3317757009345794e-05,
      "loss": 0.0046,
      "step": 168
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9994324631101021,
      "eval_eer": 0.0,
      "eval_f1": 0.9995991983967936,
      "eval_loss": 0.008926239795982838,
      "eval_precision": 0.999198717948718,
      "eval_recall": 1.0,
      "eval_runtime": 98.0214,
      "eval_samples_per_second": 17.976,
      "eval_steps_per_second": 0.286,
      "step": 168
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.003849638160318136,
      "learning_rate": 2.336448598130841e-07,
      "loss": 0.0,
      "step": 224
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 1.0,
      "eval_eer": 0.0,
      "eval_f1": 1.0,
      "eval_loss": 2.7062263541210996e-10,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 98.6428,
      "eval_samples_per_second": 17.862,
      "eval_steps_per_second": 0.284,
      "step": 224
    }
  ],
  "logging_steps": 500,
  "max_steps": 224,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.753709041220321e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}