trainer_state.json

{
  "best_global_step": 446,
  "best_metric": 0.8716257609159896,
  "best_model_checkpoint": "outputs/roberta-gru-spam-binary/checkpoint-446",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 446,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.4129560589790344,
      "learning_rate": 4.998771926094749e-05,
      "loss": 0.2949,
      "step": 446
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9054820415879017,
      "eval_f1": 0.8716257609159896,
      "eval_loss": 0.3097004294395447,
      "eval_precision": 0.9068871979144648,
      "eval_recall": 0.8482311913328375,
      "eval_runtime": 6.5502,
      "eval_samples_per_second": 242.283,
      "eval_steps_per_second": 7.633,
      "step": 446
    }
  ],
  "logging_steps": 446,
  "max_steps": 44600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}