trainer_state.json

{
  "best_global_step": 1846,
  "best_metric": 0.8753192477362434,
  "best_model_checkpoint": "outputs/phobert-hsd/checkpoint-best/checkpoint-1846",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1846,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 14.293025970458984,
      "learning_rate": 4.998769072267837e-05,
      "loss": 0.428,
      "step": 923
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8432783840260042,
      "eval_loss": 0.43178850412368774,
      "eval_runtime": 26.6614,
      "eval_samples_per_second": 161.545,
      "eval_steps_per_second": 5.064,
      "step": 923
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.456315040588379,
      "learning_rate": 4.995072162589518e-05,
      "loss": 0.3179,
      "step": 1846
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8753192477362434,
      "eval_loss": 0.37784627079963684,
      "eval_runtime": 26.6592,
      "eval_samples_per_second": 161.558,
      "eval_steps_per_second": 5.064,
      "step": 1846
    }
  ],
  "logging_steps": 923,
  "max_steps": 92300,
  "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": 7767634318166016.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}