trainer_state.json

{
  "best_global_step": 174,
  "best_metric": 0.0678451982799809,
  "best_model_checkpoint": "outputs/bilstm/checkpoint-174",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 174,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.6168758869171143,
      "learning_rate": 3.44e-06,
      "loss": 1.9259,
      "step": 87
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2055393586005831,
      "eval_loss": 1.9135147333145142,
      "eval_macro_f1": 0.04871307652444291,
      "eval_runtime": 0.1275,
      "eval_samples_per_second": 5380.078,
      "eval_steps_per_second": 86.269,
      "step": 87
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6895545125007629,
      "learning_rate": 6.92e-06,
      "loss": 1.8899,
      "step": 174
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3104956268221574,
      "eval_loss": 1.856755256652832,
      "eval_macro_f1": 0.0678451982799809,
      "eval_runtime": 0.1221,
      "eval_samples_per_second": 5619.767,
      "eval_steps_per_second": 90.113,
      "step": 174
    }
  ],
  "logging_steps": 87,
  "max_steps": 8700,
  "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": 64,
  "trial_name": null,
  "trial_params": null
}