{
  "best_global_step": 939,
  "best_metric": 0.6539075374603271,
  "best_model_checkpoint": "classifier-clinc-MBbase-distilled/run-0/checkpoint-939",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 939,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.864516129032258,
      "eval_loss": 2.181514263153076,
      "eval_runtime": 9.1767,
      "eval_samples_per_second": 337.812,
      "eval_steps_per_second": 10.57,
      "step": 313
    },
    {
      "epoch": 1.5974440894568689,
      "grad_norm": 16.532678604125977,
      "learning_rate": 1.468583599574015e-05,
      "loss": 5.3862,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.922258064516129,
      "eval_loss": 0.8375440239906311,
      "eval_runtime": 8.7929,
      "eval_samples_per_second": 352.559,
      "eval_steps_per_second": 11.032,
      "step": 626
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.94,
      "eval_loss": 0.6539075374603271,
      "eval_runtime": 9.2337,
      "eval_samples_per_second": 335.726,
      "eval_steps_per_second": 10.505,
      "step": 939
    }
  ],
  "logging_steps": 500,
  "max_steps": 1878,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 222488892388608.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.39698487372040275,
    "num_train_epochs": 6,
    "temperature": 2.14433113176934
  }
}