run-28/checkpoint-172/trainer_state.json

{
  "best_metric": 0.744,
  "best_model_checkpoint": "Bert_tinybert-distilled/run-28/checkpoint-172",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 172,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.6000565886497498,
      "learning_rate": 0.0001693455095416105,
      "loss": 0.4186,
      "step": 172
    },
    {
      "epoch": 1.0,
      "eval_AUC": 0.8243911111111111,
      "eval_BAC": 0.744,
      "eval_MCC": 0.4881406047441659,
      "eval_PR_AUC": 0.7779068309480023,
      "eval_accuracy": 0.744,
      "eval_loss": 0.38628360629081726,
      "eval_runtime": 6.2264,
      "eval_samples_per_second": 240.911,
      "eval_steps_per_second": 7.549,
      "step": 172
    }
  ],
  "logging_steps": 500,
  "max_steps": 1032,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 450377730000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.6332684113781645,
    "learning_rate": 0.0002032146114499326,
    "num_train_epochs": 6,
    "temperature": 30
  }
}