run-2/checkpoint-172/trainer_state.json

{
  "best_metric": 0.6966666666666667,
  "best_model_checkpoint": "Bert_tinybert-distilled/run-2/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": 0.39246517419815063,
      "learning_rate": 4.639522353304605e-05,
      "loss": 0.2489,
      "step": 172
    },
    {
      "epoch": 1.0,
      "eval_AUC": 0.786481777777778,
      "eval_BAC": 0.6966666666666667,
      "eval_MCC": 0.4004741770824115,
      "eval_PR_AUC": 0.7486102682312443,
      "eval_accuracy": 0.6966666666666667,
      "eval_loss": 0.23812349140644073,
      "eval_runtime": 6.2157,
      "eval_samples_per_second": 241.324,
      "eval_steps_per_second": 7.561,
      "step": 172
    }
  ],
  "logging_steps": 500,
  "max_steps": 1720,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 0.3558486326039224,
    "learning_rate": 5.155024837005116e-05,
    "num_train_epochs": 10,
    "temperature": 4
  }
}