run-12/checkpoint-172/trainer_state.json

{
  "best_metric": 0.7453333333333333,
  "best_model_checkpoint": "Bert_tinybert-distilled/run-12/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": 1.1232905387878418,
      "learning_rate": 0.00024417899038111995,
      "loss": 0.6117,
      "step": 172
    },
    {
      "epoch": 1.0,
      "eval_AUC": 0.8254151111111111,
      "eval_BAC": 0.7453333333333334,
      "eval_MCC": 0.4912976797633764,
      "eval_PR_AUC": 0.786302392146851,
      "eval_accuracy": 0.7453333333333333,
      "eval_loss": 0.5350800156593323,
      "eval_runtime": 6.3041,
      "eval_samples_per_second": 237.94,
      "eval_steps_per_second": 7.455,
      "step": 172
    }
  ],
  "logging_steps": 500,
  "max_steps": 1376,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 0.9633802106648812,
    "learning_rate": 0.0002790617032927085,
    "num_train_epochs": 8,
    "temperature": 2
  }
}