run-46/checkpoint-172/trainer_state.json

{
  "best_metric": 0.7413333333333333,
  "best_model_checkpoint": "Bert_tinybert-distilled/run-46/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": 1.144088864326477,
      "learning_rate": 0.00012140663356209371,
      "loss": 0.5667,
      "step": 172
    },
    {
      "epoch": 1.0,
      "eval_AUC": 0.8204142222222222,
      "eval_BAC": 0.7413333333333334,
      "eval_MCC": 0.4830033837261804,
      "eval_PR_AUC": 0.7818076111266022,
      "eval_accuracy": 0.7413333333333333,
      "eval_loss": 0.4875263571739197,
      "eval_runtime": 6.201,
      "eval_samples_per_second": 241.896,
      "eval_steps_per_second": 7.579,
      "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": 0.8749912051807918,
    "learning_rate": 0.00013489625951343745,
    "num_train_epochs": 10,
    "temperature": 4
  }
}