{
  "best_metric": 0.8086666666666666,
  "best_model_checkpoint": "Bert_tinybert-distilled/run-46/checkpoint-688",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 688,
  "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
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.0164926052093506,
      "learning_rate": 0.00010791700761074997,
      "loss": 0.5222,
      "step": 344
    },
    {
      "epoch": 2.0,
      "eval_AUC": 0.8510257777777778,
      "eval_BAC": 0.7833333333333333,
      "eval_MCC": 0.592488303176525,
      "eval_PR_AUC": 0.7982461316549325,
      "eval_accuracy": 0.7833333333333333,
      "eval_loss": 0.4661383032798767,
      "eval_runtime": 6.2188,
      "eval_samples_per_second": 241.205,
      "eval_steps_per_second": 7.558,
      "step": 344
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.4330801963806152,
      "learning_rate": 9.442738165940621e-05,
      "loss": 0.5008,
      "step": 516
    },
    {
      "epoch": 3.0,
      "eval_AUC": 0.8654773333333334,
      "eval_BAC": 0.8046666666666666,
      "eval_MCC": 0.6106379641208982,
      "eval_PR_AUC": 0.8316559252323027,
      "eval_accuracy": 0.8046666666666666,
      "eval_loss": 0.4465043246746063,
      "eval_runtime": 6.2827,
      "eval_samples_per_second": 238.751,
      "eval_steps_per_second": 7.481,
      "step": 516
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.048581838607788,
      "learning_rate": 8.093775570806247e-05,
      "loss": 0.4885,
      "step": 688
    },
    {
      "epoch": 4.0,
      "eval_AUC": 0.8705902222222223,
      "eval_BAC": 0.8086666666666666,
      "eval_MCC": 0.6232385881903164,
      "eval_PR_AUC": 0.8414438628337162,
      "eval_accuracy": 0.8086666666666666,
      "eval_loss": 0.43882331252098083,
      "eval_runtime": 6.2705,
      "eval_samples_per_second": 239.215,
      "eval_steps_per_second": 7.495,
      "step": 688
    }
  ],
  "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": 1801510920000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.8749912051807918,
    "learning_rate": 0.00013489625951343745,
    "num_train_epochs": 10,
    "temperature": 4
  }
}