{
  "best_metric": 0.8072407045009785,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-30/checkpoint-96",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 96,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.605053186416626,
      "learning_rate": 0.00034121516722065634,
      "loss": 0.5667,
      "step": 48
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7475538160469667,
      "eval_f1": 0.792604501607717,
      "eval_loss": 0.49347442388534546,
      "eval_precision": 0.6725784447476125,
      "eval_recall": 0.9647749510763209,
      "eval_runtime": 27.2639,
      "eval_samples_per_second": 37.486,
      "eval_steps_per_second": 0.587,
      "step": 48
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.9404067993164062,
      "learning_rate": 0.0,
      "loss": 0.4806,
      "step": 96
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8072407045009785,
      "eval_f1": 0.8233183856502243,
      "eval_loss": 0.44217967987060547,
      "eval_precision": 0.7599337748344371,
      "eval_recall": 0.898238747553816,
      "eval_runtime": 27.0528,
      "eval_samples_per_second": 37.778,
      "eval_steps_per_second": 0.591,
      "step": 96
    }
  ],
  "logging_steps": 500,
  "max_steps": 96,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 471390394560.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9330503881025105,
    "learning_rate": 0.0006824303344413127,
    "num_train_epochs": 2,
    "temperature": 23
  }
}