{
  "best_metric": 0.8140900195694716,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-44/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": 2.16261887550354,
      "learning_rate": 0.000375603411294949,
      "loss": 0.5749,
      "step": 48
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7573385518590998,
      "eval_f1": 0.7977161500815662,
      "eval_loss": 0.49295851588249207,
      "eval_precision": 0.6839160839160839,
      "eval_recall": 0.9569471624266145,
      "eval_runtime": 27.1143,
      "eval_samples_per_second": 37.692,
      "eval_steps_per_second": 0.59,
      "step": 48
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.6236350536346436,
      "learning_rate": 0.0,
      "loss": 0.4792,
      "step": 96
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8140900195694716,
      "eval_f1": 0.8300536672629695,
      "eval_loss": 0.438692569732666,
      "eval_precision": 0.7644151565074135,
      "eval_recall": 0.9080234833659491,
      "eval_runtime": 27.0934,
      "eval_samples_per_second": 37.721,
      "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": 0.962924574908117,
    "learning_rate": 0.000751206822589898,
    "num_train_epochs": 2,
    "temperature": 26
  }
}