{
  "best_metric": 0.7573385518590998,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-33/checkpoint-48",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 48,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.3328498601913452,
      "learning_rate": 0.0002538644629516305,
      "loss": 0.5508,
      "step": 48
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7573385518590998,
      "eval_f1": 0.7933333333333334,
      "eval_loss": 0.4848305583000183,
      "eval_precision": 0.690856313497823,
      "eval_recall": 0.9315068493150684,
      "eval_runtime": 27.0185,
      "eval_samples_per_second": 37.826,
      "eval_steps_per_second": 0.592,
      "step": 48
    }
  ],
  "logging_steps": 500,
  "max_steps": 144,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 235695197280.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.8587810819129409,
    "learning_rate": 0.00038079669442744575,
    "num_train_epochs": 3,
    "temperature": 25
  }
}