{
  "best_metric": 0.7749510763209393,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-26/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": 1.8972866535186768,
      "learning_rate": 0.0002957944979629203,
      "loss": 0.5972,
      "step": 48
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7455968688845401,
      "eval_f1": 0.7906602254428341,
      "eval_loss": 0.5044679045677185,
      "eval_precision": 0.6716826265389877,
      "eval_recall": 0.9608610567514677,
      "eval_runtime": 27.1432,
      "eval_samples_per_second": 37.652,
      "eval_steps_per_second": 0.589,
      "step": 48
    },
    {
      "epoch": 2.0,
      "grad_norm": 11.614222526550293,
      "learning_rate": 0.00019719633197528018,
      "loss": 0.4926,
      "step": 96
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7749510763209393,
      "eval_f1": 0.7648261758691208,
      "eval_loss": 0.4870442748069763,
      "eval_precision": 0.8008565310492506,
      "eval_recall": 0.7318982387475538,
      "eval_runtime": 27.5457,
      "eval_samples_per_second": 37.102,
      "eval_steps_per_second": 0.581,
      "step": 96
    }
  ],
  "logging_steps": 500,
  "max_steps": 192,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 471390394560.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9950900377064807,
    "learning_rate": 0.00039439266395056036,
    "num_train_epochs": 4,
    "temperature": 27
  }
}