{
  "best_metric": 0.7270058708414873,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-27/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": 3.0442044734954834,
      "learning_rate": 0.00047720243978875736,
      "loss": 0.5494,
      "step": 48
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7270058708414873,
      "eval_f1": 0.7787470261697065,
      "eval_loss": 0.4914495050907135,
      "eval_precision": 0.6546666666666666,
      "eval_recall": 0.9608610567514677,
      "eval_runtime": 28.018,
      "eval_samples_per_second": 36.476,
      "eval_steps_per_second": 0.571,
      "step": 48
    }
  ],
  "logging_steps": 500,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 235695197280.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.8647030881639047,
    "learning_rate": 0.0005965030497359467,
    "num_train_epochs": 5,
    "temperature": 29
  }
}