{
  "best_metric": 0.6666666666666666,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-160",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 320,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.8257476687431335,
      "learning_rate": 9.75330205032834e-06,
      "loss": 0.152,
      "step": 160
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_f1": 0.0,
      "eval_loss": 0.12596820294857025,
      "eval_mcc": 0.0,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.8567,
      "eval_samples_per_second": 686.692,
      "eval_steps_per_second": 21.543,
      "step": 160
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.23037900030612946,
      "learning_rate": 0.0,
      "loss": 0.1247,
      "step": 320
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_f1": 0.0,
      "eval_loss": 0.1225561797618866,
      "eval_mcc": 0.0,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 1.8775,
      "eval_samples_per_second": 679.094,
      "eval_steps_per_second": 21.305,
      "step": 320
    }
  ],
  "logging_steps": 500,
  "max_steps": 320,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 583510875840.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.15677692354654504,
    "learning_rate": 1.950660410065668e-05,
    "num_train_epochs": 2,
    "temperature": 16
  }
}