{
  "best_metric": 0.8268348623853211,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-527",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1581,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.00021999157114248083,
      "loss": 1.5849,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8268348623853211,
      "eval_loss": 1.4141968488693237,
      "eval_runtime": 6.2667,
      "eval_samples_per_second": 139.148,
      "eval_steps_per_second": 1.117,
      "step": 527
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00019249262474967072,
      "loss": 0.7139,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8188073394495413,
      "eval_loss": 1.6580967903137207,
      "eval_runtime": 6.7027,
      "eval_samples_per_second": 130.096,
      "eval_steps_per_second": 1.044,
      "step": 1054
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00016499367835686062,
      "loss": 0.505,
      "step": 1581
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.819954128440367,
      "eval_loss": 1.6739211082458496,
      "eval_runtime": 6.6063,
      "eval_samples_per_second": 131.996,
      "eval_steps_per_second": 1.06,
      "step": 1581
    }
  ],
  "logging_steps": 500,
  "max_steps": 4743,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 24238892698680.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.27850940508457317,
    "learning_rate": 0.00024749051753529094,
    "num_train_epochs": 9,
    "temperature": 14
  }
}