{
  "best_metric": 0.7259174311926605,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-527",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 527,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 4.747544288635254,
      "learning_rate": 8.421921303617797e-06,
      "loss": 1.1824,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7259174311926605,
      "eval_loss": 1.0221459865570068,
      "eval_runtime": 2.6361,
      "eval_samples_per_second": 330.793,
      "eval_steps_per_second": 2.655,
      "step": 527
    }
  ],
  "logging_steps": 500,
  "max_steps": 3162,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8057768762220.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.8183970243354497,
    "learning_rate": 1.0106305564341356e-05,
    "num_train_epochs": 6,
    "temperature": 4
  }
}