Test

src/populate.py

@@ -11,6 +11,7 @@ from src.leaderboard.read_evals import get_raw_eval_results
 def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame:
     """Creates a dataframe from all the individual experiment results"""
     raw_data = get_raw_eval_results(results_path, requests_path)
+    print(f"Found {len(raw_data)} raw eval results")
     all_data_json = [v.to_dict() for v in raw_data]
 
     df = pd.DataFrame.from_records(all_data_json)