add

src/leaderboard/read_evals.py

@@ -175,7 +175,9 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
     eval_results = {}
     for model_result_filepath in model_result_filepaths:
         # Creation of result
+        print(f"Model result filepath: {model_result_filepath}")
         eval_result = EvalResult.init_from_json_file(model_result_filepath)
+        print(eval_result)
         eval_result.update_with_request_file(requests_path)
 
         # Store results of same eval together
@@ -184,6 +186,7 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
             eval_results[eval_name].results.update({k: v for k, v in eval_result.results.items() if v is not None})
         else:
             eval_results[eval_name] = eval_result
+    print(eval_results)
 
     results = []
     for v in eval_results.values():

src/populate.py

@@ -14,8 +14,6 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
     all_data_json = [v.to_dict() for v in raw_data]
 
     df = pd.DataFrame.from_records(all_data_json)
-    print(df.head())
-    print(df)
     df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
     df = df[cols].round(decimals=2)