test

app.py

@@ -203,4 +203,4 @@ with demo:
 scheduler = BackgroundScheduler()
 scheduler.add_job(restart_space, "interval", seconds=1800)
 scheduler.start()
-demo.queue(default_concurrency_limit=30).launch()
+demo.queue(default_concurrency_limit=40).launch()

src/populate.py

@@ -11,7 +11,8 @@ 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(raw_data)
+    assert 0
     all_data_json = [v.to_dict() for v in raw_data]
 
     df = pd.DataFrame.from_records(all_data_json)