update scripts

src/leaderboard/read_evals.py

@@ -66,6 +66,7 @@ class EvalResult:
         results = {}
         for task in utils.Tasks:
             task = task.value
+            print(task.value)
             if isinstance(task.metric, str):
                 accs = np.array([v.get(task.metric, None) for k, v in data["results"].items() if
                                  task.benchmark == k and isinstance(v, dict)])