revert

lm_eval/api/task.py

@@ -1186,7 +1186,9 @@ class ConfigurableTask(Task):
                             predictions=[result],
                             **self._metric_fn_kwargs[metric],
                         )
-                    except TypeError:  # needed for now in order to use a different interface between our own metrics and HF Evaluate metrics
+                    except (
+                        TypeError
+                    ):  # needed for now in order to use a different interface between our own metrics and HF Evaluate metrics
                         result_score = self._metric_fn_list[metric]([gold, result])
                     if isinstance(result_score, dict):
                         # TODO: this handles the case where HF evaluate returns a dict.