Debug

src/leaderboard/read_evals.py

@@ -200,6 +200,7 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
         try:
             v.to_dict(tasks) # we test if the dict version is complete
             results.append(v)
-        except KeyError:  # not all eval values present
+        except KeyError as e:  # not all eval values present
+            print(e)
             continue
     return results