Update eval_utils.py

eval_utils.py

@@ -478,6 +478,7 @@ def get_evaluation_scores(gold_data, submission_data):
             if isinstance(result, str):
                 evaluation_results[task] = result
             else:
+                print(task, result)
                 evaluation_results[task] = f"{result:.2f}"
 
     blank_scores = {