Update eval_utils.py

eval_utils.py

@@ -238,7 +238,9 @@ def evaluate_pcr(gold_data, pred_data):
 
         print(f"Micro-F1@{k} on IL-PCR test set:", f1)
 
-    return f1_scores
+    max_f1 = max(f1)
+    index_max = f1.index(max_f1) + 1
+    return f"{max_f1:.2f}@{index_max}"
 
 
 def evaluate_summ(gold_data, pred_data):
@@ -478,7 +480,6 @@ 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 = {