Update eval_utils.py

eval_utils.py

@@ -60,11 +60,12 @@ def evaluate_cjpe(gold_data, pred_data):
 
     f1 = f1_score(gold_labels, pred_labels, average="macro")
     prediction_result = {"cjpe-eval": f1}
-
+    print("Macro-F1 on ILDC test:", prediction_result)
+    
     R = []
     B = []
     rl_evaluator = rouge.Rouge(metrics=['rouge-l'], max_n=2, limit_length=False, apply_avg=True)
-    for x in range(1, 6):
+    for x in tqdm(range(1, 6), desc="cjpe explanation expert-wise"):
         gold_explanations = []
         pred_explanations = []
         for k,v in gold_data['explanation'].items():
@@ -84,7 +85,6 @@ def evaluate_cjpe(gold_data, pred_data):
             "bleu": bleu_score,
         }
     }
-    print("Macro-F1 on ILDC test:", prediction_result)
     print("Explanability for ILDC Expert:", explanation_result)
     return {**prediction_result, **explanation_result}