Update eval.py

eval.py

@@ -40,9 +40,9 @@ def statistics(commonsense_statistic):
 def eval_score(validation_or_test: str, file_path: str, TOKEN):
 
     if validation_or_test == 'validation':
-        query_data_list  = load_dataset('osunlp/TravelBenchEval','validation',token=TOKEN)['validation']
+        query_data_list  = load_dataset('osunlp/TravelPlannerEval','validation',token=TOKEN)['validation']
     elif validation_or_test == 'test':
-        query_data_list  = load_dataset('osunlp/TravelBenchEval','test',token=TOKEN)['test']
+        query_data_list  = load_dataset('osunlp/TravelPlannerEval','test',token=TOKEN)['test']
 
     query_data_list = [x for x in query_data_list]
     hardConstraint_statistic= {level:{day:[] for day in [3,5,7]} for level in ['easy','medium','hard']}