Update evaluation.py

evaluation.py

@@ -102,7 +102,7 @@ def convert_adherence_to_numerical(adherence_score):
     else:
         return 0  # False becomes 0
         
-def retrieve_ground_truths(question, dataset):
+def retrieve_ground_truths(question, dataset,time_taken):
     """Retrieve the ground truth answer for a given question from the dataset."""
     for split_name, instances in dataset.items():
         for instance in instances:
@@ -145,7 +145,7 @@ def store_rmse(question, predicted_metrics, ground_truth_metrics):
 
 def calculate_metrics(question, q_dataset, response, docs, time_taken):
     data = load_query_dataset(q_dataset)
-    ground_truth_answer, ground_truth_metrics = retrieve_ground_truths(question, data)  # Store the ground truth answer
+    ground_truth_answer, ground_truth_metrics = retrieve_ground_truths(question, data,time_taken)  # Store the ground truth answer
 
     # Ensure ground_truth_answer is not empty before proceeding
     if ground_truth_answer is None: