Code Changes - Evaluation Function

app.py

@@ -102,7 +102,7 @@ def run_evaluation(
                     docs = []
                 else:
                     query, ans, docs = processdata(instance, noise_rate, passage_num, dataset, correct_rate)
-                    print(f"Results: \n*********query: {query}, \n*********Answer: {ans}, \n*********docs: {docs}\n*********\n")
+                    # print(f"Results: \n*********query: {query}, \n*********Answer: {ans}, \n*********docs: {docs}\n*********\n")
                 
                 label, prediction, factlabel = predict(query, ans, docs, model, system, instruction, temperature, dataset)
                 print("f******** Label: {label}\n******** Prediction: {prediction}\n******** factlabel: {factlabel}\n ******** \n")
@@ -158,10 +158,16 @@ def run_evaluation(
         })
 
     # Save results
-    score_file = f"{output_file[:-5]}_result.json"
-    with open(score_file, 'w') as f:
-        json.dump(scores, f, ensure_ascii=False, indent=4)
-
+    try:
+        score_file = f"{output_file[:-5]}_result.json"
+        with open(score_file, 'w') as f:
+            json.dump(scores, f, ensure_ascii=False, indent=4)
+    except Exception as e:
+        print("Error saving scores:", e)
+
+    # with open(score_file, 'w') as f:
+    #     json.dump(scores, f, ensure_ascii=False, indent=4)
+    print(f"Scores ares {scores}")
     return scores
 
 def evaluate_model_ui(modelname, dataset, api_key, url, temperature, noise_rate, correct_rate, passage_num, factchecking):