Update app.py

app.py

@@ -70,6 +70,7 @@ eval_dataframe_test = get_dataframe_from_results(eval_results=eval_results, spli
 # Gold answers
 gold_results = {}
 gold_dataset = load_dataset(INTERNAL_DATA_DATASET, "test", token=TOKEN, trust_remote_code=True)
+print(gold_dataset["test"])
 #gold_results = {"test": {row["cqs"]: row for row in gold_dataset["test"]}}
 
 
@@ -150,13 +151,15 @@ def add_new_eval(
     num_questions = 0
     task_ids = []
 
-    with open(f"scored/{organisation}_{model}.jsonl", "w") as scored_file: 
+    with open(f"scored/{organisation}_{model}.jsonl", "w") as scored_file: # I am not sure where this is being saved
         with open(file_path, 'r') as f:
             data = json.load(f)
             for ix, line in data.items():
-                return format_error(os.getcwd())
+                #return format_error(line['cqs'])
 
                 # TODO: look at each question, compare it to the references, output a label between 0 and 1
+
+                
                 
                 #try:
                 #    task = json.loads(line)