Update app.py

app.py

@@ -49,7 +49,7 @@ def main():
            inputs =  tokenizer(query, text, return_tensors='tf')
            #outputs = qa_model(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'])
            outputs = qa_model(input_ids=inputs['input_ids']) 
-           loss = tf.math.reduce_mean(outputs.loss) 
+           loss = outputs.loss
            answer_start_index = int(tf.math.argmax(outputs.start_logits, axis=-1)[0])
            answer_end_index = int(tf.math.argmax(outputs.end_logits, axis=-1)[0])
            predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1]