diff --git a/run_classifier.py b/run_classifier.py
index 41c7459bd3..54b7d5a26c 100644
--- a/run_classifier.py
+++ b/run_classifier.py
@@ -520,7 +520,7 @@ def main():
             for step, batch in enumerate(tqdm(train_dataloader, desc="Iteration")):
                 batch = tuple(t.to(device) for t in batch)
                 input_ids, input_mask, segment_ids, label_ids = batch
-                loss = model(input_ids, segment_ids, input_mask, label_ids)
+                loss, _ = model(input_ids, segment_ids, input_mask, label_ids)
                 if n_gpu > 1:
                     loss = loss.mean() # mean() to average on multi-gpu.
                 if args.gradient_accumulation_steps > 1: