push fix to training

examples/run_glue.py

@@ -154,8 +154,8 @@ def train(args, train_dataset, model, tokenizer):
 
             tr_loss += loss.item()
             if (step + 1) % args.gradient_accumulation_steps == 0:
-                scheduler.step()  # Update learning rate schedule
                 optimizer.step()
+                scheduler.step()  # Update learning rate schedule
                 model.zero_grad()
                 global_step += 1