diff --git a/examples/run_squad.py b/examples/run_squad.py
index 25e2c409..cc4eda30 100644
--- a/examples/run_squad.py
+++ b/examples/run_squad.py
@@ -157,8 +157,8 @@ 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