diff --git a/README.md b/README.md
index 4e57de58..9751c720 100644
--- a/README.md
+++ b/README.md
@@ -393,8 +393,8 @@ for batch in train_data:
     loss = model(batch)
     loss.backward()
     torch.nn.utils.clip_grad_norm_(model.parameters(), max_grad_norm)  # Gradient clipping is not in AdamW anymore (so you can use amp without issue)
-    scheduler.step()
     optimizer.step()
+    scheduler.step()
     optimizer.zero_grad()
 ```