swap optimizer.step and scheduler.step

examples/lm_finetuning/simple_lm_finetuning.py

@@ -602,8 +602,8 @@ def main():
                 nb_tr_examples += input_ids.size(0)
                 nb_tr_steps += 1
                 if (step + 1) % args.gradient_accumulation_steps == 0:
-                    scheduler.step()  # Update learning rate schedule
                     optimizer.step()
+                    scheduler.step()  # Update learning rate schedule
                     optimizer.zero_grad()
                     global_step += 1