swap optimizer.step and scheduler.step

examples/lm_finetuning/finetune_on_pregenerated.py

@@ -314,8 +314,8 @@ def main():
                 mean_loss = tr_loss * args.gradient_accumulation_steps / nb_tr_steps
                 pbar.set_postfix_str(f"Loss: {mean_loss:.5f}")
                 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