Fix: #3833 Feedback about Multi GPU training with DDP

Author: samithcsachi

beginner_source/ddp_series_multigpu.rst

@@ -202,6 +202,8 @@ Running the distributed training job
 Here's what the code looks like:
 
 .. code-block:: python
+
+   
    def main(rank, world_size, total_epochs, save_every):
       ddp_setup(rank, world_size)
       dataset, model, optimizer = load_train_objs()