Update docs/source/getting_started.md

Co-authored-by: Svetlana Karslioglu <[email protected]>

Author: AlannaBurke

docs/source/getting_started.md

@@ -198,7 +198,7 @@ python -m apps.grpo.main --config apps/grpo/qwen3_1_7b.yaml
 - **TorchStore** handles weight synchronization from training to inference
 
 **Expected Output:**
-```
+```bash
 Initializing GRPO training...
 Loading policy model on GPU 0...
 Loading reference model on GPU 1...