Update README.md

README.md

@@ -63,6 +63,7 @@ This model was trained for 1000 steps (1.2 epochs) with the model being evaluate
 We used the [qlora](https://github.com/artidoro/qlora) package from artidoro.
 We trained with the following hyperparameters:
 
+```
 Per device evaluation batch size: 16
 Per device train batch size: 8
 LoRA (lora_r): 64
@@ -81,6 +82,7 @@ Adam beta2: 0.999
 Maximum gradient norm: 0.3
 LoRA dropout: 0.05
 Weight decay: 0.0
+```
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/UWiE7z5tG8t_vdSFrb5WC.png)