update model card README.md

README.md

@@ -1,6 +1,8 @@
 ---
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: bart-base-cantonese-v4
   results: []
@@ -11,7 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart-base-cantonese-v4
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [notebooks/cantonese/bart-base-chinese](https://huggingface.co/notebooks/cantonese/bart-base-chinese) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9313
+- Accuracy: 0.8312
 
 ## Model description