update model card README.md

README.md

@@ -1,6 +1,9 @@
 ---
+base_model: ./clip-roberta
 tags:
 - generated_from_trainer
+datasets:
+- MP
 model-index:
 - name: clip-roberta-finetuned
   results: []
@@ -11,7 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # clip-roberta-finetuned
 
-This model was trained from scratch on the None dataset.
+This model is a fine-tuned version of [./clip-roberta](https://huggingface.co/./clip-roberta) on the MP dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6548
 
 ## Model description