update model card README.md

README.md

@@ -2,6 +2,9 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- f1
 model-index:
 - name: bart-base-coqa
   results: []
@@ -13,6 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 # bart-base-coqa
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7936
+- Accuracy: 0.0926
+- F1: 0.0597
 
 ## Model description