Update README.md

README.md

@@ -12,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # biolinkbert-mednli
 
-This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-large](https://huggingface.co/michiyasunaga/BioLinkBERT-large) on an unknown dataset.
+This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-large](https://huggingface.co/michiyasunaga/BioLinkBERT-large) on [MedNLI](https://physionet.org/content/mednli/1.0.0/).
 It achieves the following results on the evaluation set:
 - eval_loss: 0.8807
 - eval_accuracy: 0.8608
@@ -21,6 +21,16 @@ It achieves the following results on the evaluation set:
 - eval_steps_per_second: 10.809
 - step: 0
 
+The accuracy for the test set is
+```
+  eval_accuracy           =     0.8608
+  eval_loss               =     0.8807
+  eval_runtime            = 0:00:16.46
+  eval_samples            =       1395
+  eval_samples_per_second =     86.354
+  eval_steps_per_second   =     10.809
+```
+
 ## Model description
 
 More information needed