Update README.md

README.md

@@ -159,7 +159,7 @@ Each task had a specific CLS embedding, which is dropped 10% of the time to faci
 The number of examples per task was capped to 64. The model was trained for 20k steps with a batch size of 384, a peak learning rate of 2e-5.
 
 You can fine-tune this model to use it for multiple-choice or any classification task (e.g. NLI) like any debertav2 model. 
-This model has strong validation performance on many tasks (e.g. 70% on WNLI).
+This model has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI).
 
 The list of tasks is available in tasks.md