Update README.md

README.md

@@ -17,4 +17,11 @@ I trained this model to detect spam in german as there is no german labeled spam
 
 ## Intended use
 Identifying spam mail in any XLM-RoBERTa-supported language.
-Note that there was no thorough testing on it's intended use - only validation on the enron mail dataset.
+Note that there was no thorough testing on it's intended use - only validation on the enron mail dataset.
+
+## Evaluation
+
+Eval on test set of enron spam:
+
+- loss: 0.0315
+- accuracy: 0.996