Update README.md

README.md

@@ -50,18 +50,11 @@ training_args = TrainingArguments(
 ```
 
 ### Eval results
-The model was evaluated using the test sets for MultiNLI and ANLI and the dev set for Fever-NLI
-dataset | accuracy
--------|------
-mnli-m | 0.903
-mnli-mm | 0.903
-fever-nli | 0.777
-anli-all | 0.579
-anli-r3 | 0.495
+The model was evaluated using the test sets for MultiNLI and ANLI and the dev set for Fever-NLI. The metric used is accuracy.
 
-metric   |  | precision | recall | accuracy (not balanced) 
--------|---------|----------|---------|----------
-accuracy  | 0.773 | 0.772 | 0.771 | 0.771
+mnli-m | mnli-mm | fever-nli | anli-all | anli-r3
+---------|----------|---------|----------|----------
+0.903 | 0.903 | 0.777 | 0.579 | 0.495
 
 
 ## Limitations and bias