Add evaluation results on the mrpc config and validation split of glue

Beep boop, I am a bot from Hugging Face's automatic model evaluator 👋!\
Your model has been evaluated on the mrpc config and validation split of the [glue](https://huggingface.co/datasets/glue) dataset by

@lewtun
, using the predictions stored [here](https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-31466167-6d47-4d63-9ebd-59fe66b62d96-5553).\
Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=glue).\
Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/model-evaluator?dataset=glue).

README.md

@@ -11,8 +11,8 @@ model-index:
 - name: natural-language-inference
   results:
   - task:
-      name: Text Classification
       type: text-classification
+      name: Text Classification
     dataset:
       name: glue
       type: glue
@@ -20,12 +20,12 @@ model-index:
       split: train
       args: mrpc
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.8284313725490197
-    - name: F1
-      type: f1
+      name: Accuracy
+    - type: f1
       value: 0.8821548821548822
+      name: F1
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You