Add evaluation results on the default config and test split of xsum

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

@AkankshaK

, using the predictions stored [here](https://huggingface.co/datasets/autoevaluate/autoeval-eval-xsum-default-604b3d-2333173628).\
Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=xsum).\
Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/model-evaluator?dataset=xsum).

README.md

@@ -49,23 +49,23 @@ model-index:
     metrics:
     - name: ROUGE-1
       type: rouge
-      value: 46.8623
+      value: 46.861
       verified: true
     - name: ROUGE-2
       type: rouge
-      value: 24.4533
+      value: 24.4341
       verified: true
     - name: ROUGE-L
       type: rouge
-      value: 39.0548
+      value: 39.0618
       verified: true
     - name: ROUGE-LSUM
       type: rouge
-      value: 39.0994
+      value: 39.0985
       verified: true
     - name: loss
       type: loss
-      value: 1.5717021226882935
+      value: 1.5713257789611816
       verified: true
     - name: gen_len
       type: gen_len