Add evaluation results on the default config and validation 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 validation split of the [xsum](https://huggingface.co./datasets/xsum) dataset by

@morenolq

, using the predictions stored [here](https://huggingface.co./datasets/autoevaluate/autoeval-eval-xsum-default-d5c7a7-1507154810).\
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

@@ -39,6 +39,39 @@ model-index:
       type: gen_len
       value: 19.7028
       verified: true
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: xsum
+      type: xsum
+      config: default
+      split: validation
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 38.7415
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 17.8295
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 32.2861
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 32.2763
+      verified: true
+    - name: loss
+      type: loss
+      value: 1.8132821321487427
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 19.7116
+      verified: true
   dataset:
     type:
       xsum: null