Add evaluation results on the default config of xsum (#3)

- Add evaluation results on the default config of xsum (f19ba2c12e9367e189fe922b45b47c2e348ff901)


Co-authored-by: Evaluation Bot <[email protected]>

README.md

@@ -250,6 +250,39 @@ model-index:
       type: gen_len
       value: 19.1111
       verified: true
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: xsum
+      type: xsum
+      config: default
+      split: test
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 25.2061
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 4.7048
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 17.8593
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 18.0798
+      verified: true
+    - name: loss
+      type: loss
+      value: 3.003053665161133
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 27.4815
+      verified: true
 ---
   
 # README - long-t5-tglobal-base-16384-booksum-V11-big_patent-V2