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

README.md

@@ -57,6 +57,39 @@ model-index:
       name: gen_len
       verified: true
       verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWZhOGMwMDJjNGU2MzA2YzI1OWU1ZDY5N2NjZmM1YTA5NDg1MzUwNmU1YTBhNjQyNWYwYzA3OGNmODFjMmE2NSIsInZlcnNpb24iOjF9.Rc9u89zCdbFnjsnmq65l_JvCtUwOX_ZWapKJpTZ-rC8HxcUVfi2Ash2QfvvvxHH_YWhwklxxdnNa0HCm46qLAA
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: billsum
+      type: billsum
+      config: default
+      split: test
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 41.3645
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 16.144
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 24.2981
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 35.3234
+      verified: true
+    - name: loss
+      type: loss
+      value: 1.282260775566101
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 291.8158
+      verified: true
 ---
 
 # long-t5-tglobal-xl + BookSum