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

README.md

@@ -43,6 +43,39 @@ model-index:
       type: gen_len
       value: 78.5866
       verified: true
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: gigaword
+      type: gigaword
+      config: default
+      split: test
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 16.4548
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 5.2209
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 14.0704
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 14.7993
+      verified: true
+    - name: loss
+      type: loss
+      value: 4.663515567779541
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 63.7811
+      verified: true
 ---
 # BART (large-sized model), fine-tuned on CNN Daily Mail