Add evaluation results on the samsum config and validation split of samsum

README.md

@@ -41,6 +41,39 @@ model-index:
       type: gen_len
       value: 78.5866
       verified: true
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: samsum
+      type: samsum
+      config: samsum
+      split: validation
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 31.5121
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 11.0254
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 23.8633
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 29.5362
+      verified: true
+    - name: loss
+      type: loss
+      value: 2.1685919761657715
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 66.1271
+      verified: true
 ---
 # BART (large-sized model), fine-tuned on CNN Daily Mail