Add evaluation results on the plain_text config and validation split of launch/gov_report (#7)

- Add evaluation results on the plain_text config and validation split of launch/gov_report (8f66b46acdcf026f1bbf1e826a57e07e1831e25a)


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

README.md

@@ -384,6 +384,39 @@ model-index:
       type: gen_len
       value: 71.6372
       verified: true
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: launch/gov_report
+      type: launch/gov_report
+      config: plain_text
+      split: validation
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 23.5925
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 5.6762
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 13.8108
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 20.2437
+      verified: true
+    - name: loss
+      type: loss
+      value: 2.6377077102661133
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 64.1807
+      verified: true
 ---
   
 # README - long-t5-tglobal-base-16384-booksum-V11-big_patent-V2