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

README.md

@@ -422,6 +422,45 @@ model-index:
       name: gen_len
       verified: true
       verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDQxZmEwYmU5MGI1ZWE5NTIyMmM1MTVlMjVjNTg4MDQyMjJhNGE5NDJhNmZiN2Y4ZDc4ZmExNjBkMjQzMjQxMyIsInZlcnNpb24iOjF9.o3WblPY-iL1vT66xPwyyi1VMPhI53qs9GJ5HsHGbglOALwZT4n2-6IRxRNcL2lLj9qUehWUKkhruUyDM5-4RBg
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: xsum
+      type: xsum
+      config: default
+      split: test
+    metrics:
+    - type: rouge
+      value: 16.3186
+      name: ROUGE-1
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjNiYzkxNTc1M2ZiYzY4NmVhY2U4MGU0YWE1NzQ4YzQxNjM1ZThmOWU3ZjUwMWUxMWM1NTQyYzc0OWQ5MzQyZSIsInZlcnNpb24iOjF9.cDZzbzxrXaM4n-Fa-vBpUgq7ildtHg9hlO5p9pt58VYLGK3rsid3oUE2qsFH6Qk63j2cF4_hzgq93xoVlnR3Dg
+    - type: rouge
+      value: 3.0261
+      name: ROUGE-2
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjkzNzA0ODk3NWJjOGM2ZWFlY2MyZWM4NzZlYzZiMGQ2ODc0NzgzNDYzYmVlZjg2ZjBmNDMwOGViYTljYWQ2NSIsInZlcnNpb24iOjF9.ohBfAUhEktfITK6j_NusN5SOmF4XUHZWPNMpGrsGXRHTf1bUl6_UEQ0S3w58WQsgIuV3MkxWNRBU1oZAm3fbBQ
+    - type: rouge
+      value: 10.4045
+      name: ROUGE-L
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDM2ZDZhYzBiNGM3NDdhODlmNjJhMTNlZDE3ZTZmYjM1MWU5YmE0ODMyZGFhMmM0YmMwMzNiZWU4ZDAzMDFlNiIsInZlcnNpb24iOjF9.653PFaov_0t8g_fVyVxm8DBx7uV4646yK0rtxOxC7qsnRdljdThSOklw9tND5-44WdkzipzuLyVzq1qe-TbKBA
+    - type: rouge
+      value: 12.612
+      name: ROUGE-LSUM
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmY5YzU2ZjE2OWM0ZGQwZmVjZjQwZTQ0MDNkZmNiMTdhZjFkMDA5OGFhYWQ0Y2QwZDY0YWJlNWUxZGQ0YTUwZiIsInZlcnNpb24iOjF9.RXyu1jIj_gV26WCHSGHZufWXKFEexuRaLD4gkOvlBcaXJrFoE11tttB6mYzN6Tk8qx5cvV5L_ZIUfDmOqunkAA
+    - type: loss
+      value: 3.323798179626465
+      name: loss
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjU5ZWUxMjIwMWYwNDY1YzUwMzUxNGFiZWI3ZDVhZDFlYzJhNzk3MjA1OGExNTg0NjZlOGQyYzBiZjdhN2E2YSIsInZlcnNpb24iOjF9.vFxH1vHAACKE4XcgBhuoaV38yUZuYJuNm23V3nWVbF4FwyN79srV3Y9CqPGoOiIoUSQJ9fdKZXZub5j0GuUJAA
+    - type: gen_len
+      value: 149.7551
+      name: gen_len
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzg1ZjY5MTJkMTgzMjhiYzMxNjkyZjlmNmI2ZGU0YTRhZjU5NjQwOWE5MjczZDIxNGI1MGI4YzhhOGVkZDFkYSIsInZlcnNpb24iOjF9.S7W5-vqldJuqtC5MweC3iCK6uy-uTRe4kGqoApMl2Sn6w9sVHnY7u905yNLXzFLrLYMgjlct5LB7AAirHeEJBw
 ---
 # LED-Based Summarization Model: Condensing Long and Technical Information