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

README.md

@@ -1,9 +1,9 @@
 ---
-tags:
-- summarization
 language:
 - en
 license: mit
+tags:
+- summarization
 model-index:
 - name: facebook/bart-large-xsum
   results:
@@ -16,29 +16,29 @@ model-index:
       config: 3.0.0
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 25.2697
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+    - type: rouge
       value: 7.6638
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+    - type: rouge
       value: 17.1808
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+    - type: rouge
       value: 21.7933
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+    - type: loss
       value: 3.5042972564697266
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+    - type: gen_len
       value: 27.4462
+      name: gen_len
       verified: true
   - task:
       type: summarization
@@ -49,30 +49,36 @@ model-index:
       config: default
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
-      value: 45.4525
-      verified: true
-    - name: ROUGE-2
-      type: rouge
-      value: 22.3455
-      verified: true
-    - name: ROUGE-L
-      type: rouge
-      value: 37.2302
-      verified: true
-    - name: ROUGE-LSUM
-      type: rouge
-      value: 37.2323
-      verified: true
-    - name: loss
-      type: loss
-      value: 2.3128726482391357
-      verified: true
-    - name: gen_len
-      type: gen_len
+    - type: rouge
+      value: 45.4419
+      name: ROUGE-1
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzkzZTM0ZTQ3OTJhODgxOGJhNWE0Y2QxMjcwMjBiODdlMzY3Yjk1MjQ1MDJlODQwZjNlZWUyMTEwNmYyYjUzYiIsInZlcnNpb24iOjF9.3_JITjNVx36poltYC02qpeuMiAyYu2AOrfMpCACYdX2_FTtSxxWeYkUJHEbBnuJQKgERHmJncLcQxbh4IlvXBA
+    - type: rouge
+      value: 22.3723
+      name: ROUGE-2
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDQzZTkxMWM4ZDgyOTcyYmI1MDgyNTk1YmExNTJmNDAxYjViNjlmZjUzNjQ3ZDQwNzQ5ZWQ0ZDU1YTFjYTdlYiIsInZlcnNpb24iOjF9.sDIZfKrHyHDcuYxKNYcvrl-1eMrnwMtm8cA-xDxNP4hX7eEhNoQSAo_CLiPibibcHNMOjZX9fPCMULiGb0qnBw
+    - type: rouge
+      value: 37.2229
+      name: ROUGE-L
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWM2MThmY2Y1YmY4OTEwYTZjZjRiNTYxMTY4NDVmMzBhOGM3YTlkZmExMDZmOGU0ZmM1MjMwM2RjOWU1YWQxNyIsInZlcnNpb24iOjF9.TNMvdtMB-5DHUth3HeMc9IilhlciZgPI8AW8RLWl5fWTDko8X0JRk-gTMW6b6cNcRUe2lmfZ9I_ZSd-ZvnjEBA
+    - type: rouge
+      value: 37.2239
+      name: ROUGE-LSUM
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzZlMGI2NmRmMTEwMWFhNzAxOTRlMWQyNzA0YjI1ODE3ZjVjYmE1ODMzZTE1M2Y3MTk2YTcxZDYwN2U2NGI4NiIsInZlcnNpb24iOjF9.tcsUnGTDhbrOi1ZNusrI8Do4kt8BuNLD91fhbJwOsr9EvP6NlAAWnfoG1iBSNYKByMcC9Y31lwZlUOUBvnUdDQ
+    - type: loss
+      value: 2.3128323554992676
+      name: loss
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzQ3ODBjNWY2ODdhZTAwODUxY2ViMjBmNDY3N2EwMTUzYzdjOGJlZjZlMTI0ZjhkM2I0MGRjNjM5OWNhZDU3NSIsInZlcnNpb24iOjF9.IleOf5Dq60z64kqp6w5dyc6azb1egIARnnKch-x-hpKdQUdTMyPmUO34SpWzuhMt9bJQXRG5qNxb0mpr2-ZMCg
+    - type: gen_len
       value: 25.5435
+      name: gen_len
       verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTE3ODlkZDhhMTEwNTlhNzVjMWMxMGQyZDc0OTc0NWY0MDBlMzUzNGI3MGQwNmJmNzQ3NTQ5MjhhNDhiYTM5YSIsInZlcnNpb24iOjF9.e7nHzg3OH3zkWiCj3iZVAAQG6Zy0E16_MJzBEEyGTlSVuPGMziNfcjRvLD6WeY_6lXUonEwc9lur0X-qUvB7Aw
   - task:
       type: summarization
       name: Summarization
@@ -82,29 +88,29 @@ model-index:
       config: samsum
       split: train
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 24.7852
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+    - type: rouge
       value: 5.2533
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+    - type: rouge
       value: 18.6792
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+    - type: rouge
       value: 20.629
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+    - type: loss
       value: 3.746837854385376
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+    - type: gen_len
       value: 23.1206
+      name: gen_len
       verified: true
   - task:
       type: summarization
@@ -115,29 +121,29 @@ model-index:
       config: samsum
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 24.9158
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+    - type: rouge
       value: 5.5837
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+    - type: rouge
       value: 18.8935
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+    - type: rouge
       value: 20.76
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+    - type: loss
       value: 3.775235891342163
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+    - type: gen_len
       value: 23.0928
+      name: gen_len
       verified: true
 ---
 ### Bart model finetuned on xsum