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

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
@@ -49,29 +49,29 @@ model-index:
       config: default
       split: test
     metrics:
-    - name: ROUGE-1
-      type: rouge
+    - type: rouge
       value: 45.4525
+      name: ROUGE-1
       verified: true
-    - name: ROUGE-2
-      type: rouge
+    - type: rouge
       value: 22.3455
+      name: ROUGE-2
       verified: true
-    - name: ROUGE-L
-      type: rouge
+    - type: rouge
       value: 37.2302
+      name: ROUGE-L
       verified: true
-    - name: ROUGE-LSUM
-      type: rouge
+    - type: rouge
       value: 37.2323
+      name: ROUGE-LSUM
       verified: true
-    - name: loss
-      type: loss
+    - type: loss
       value: 2.3128726482391357
+      name: loss
       verified: true
-    - name: gen_len
-      type: gen_len
+    - type: gen_len
       value: 25.5435
+      name: gen_len
       verified: true
   - task:
       type: summarization
@@ -82,29 +82,29 @@ 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
@@ -115,30 +115,69 @@ 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
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: gigaword
+      type: gigaword
+      config: default
+      split: test
+    metrics:
+    - type: rouge
+      value: 16.579
+      name: ROUGE-1
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDFkOTg5ZTM4MDk3NGY4NTcxYzgyY2IxMzlkYmQ0OGUxNzM2YzBhMTI3YjZhMjAzMzZjM2FlZTJmOGM0NmNhMCIsInZlcnNpb24iOjF9.v29vzy3WA75dWDALKoo_pnByEd1kJUQb1TICtczTMvpFmmZBUj1JMbEAX9DMwQa8gq30hbIAvnXa7B0w33oKDQ
+    - type: rouge
+      value: 3.7036
+      name: ROUGE-2
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjMxYjM2MGUwZTI4OGJiZTMzMzY2OWNhNGIyM2NkOTk5ODI3OGRhZGRmMjIyZGNkMzg2MTI3OTg0NjgzMWRkNCIsInZlcnNpb24iOjF9.QWCiactfiS4V_rdnjpt3MJUciVpT7VlMRzGmFJ2PxioadewS2kApbYqu6CCilqC9hfVfsLg-VxrH-Os16Xp2Cg
+    - type: rouge
+      value: 14.3642
+      name: ROUGE-L
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjJjNDgxOTYwOGVmMWYxN2U5ZmM3MDg4NmYwMDllMjgzNjI2OTUxZDQyMzQ5NmY5ZWIwMjlkODdhZDcyNjIzMCIsInZlcnNpb24iOjF9.HbWvD3wc7PRAyT87I-5do9GU0cCXQuEIBDAVSDdGEKXfY-LQ_HBI87vl46z7okCPB7xqAQ-jBsLFmjekw-DSAA
+    - type: rouge
+      value: 14.3846
+      name: ROUGE-LSUM
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzBmNjNhZmMyNDY0N2Y4OTJmYTk0NWEwYjJjZDJiODMzMmUwNzhmMjVlYzkxMTg1YWYyZThlODY4MjE4NTAwYSIsInZlcnNpb24iOjF9.EZkXXT058YsPzxr-_k-asvYgBaf5IjJyuUzn_IrMEvqW6khWxq8MnnWeGkVPqhVq7hunVvrEYGo2N5ZJbCYOCQ
+    - type: loss
+      value: 6.708169460296631
+      name: loss
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGM3NmJjNmE4MWM3MGFjM2YzMDRjNGY1MzhjYWI0ZWVhNDQ2ZDA3ODVhZTVhZjRjZjFmMDMzNjZjMDRmMmQxNyIsInZlcnNpb24iOjF9.0IiFBEZWGIkz6FUNbxFwDsPivj0Vdzd0txS_5u0zraLxiML-rnitSWOip-WYbNRO9Gmllu3nRzeKBFFjkOj3DQ
+    - type: gen_len
+      value: 23.694
+      name: gen_len
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTc2MzlmNjE5ZmVkYTVmZGM5NzFhNDNkODcwOGUyNTFkOTkyOTNmMDNlNjU0YTlmYWMyNzljMDFhZTQzZmZiNSIsInZlcnNpb24iOjF9.MbmvTN8XJuMVhd4JJQdKpnijOKaS2OA2_cjO53777newl0EOHJtTF0CMS3sOjIVt7lrJUEr2JcfY7n8BPxDaAg
 ---
 ### Bart model finetuned on xsum