Add evaluation results on the 3.0.0 config and test split of cnn_dailymail

#6
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +39 -0
README.md CHANGED
@@ -88,6 +88,45 @@ model-index:
88
  name: gen_len
89
  verified: true
90
  verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWRlMjM5MzAyMjEzYzdkODFmNDk4NDg5NWM4NWIxMTU4YWMxNzZjMGFjOWJiMDdkMjQyMTY0ZGFmYzA2OTA0YiIsInZlcnNpb24iOjF9.IFiGJEsyD7Uhj8bo9SsAgibk9qCXZH6IWaLKULLxBz5N8WXF2vc2Mfg5OThEzdrydPhJInRgp0jd8m-kF5nNCA
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  ---
92
 
93
  # T5-large Summarization Model Trained on the combined XSUM-CNN Daily Mail Dataset
 
88
  name: gen_len
89
  verified: true
90
  verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWRlMjM5MzAyMjEzYzdkODFmNDk4NDg5NWM4NWIxMTU4YWMxNzZjMGFjOWJiMDdkMjQyMTY0ZGFmYzA2OTA0YiIsInZlcnNpb24iOjF9.IFiGJEsyD7Uhj8bo9SsAgibk9qCXZH6IWaLKULLxBz5N8WXF2vc2Mfg5OThEzdrydPhJInRgp0jd8m-kF5nNCA
91
+ - task:
92
+ type: summarization
93
+ name: Summarization
94
+ dataset:
95
+ name: cnn_dailymail
96
+ type: cnn_dailymail
97
+ config: 3.0.0
98
+ split: test
99
+ metrics:
100
+ - type: rouge
101
+ value: 20.0241
102
+ name: ROUGE-1
103
+ verified: true
104
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzlmYTdhN2E0YjIxOTkwMTJkZTc3YTI4Yjg2ZWRiNWI2MDA5MTQxY2JhNWJhMWEzNmI0YTg4MmJmYWJhYTJiZiIsInZlcnNpb24iOjF9.fAbo4oF2nXvniDJ0TZXmjwlkC2b-B8JSVkWhOq3Y8QK2H9uJH4Ia9_O2E_OSkRlgY4CaJgGI5C1l_zkD-43tBA
105
+ - type: rouge
106
+ value: 5.0689
107
+ name: ROUGE-2
108
+ verified: true
109
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjY5NGQ4OTkzZWQ2ZGY1OWRmYzMzZGJjZjI0NzYwNDAzYjcxYjliZGE3NmE1MmNkYjEyZjZiZmExMGUxNDNmYyIsInZlcnNpb24iOjF9.jCuwA8JXxg1X9g1BAeuKXKCX4zo5GsYIo4OMYo_H_uBSjO5E2kmGQzZXJXr-XhLskQv2Gx1xsj5XhWkeeSDQDA
110
+ - type: rouge
111
+ value: 14.4763
112
+ name: ROUGE-L
113
+ verified: true
114
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmU0ZjhlZTVlM2UxOWM3MGZjOGFlMGJkZDllMmM5YjJjZWQ5YmNlYTQ4ZGE3ZGFmNTgyNTU4MjBiMmRkMzllYSIsInZlcnNpb24iOjF9.wTQeJbnOJRBSsmILMVxJielfyOZllcIH9IgliTfCMdHFMIbvFdzxqDP95QCZkVNjcwylv1ozPNfZUM65tCJBBw
115
+ - type: rouge
116
+ value: 17.681
117
+ name: ROUGE-LSUM
118
+ verified: true
119
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWJiZTdjZjk3OTk1ZDYyNTEzOTRkMmMzNjgyNWE3MThmY2I4YTU5ZDI2MmU5ZGQxOTkxNTQ5ZDQ4NDM1NTgxOSIsInZlcnNpb24iOjF9.TURqZk7PRJzo9EZ7UeOYUtZNz5hf5eQlpeGK_o3Ewa0Rie0g85Xzn9Lu2OSwAYAI_bD0W1fefN8mzv5XKnG5Aw
120
+ - type: loss
121
+ value: 2.863785743713379
122
+ name: loss
123
+ verified: true
124
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWRiZmFhOTY0MTE3NTE4MDcyZWUyMjM3MWI4NjIwY2I2YTI0YTQ1NzA3ODMzY2FiZDcwMjdjMWViNjk3NGEzNiIsInZlcnNpb24iOjF9.kygh8aIGin_1ucBoEMehNArgK0A1zwMK2Kd0JaAkFSnc3ZXvrYAdrSmxFfoGAlqYJT6bNL9UQievBlgyxt-aDg
125
+ - type: gen_len
126
+ value: 18.6581
127
+ name: gen_len
128
+ verified: true
129
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTNkNTE4M2E4ZDI5NGZmN2I3YzM3ZTJkYmNjODdmMDk1ZjA4YzlmOGE1ODQxM2M4NjRiNTJjYzI0OTc2MmUxZCIsInZlcnNpb24iOjF9.6uPTg-C8HTQKq6Ppn0iwTWDz7P86_1cc5n6_3ct605etp4li79phSHS7TGpLKWeVSQKGpiSVOzUQhwslqyrVCg
130
  ---
131
 
132
  # T5-large Summarization Model Trained on the combined XSUM-CNN Daily Mail Dataset