Add evaluation results on the default config of multi_news

#1
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +33 -0
README.md CHANGED
@@ -20,6 +20,39 @@ model-index:
20
  - name: Rouge1
21
  type: rouge
22
  value: 41.6136
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
20
  - name: Rouge1
21
  type: rouge
22
  value: 41.6136
23
+ - task:
24
+ type: summarization
25
+ name: Summarization
26
+ dataset:
27
+ name: multi_news
28
+ type: multi_news
29
+ config: default
30
+ split: test
31
+ metrics:
32
+ - name: ROUGE-1
33
+ type: rouge
34
+ value: 39.6512
35
+ verified: true
36
+ - name: ROUGE-2
37
+ type: rouge
38
+ value: 14.333
39
+ verified: true
40
+ - name: ROUGE-L
41
+ type: rouge
42
+ value: 21.5797
43
+ verified: true
44
+ - name: ROUGE-LSUM
45
+ type: rouge
46
+ value: 35.5793
47
+ verified: true
48
+ - name: loss
49
+ type: loss
50
+ value: 5.507579803466797
51
+ verified: true
52
+ - name: gen_len
53
+ type: gen_len
54
+ value: 132.1745
55
+ verified: true
56
  ---
57
 
58
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You