Add evaluation results on the default config of xsum

#7
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +36 -0
README.md CHANGED
@@ -7,6 +7,42 @@ datasets:
7
  - cnn_dailymail
8
  - xsum
9
  thumbnail: https://huggingface.co/front/thumbnails/distilbart_medium.png
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  ### Usage
 
7
  - cnn_dailymail
8
  - xsum
9
  thumbnail: https://huggingface.co/front/thumbnails/distilbart_medium.png
10
+ model-index:
11
+ - name: sshleifer/distilbart-cnn-12-6
12
+ results:
13
+ - task:
14
+ type: summarization
15
+ name: Summarization
16
+ dataset:
17
+ name: xsum
18
+ type: xsum
19
+ config: default
20
+ split: test
21
+ metrics:
22
+ - name: ROUGE-1
23
+ type: rouge
24
+ value: 21.0357
25
+ verified: true
26
+ - name: ROUGE-2
27
+ type: rouge
28
+ value: 3.8995
29
+ verified: true
30
+ - name: ROUGE-L
31
+ type: rouge
32
+ value: 13.7879
33
+ verified: true
34
+ - name: ROUGE-LSUM
35
+ type: rouge
36
+ value: 16.9128
37
+ verified: true
38
+ - name: loss
39
+ type: loss
40
+ value: 3.8684895038604736
41
+ verified: true
42
+ - name: gen_len
43
+ type: gen_len
44
+ value: 68.5219
45
+ verified: true
46
  ---
47
 
48
  ### Usage