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

#2
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +33 -0
README.md CHANGED
@@ -39,6 +39,39 @@ model-index:
39
  type: gen_len
40
  value: 19.7028
41
  verified: true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  dataset:
43
  type:
44
  xsum: null
 
39
  type: gen_len
40
  value: 19.7028
41
  verified: true
42
+ - task:
43
+ type: summarization
44
+ name: Summarization
45
+ dataset:
46
+ name: xsum
47
+ type: xsum
48
+ config: default
49
+ split: validation
50
+ metrics:
51
+ - name: ROUGE-1
52
+ type: rouge
53
+ value: 38.7415
54
+ verified: true
55
+ - name: ROUGE-2
56
+ type: rouge
57
+ value: 17.8295
58
+ verified: true
59
+ - name: ROUGE-L
60
+ type: rouge
61
+ value: 32.2861
62
+ verified: true
63
+ - name: ROUGE-LSUM
64
+ type: rouge
65
+ value: 32.2763
66
+ verified: true
67
+ - name: loss
68
+ type: loss
69
+ value: 1.8132821321487427
70
+ verified: true
71
+ - name: gen_len
72
+ type: gen_len
73
+ value: 19.7116
74
+ verified: true
75
  dataset:
76
  type:
77
  xsum: null