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

#24
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +33 -0
README.md CHANGED
@@ -43,6 +43,39 @@ model-index:
43
  type: gen_len
44
  value: 78.5866
45
  verified: true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  ---
47
  # BART (large-sized model), fine-tuned on CNN Daily Mail
48
 
 
43
  type: gen_len
44
  value: 78.5866
45
  verified: true
46
+ - task:
47
+ type: summarization
48
+ name: Summarization
49
+ dataset:
50
+ name: gigaword
51
+ type: gigaword
52
+ config: default
53
+ split: test
54
+ metrics:
55
+ - name: ROUGE-1
56
+ type: rouge
57
+ value: 16.4548
58
+ verified: true
59
+ - name: ROUGE-2
60
+ type: rouge
61
+ value: 5.2209
62
+ verified: true
63
+ - name: ROUGE-L
64
+ type: rouge
65
+ value: 14.0704
66
+ verified: true
67
+ - name: ROUGE-LSUM
68
+ type: rouge
69
+ value: 14.7993
70
+ verified: true
71
+ - name: loss
72
+ type: loss
73
+ value: 4.663515567779541
74
+ verified: true
75
+ - name: gen_len
76
+ type: gen_len
77
+ value: 63.7811
78
+ verified: true
79
  ---
80
  # BART (large-sized model), fine-tuned on CNN Daily Mail
81