Add evaluation results on the plain_text config and test split of launch/gov_report

#16
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +33 -0
README.md CHANGED
@@ -41,6 +41,39 @@ model-index:
41
  type: gen_len
42
  value: 78.5866
43
  verified: true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  ---
45
  # BART (large-sized model), fine-tuned on CNN Daily Mail
46
 
 
41
  type: gen_len
42
  value: 78.5866
43
  verified: true
44
+ - task:
45
+ type: summarization
46
+ name: Summarization
47
+ dataset:
48
+ name: launch/gov_report
49
+ type: launch/gov_report
50
+ config: plain_text
51
+ split: test
52
+ metrics:
53
+ - name: ROUGE-1
54
+ type: rouge
55
+ value: 27.2717
56
+ verified: true
57
+ - name: ROUGE-2
58
+ type: rouge
59
+ value: 11.3584
60
+ verified: true
61
+ - name: ROUGE-L
62
+ type: rouge
63
+ value: 18.1249
64
+ verified: true
65
+ - name: ROUGE-LSUM
66
+ type: rouge
67
+ value: 25.2421
68
+ verified: true
69
+ - name: loss
70
+ type: loss
71
+ value: 2.607404947280884
72
+ verified: true
73
+ - name: gen_len
74
+ type: gen_len
75
+ value: 72.8931
76
+ verified: true
77
  ---
78
  # BART (large-sized model), fine-tuned on CNN Daily Mail
79