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

#7
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +33 -0
README.md CHANGED
@@ -78,6 +78,39 @@ model-index:
78
  type: gen_len
79
  value: 186.2003
80
  verified: true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
  ---
82
 
83
  # BigBirdPegasus model (large)
 
78
  type: gen_len
79
  value: 186.2003
80
  verified: true
81
+ - task:
82
+ type: summarization
83
+ name: Summarization
84
+ dataset:
85
+ name: launch/gov_report
86
+ type: launch/gov_report
87
+ config: plain_text
88
+ split: validation
89
+ metrics:
90
+ - name: ROUGE-1
91
+ type: rouge
92
+ value: 26.6836
93
+ verified: true
94
+ - name: ROUGE-2
95
+ type: rouge
96
+ value: 3.937
97
+ verified: true
98
+ - name: ROUGE-L
99
+ type: rouge
100
+ value: 15.2322
101
+ verified: true
102
+ - name: ROUGE-LSUM
103
+ type: rouge
104
+ value: 23.5209
105
+ verified: true
106
+ - name: loss
107
+ type: loss
108
+ value: 7.046688556671143
109
+ verified: true
110
+ - name: gen_len
111
+ type: gen_len
112
+ value: 183.2895
113
+ verified: true
114
  ---
115
 
116
  # BigBirdPegasus model (large)