lewtun HF staff autoevaluator HF staff commited on
Commit
a696276
1 Parent(s): d2e47ef

Add evaluation results on samsum dataset (#1)

Browse files

- Add evaluation results on samsum dataset (4c770556343e0cd8c64a32b46d9d0610be4e8b71)
- Merge branch 'main' into pr/1 (5f7b7e8b5057ef57dbedebf206eec4b59e8bdcbb)


Co-authored-by: Evaluation Bot <[email protected]>

Files changed (1) hide show
  1. README.md +33 -0
README.md CHANGED
@@ -73,6 +73,39 @@ model-index:
73
  type: gen_len
74
  value: 25.5435
75
  verified: true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  ---
77
  ### Bart model finetuned on xsum
78
 
 
73
  type: gen_len
74
  value: 25.5435
75
  verified: true
76
+ - task:
77
+ type: summarization
78
+ name: Summarization
79
+ dataset:
80
+ name: samsum
81
+ type: samsum
82
+ config: samsum
83
+ split: train
84
+ metrics:
85
+ - name: ROUGE-1
86
+ type: rouge
87
+ value: 24.7852
88
+ verified: true
89
+ - name: ROUGE-2
90
+ type: rouge
91
+ value: 5.2533
92
+ verified: true
93
+ - name: ROUGE-L
94
+ type: rouge
95
+ value: 18.6792
96
+ verified: true
97
+ - name: ROUGE-LSUM
98
+ type: rouge
99
+ value: 20.629
100
+ verified: true
101
+ - name: loss
102
+ type: loss
103
+ value: 3.746837854385376
104
+ verified: true
105
+ - name: gen_len
106
+ type: gen_len
107
+ value: 23.1206
108
+ verified: true
109
  ---
110
  ### Bart model finetuned on xsum
111