lidiya autoevaluator HF staff commited on
Commit
2b0c321
1 Parent(s): eeb1911

Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#3)

Browse files

- Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (04638e9b48a06f66cdc9c63e1cfc914487d49f57)


Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +32 -26
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  language: en
 
3
  tags:
4
  - bart
5
  - seq2seq
6
  - summarization
7
- license: apache-2.0
8
  datasets:
9
  - samsum
10
  widget:
@@ -16,30 +16,30 @@ model-index:
16
  - name: bart-base-samsum
17
  results:
18
  - task:
19
- name: Abstractive Text Summarization
20
  type: abstractive-text-summarization
 
21
  dataset:
22
  name: 'SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization'
23
  type: samsum
24
  metrics:
25
- - name: Validation ROUGE-1
26
- type: rouge-1
27
  value: 46.6619
28
- - name: Validation ROUGE-2
29
- type: rouge-2
30
  value: 23.3285
31
- - name: Validation ROUGE-L
32
- type: rouge-l
33
  value: 39.4811
34
- - name: Test ROUGE-1
35
- type: rouge-1
36
  value: 44.9932
37
- - name: Test ROUGE-2
38
- type: rouge-2
39
  value: 21.7286
40
- - name: Test ROUGE-L
41
- type: rouge-l
42
  value: 38.1921
 
43
  - task:
44
  type: summarization
45
  name: Summarization
@@ -49,30 +49,36 @@ model-index:
49
  config: samsum
50
  split: test
51
  metrics:
52
- - name: ROUGE-1
53
- type: rouge
54
  value: 45.0148
 
55
  verified: true
56
- - name: ROUGE-2
57
- type: rouge
58
  value: 21.6861
 
59
  verified: true
60
- - name: ROUGE-L
61
- type: rouge
62
  value: 38.1728
 
63
  verified: true
64
- - name: ROUGE-LSUM
65
- type: rouge
66
  value: 41.2794
 
67
  verified: true
68
- - name: loss
69
- type: loss
70
  value: 1.597476601600647
 
71
  verified: true
72
- - name: gen_len
73
- type: gen_len
74
  value: 17.6606
 
75
  verified: true
 
76
  ---
77
  ## `bart-base-samsum`
78
  This model was obtained by fine-tuning `facebook/bart-base` on Samsum dataset.
1
  ---
2
  language: en
3
+ license: apache-2.0
4
  tags:
5
  - bart
6
  - seq2seq
7
  - summarization
 
8
  datasets:
9
  - samsum
10
  widget:
16
  - name: bart-base-samsum
17
  results:
18
  - task:
 
19
  type: abstractive-text-summarization
20
+ name: Abstractive Text Summarization
21
  dataset:
22
  name: 'SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization'
23
  type: samsum
24
  metrics:
25
+ - type: rouge-1
 
26
  value: 46.6619
27
+ name: Validation ROUGE-1
28
+ - type: rouge-2
29
  value: 23.3285
30
+ name: Validation ROUGE-2
31
+ - type: rouge-l
32
  value: 39.4811
33
+ name: Validation ROUGE-L
34
+ - type: rouge-1
35
  value: 44.9932
36
+ name: Test ROUGE-1
37
+ - type: rouge-2
38
  value: 21.7286
39
+ name: Test ROUGE-2
40
+ - type: rouge-l
41
  value: 38.1921
42
+ name: Test ROUGE-L
43
  - task:
44
  type: summarization
45
  name: Summarization
49
  config: samsum
50
  split: test
51
  metrics:
52
+ - type: rouge
 
53
  value: 45.0148
54
+ name: ROUGE-1
55
  verified: true
56
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWNlYWIyNzI4MDg5YTcxNzE2NDg3MTBkZGMzMGFmNjVhNDhiMjdiM2YxODdiMDRhZWYyYTdlY2ZkOTZlMThkNyIsInZlcnNpb24iOjF9.hUpQMm2qHUkBPstp7nldJFNy-9B75Z6zunEQCstfGSxIUYXdIlI9u-o0Y9DHIBr4ZLx_CvBtvR2e0shcFFbUBg
57
+ - type: rouge
58
  value: 21.6861
59
+ name: ROUGE-2
60
  verified: true
61
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTAwNjdmM2MwMTcxYjNjMTA4ODk4ZDRhODQ1M2UwN2U2ZjM0MDAyZTJhMTRmMTg0ZThiYThiYTJiN2FiYTk1ZiIsInZlcnNpb24iOjF9._QzKtHvIc_oi1VO-Maxofu-LKINnu9NuAwHmLKka_KwEwrTUZkL74zLa-r4ojKNWpRLRicu02L8W_AQafYoZCw
62
+ - type: rouge
63
  value: 38.1728
64
+ name: ROUGE-L
65
  verified: true
66
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGU0OTEzZTFhMGExOTkzYTI3NzljYjg2YzAxNDM4YzBhM2NjNjI4NWMxYjUwYmFjYzc5YTcxMGVmMTI3YThmMiIsInZlcnNpb24iOjF9.2JgzUAzdOOxUlt8HOWYa8mQuqyRBdyn-LqPiZI-h72zT8mrEO3sIEmmBOvmW40Gf5rvlErYtq87BgxzNwwYUAA
67
+ - type: rouge
68
  value: 41.2794
69
+ name: ROUGE-LSUM
70
  verified: true
71
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjI3ODg4YWQ5MjgwZmZkYTMzMGRjMGI2OWU2MDQ0ZDI3MThkZmYzN2U0OGMwMWJlMjhlMTc5YzgwMDBiM2JiZSIsInZlcnNpb24iOjF9.EnYKG7MuM-lNLkKOrlsb6mB94HqOg9sDBG1mCOni8hi7kM0rveSgSDVLk5Z6Adp-cfdRlho8zK-15TJTHJRxAw
72
+ - type: loss
73
  value: 1.597476601600647
74
+ name: loss
75
  verified: true
76
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTBmYjJmZDhiYmJiMTcxODM5M2ZmMTBkZTcwYzM2NDFiMDJjNjJhOGMyNGQ3MGI1Y2UxZTBhNTBiMjFjZGZiNyIsInZlcnNpb24iOjF9.UdOhxHcBJGRM-kz46st_vVQR_-KWr9EtsaQnLvj7YjCzE6JqHA2LPXnDogpUQX96PISJj32XoK7jlj-2z-CGBQ
77
+ - type: gen_len
78
  value: 17.6606
79
+ name: gen_len
80
  verified: true
81
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWNlM2IyY2EzZGNiOWE0ZGMxZmJmZjhmMDI2YzE1YTQ3NmM3OGQ1NjY2ODllYjI5MDllODNhMjNmMWMyMDAyMiIsInZlcnNpb24iOjF9.sewPQx2WKY8IOBgr0XZkmzOzgwsvJko2iK0noBHpgbyWp41akxWHiaxmvipTOLcx7rbIroXQEr_UgE_LMv46Dw
82
  ---
83
  ## `bart-base-samsum`
84
  This model was obtained by fine-tuning `facebook/bart-base` on Samsum dataset.