Sebastian autoevaluator HF staff commited on
Commit
cf83ca2
1 Parent(s): d88b80d

Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#8)

Browse files

- Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (f15e2df316f03bf05de5724308ab38d2174120fb)


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

Files changed (1) hide show
  1. README.md +14 -10
README.md CHANGED
@@ -1,12 +1,12 @@
1
  ---
2
  language: en
3
- datasets:
4
- - squad_v2
5
  license: cc-by-4.0
6
  tags:
7
  - deberta
8
  - deberta-v3
9
  - deberta-v3-large
 
 
10
  model-index:
11
  - name: deepset/deberta-v3-large-squad2
12
  results:
@@ -19,14 +19,16 @@ model-index:
19
  config: squad_v2
20
  split: validation
21
  metrics:
22
- - name: Exact Match
23
- type: exact_match
24
  value: 88.0876
 
25
  verified: true
26
- - name: F1
27
- type: f1
28
  value: 91.1623
 
29
  verified: true
 
30
  - task:
31
  type: question-answering
32
  name: Question Answering
@@ -36,14 +38,16 @@ model-index:
36
  config: plain_text
37
  split: validation
38
  metrics:
39
- - name: Exact Match
40
- type: exact_match
41
  value: 89.2366
 
42
  verified: true
43
- - name: F1
44
- type: f1
45
  value: 95.0569
 
46
  verified: true
 
47
  ---
48
  # deberta-v3-large for QA
49
 
1
  ---
2
  language: en
 
 
3
  license: cc-by-4.0
4
  tags:
5
  - deberta
6
  - deberta-v3
7
  - deberta-v3-large
8
+ datasets:
9
+ - squad_v2
10
  model-index:
11
  - name: deepset/deberta-v3-large-squad2
12
  results:
19
  config: squad_v2
20
  split: validation
21
  metrics:
22
+ - type: exact_match
 
23
  value: 88.0876
24
+ name: Exact Match
25
  verified: true
26
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmE0MWEwNjBkNTA1MmU0ZDkyYTA1OGEwNzY3NGE4NWU4NGI0NTQzNjRlNjY1NGRmNDU2MjA0NjU1N2JlZmNhYiIsInZlcnNpb24iOjF9.PnBF_vD0HujNBSShGJzsJnjmiBP_qT8xb2E7ORmpKfNspKXEuN_pBk9iV0IHRzdqOSyllcxlCv93XMPblNjWDw
27
+ - type: f1
28
  value: 91.1623
29
+ name: F1
30
  verified: true
31
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDBkNDUzZmNkNDQwOGRkMmVlZjkxZWVlMzk3NzFmMGIxMTFmMjZlZDcyOWFiMjljNjM5MThlZDM4OWRmNzMwOCIsInZlcnNpb24iOjF9.bacyetziNI2DxO67GWpTyeRPXqF1POkyv00wEHXlyZu71pZngsNpZyrnuj2aJlCqQwHGnF_lT2ysaXKHprQRBg
32
  - task:
33
  type: question-answering
34
  name: Question Answering
38
  config: plain_text
39
  split: validation
40
  metrics:
41
+ - type: exact_match
 
42
  value: 89.2366
43
+ name: Exact Match
44
  verified: true
45
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjQ1Yjk3YTdiYTY1NmYxMTI1ZGZlMjRkNTlhZTkyNjRkNjgxYWJiNDk2NzE3NjAyYmY3YmRjNjg4YmEyNDkyYyIsInZlcnNpb24iOjF9.SEWyqX_FPQJOJt2KjOCNgQ2giyVeLj5bmLI5LT_Pfo33tbWPWD09TySYdsthaVTjUGT5DvDzQLASSwBH05FyBw
46
+ - type: f1
47
  value: 95.0569
48
+ name: F1
49
  verified: true
50
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2QyODQ1NWVlYjQxMjA0YTgyNmQ2NmIxOWY3MDRmZjE3ZWI5Yjc4ZDE4NzA2YjE2YTE1YTBlNzNiYmNmNzI3NCIsInZlcnNpb24iOjF9.NcXEc9xoggV76w1bQKxuJDYbOTxFzdny2k-85_b6AIMtfpYV3rGR1Z5YF6tVY2jyp7mgm5Jd5YSgGI3NvNE-CQ
51
  ---
52
  # deberta-v3-large for QA
53