autoevaluator HF staff commited on
Commit
44b340e
1 Parent(s): 859e7e6

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

Browse files

Beep boop, I am a bot from Hugging Face's automatic model evaluator 👋! We've added a new `verifyToken` field to your evaluation results to verify that they are produced by the model evaluator. Accept this PR to ensure that your results remain listed as **verified** on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards).

Files changed (1) hide show
  1. README.md +12 -8
README.md CHANGED
@@ -14,14 +14,16 @@ model-index:
14
  config: squad_v2
15
  split: validation
16
  metrics:
17
- - name: Exact Match
18
- type: exact_match
19
  value: 79.3917
 
20
  verified: true
21
- - name: F1
22
- type: f1
23
  value: 82.6738
 
24
  verified: true
 
25
  - task:
26
  type: question-answering
27
  name: Question Answering
@@ -31,14 +33,16 @@ model-index:
31
  config: plain_text
32
  split: validation
33
  metrics:
34
- - name: Exact Match
35
- type: exact_match
36
  value: 84.9246
 
37
  verified: true
38
- - name: F1
39
- type: f1
40
  value: 91.6201
 
41
  verified: true
 
42
  ---
43
 
44
  # Deberta-v3-xsmall-squad2
 
14
  config: squad_v2
15
  split: validation
16
  metrics:
17
+ - type: exact_match
 
18
  value: 79.3917
19
+ name: Exact Match
20
  verified: true
21
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTFiMWI5YzFlMDZhMzc2NDIwYjNiZmIyMThmOWQxYjFjZmM2ZDQ0OGM2NmNlNmI3Y2U2N2JjMmVkZTgyZjNiOCIsInZlcnNpb24iOjF9.MCw9UJ3MI3Lf5hvOgk7Lw2xZfN4678p7ebG3vnGXX_Avw6fELTPwxZ9qGA-9tL00p4NxaSb3Cx6XAFvWetAIBA
22
+ - type: f1
23
  value: 82.6738
24
+ name: F1
25
  verified: true
26
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjdiYWY2MzU4YjZhMWQzZGJhZTk3NzU3Y2UwYmQ4MzliZmQxOGUxZDllN2Y0ZmZhYjVlNTE0MzY1MjU5OWMwMCIsInZlcnNpb24iOjF9.zeWLwXy77n0YKxGA5gjySe8p-_nPQxbiPnvQU2tF45IyMmlYKUuLeq4hJnNe-5NgriTf8xkBJBE7Cr5lWHy_Cw
27
  - task:
28
  type: question-answering
29
  name: Question Answering
 
33
  config: plain_text
34
  split: validation
35
  metrics:
36
+ - type: exact_match
 
37
  value: 84.9246
38
+ name: Exact Match
39
  verified: true
40
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGJhYmU0Y2I4Y2UyOGVlOTlkMmQ2OTcyMTZkNTkwNTMzNzhmNzZiYjU4ZDkxMGM5NzAyMjk1M2ExNGIzOWU4NCIsInZlcnNpb24iOjF9.ql1rCId6lQ7Uwq2spG3q2fFppkFGHA1IWQjvyPRhvKdRNzApBO0mu9JjMAv4uNKZX-kmGEkI018_9tAzN7kwDw
41
+ - type: f1
42
  value: 91.6201
43
+ name: F1
44
  verified: true
45
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjBjMmI0OTFmODVjMzllZDM0NTdmNjU4NGI4NzA4NTJhOWVkMDQ5OTY0MDcyMWEwZTFkODNlY2VhZjU2NWJmZSIsInZlcnNpb24iOjF9.rGvF60bfWIXzB66C7fkdxCtZvRZ_m3onbLaNbs7M4M0Fk27xnMat6IAy1DeTztkOKLoiD2s2NQH6wXid83cgCw
46
  ---
47
 
48
  # Deberta-v3-xsmall-squad2