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

#3
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +19 -15
README.md CHANGED
@@ -1,4 +1,11 @@
1
  ---
 
 
 
 
 
 
 
2
  widget:
3
  - context: While deep and large pre-trained models are the state-of-the-art for various
4
  natural language processing tasks, their huge size poses significant challenges
@@ -28,13 +35,6 @@ widget:
28
  question answering dataset and a massive multi-lingual NER dataset with 41 languages.
29
  example_title: xtremedistil q2
30
  text: On what is the model validated?
31
- datasets:
32
- - squad_v2
33
- metrics:
34
- - f1
35
- - exact
36
- tags:
37
- - question-answering
38
  model-index:
39
  - name: nbroad/xdistil-l12-h384-squad2
40
  results:
@@ -47,14 +47,16 @@ model-index:
47
  config: squad_v2
48
  split: validation
49
  metrics:
50
- - name: Exact Match
51
- type: exact_match
52
  value: 75.4591
 
53
  verified: true
54
- - name: F1
55
- type: f1
56
  value: 79.3321
 
57
  verified: true
 
58
  - task:
59
  type: question-answering
60
  name: Question Answering
@@ -64,14 +66,16 @@ model-index:
64
  config: plain_text
65
  split: validation
66
  metrics:
67
- - name: Exact Match
68
- type: exact_match
69
  value: 81.8604
 
70
  verified: true
71
- - name: F1
72
- type: f1
73
  value: 89.6654
 
74
  verified: true
 
75
  ---
76
 
77
  xtremedistil-l12-h384 trained on SQuAD 2.0
 
1
  ---
2
+ tags:
3
+ - question-answering
4
+ datasets:
5
+ - squad_v2
6
+ metrics:
7
+ - f1
8
+ - exact
9
  widget:
10
  - context: While deep and large pre-trained models are the state-of-the-art for various
11
  natural language processing tasks, their huge size poses significant challenges
 
35
  question answering dataset and a massive multi-lingual NER dataset with 41 languages.
36
  example_title: xtremedistil q2
37
  text: On what is the model validated?
 
 
 
 
 
 
 
38
  model-index:
39
  - name: nbroad/xdistil-l12-h384-squad2
40
  results:
 
47
  config: squad_v2
48
  split: validation
49
  metrics:
50
+ - type: exact_match
 
51
  value: 75.4591
52
+ name: Exact Match
53
  verified: true
54
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2QzODE0YTE5ZjMyMWY3NzdjNjcwZDJjY2YyMjBkMWJjMTg3ZDAwYmUwNzU3ZTlkODhmM2VhMWFkY2I2ZjgzMyIsInZlcnNpb24iOjF9.IEjMS4U3uuSP6PfRcD87VFHBIdhoDsIfXkAYV7sz_bveSqhTE16VKJzHaDilCkUCBHYGTjoZ7pDqlYDcF6NKCQ
55
+ - type: f1
56
  value: 79.3321
57
+ name: F1
58
  verified: true
59
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjAxMDdkNzcxNjAzNzQ4N2MwN2Y3ZDZhOGM5MmU0MzYyOGFjNDM3NjJkNGUzYTkyYmY3MDk1ZGIxYzQ0ZDllMyIsInZlcnNpb24iOjF9.N0jPenoMpxbTzKeJciDfoXiLronfXx3uM-A9NEJCMQ9tiApF-EyNmh4F-G9GBXdbVsq1IZ3MbPto0mn0P9hADQ
60
  - task:
61
  type: question-answering
62
  name: Question Answering
 
66
  config: plain_text
67
  split: validation
68
  metrics:
69
+ - type: exact_match
 
70
  value: 81.8604
71
+ name: Exact Match
72
  verified: true
73
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzRiYjBkYTU0MGRjZDZhNzY2MDZhMGYzZDY2NDU2MTMyMjk0M2YwNTcxZjkyMDNkYTE0YTA5ODVlY2EwOWIxYyIsInZlcnNpb24iOjF9.3jco8t0D7YkHtWHWRttV3y3L0ylQZj3y534HtIW7NuUX34nvVSGMzHVJ32BgaFDomOtnJkaSQFXmumO10FL2BA
74
+ - type: f1
75
  value: 89.6654
76
+ name: F1
77
  verified: true
78
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjg5YzNmODRlMTM1ZWQ1MjYwYzVkZmJhMzAwMDMzZGQyYzE1MzFlZGFlYmI4Y2JlMTQyNTBkZDRhMWQxYWQ2MCIsInZlcnNpb24iOjF9.Ld2IHVoqmZ-YFx71FgpuoVDEmAAboxRvhke1DhJYLbdIefM-AH60-58OlZcfZGxgUv6fywGjoPCE9g7CxbSzAQ
79
  ---
80
 
81
  xtremedistil-l12-h384 trained on SQuAD 2.0