autoevaluator HF staff commited on
Commit
7683e97
1 Parent(s): c5275b4

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 +15 -11
README.md CHANGED
@@ -1,12 +1,12 @@
1
  ---
2
- datasets:
3
- - squad_v2
4
  language: en
5
  license: mit
6
- pipeline_tag: question-answering
7
  tags:
8
  - deberta
9
  - deberta-v3
 
 
 
10
  model-index:
11
  - name: navteca/deberta-v3-base-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: 83.8248
 
25
  verified: true
26
- - name: F1
27
- type: f1
28
  value: 87.41
 
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: 84.9678
 
42
  verified: true
43
- - name: F1
44
- type: f1
45
  value: 92.2777
 
46
  verified: true
 
47
  ---
48
 
49
  # Deberta v3 base model for QA (SQuAD 2.0)
 
1
  ---
 
 
2
  language: en
3
  license: mit
 
4
  tags:
5
  - deberta
6
  - deberta-v3
7
+ datasets:
8
+ - squad_v2
9
+ pipeline_tag: question-answering
10
  model-index:
11
  - name: navteca/deberta-v3-base-squad2
12
  results:
 
19
  config: squad_v2
20
  split: validation
21
  metrics:
22
+ - type: exact_match
 
23
  value: 83.8248
24
+ name: Exact Match
25
  verified: true
26
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjFkNmYwODcyYjY3MjJjMzAwNjQzZjI2NjliYmQ4MGZiMDI2OWZkMTdhYmFmN2UyMzE2NDk4YTBjNTdjYTE2ZCIsInZlcnNpb24iOjF9.LgIENpA4WbqDCo_noI-6Dc2UmpufMqCLYAb7rZpEj33vqp4kqOkUGNaHC1iOgfPmyyeedk0NylgUEVmkS51lBQ
27
+ - type: f1
28
  value: 87.41
29
+ name: F1
30
  verified: true
31
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2E3NWYxMTc2NDUzOGM3ZWUyNDA0NDRhNGEyY2QyYmFmZmJlNGYwZmRhMjljZmE2OTIyNmFlMmQ1YWExNDQwNyIsInZlcnNpb24iOjF9.oRi3d751NQo6jQfSWB3xuw9e54-UhjeiNRyiIjE6WgeYd5T3-oRuphubLwnhv8xQPYQqSih8VOuEYj4Qbqj-AA
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: 84.9678
43
+ name: Exact Match
44
  verified: true
45
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGZkZWUyZjJlZWMwOTZiMWU1NmNlN2RiNDI4MWY5YTI3Njc3Y2NjMmYzMDYxYjUwOWI3NTMyOGQ1YjM5MjNhYyIsInZlcnNpb24iOjF9.1Ti7oa5RXpETbOlpHtKpKZ2gz0spb4kzkBfOG1LQGbFMp5v3sRz4u_LhSXYiS2ksJ3sJNz7yIMK8Ci5xT05ODg
46
+ - type: f1
47
  value: 92.2777
48
+ name: F1
49
  verified: true
50
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWE0Mjc5OTE2NjExYzZiM2YyNjdjMjI5Nzk5MTkxZDcxNjMwMjU5MWNkOWNkOTRmMjk1OTczZGRiZGY2ZWRlYSIsInZlcnNpb24iOjF9.Gyhns0q1kBjiDgG7rE2X78lK4HATol9R2d53rWmdf6QamGb5qX2-d8tA48KTEP8WTCxvvvfOPV1es6qmMzN1BQ
51
  ---
52
 
53
  # Deberta v3 base model for QA (SQuAD 2.0)