JeremiahZ autoevaluator HF staff commited on
Commit
0190d1b
1 Parent(s): ef881eb

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 (6b10ebeb55eb19901263e133d6c7175c8ed3329f)


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

Files changed (1) hide show
  1. README.md +21 -15
README.md CHANGED
@@ -12,16 +12,16 @@ model-index:
12
  - name: roberta-base-rte
13
  results:
14
  - task:
15
- name: Text Classification
16
  type: text-classification
 
17
  dataset:
18
  name: GLUE RTE
19
  type: glue
20
  args: rte
21
  metrics:
22
- - name: Accuracy
23
- type: accuracy
24
  value: 0.7978339350180506
 
25
  - task:
26
  type: natural-language-inference
27
  name: Natural Language Inference
@@ -31,30 +31,36 @@ model-index:
31
  config: rte
32
  split: validation
33
  metrics:
34
- - name: Accuracy
35
- type: accuracy
36
  value: 0.7906137184115524
 
37
  verified: true
38
- - name: Precision
39
- type: precision
40
  value: 0.7552447552447552
 
41
  verified: true
42
- - name: Recall
43
- type: recall
44
  value: 0.8244274809160306
 
45
  verified: true
46
- - name: AUC
47
- type: auc
48
  value: 0.8564258078008994
 
49
  verified: true
50
- - name: F1
51
- type: f1
52
  value: 0.7883211678832117
 
53
  verified: true
54
- - name: loss
55
- type: loss
56
  value: 0.5560466051101685
 
57
  verified: true
 
58
  ---
59
 
60
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
12
  - name: roberta-base-rte
13
  results:
14
  - task:
 
15
  type: text-classification
16
+ name: Text Classification
17
  dataset:
18
  name: GLUE RTE
19
  type: glue
20
  args: rte
21
  metrics:
22
+ - type: accuracy
 
23
  value: 0.7978339350180506
24
+ name: Accuracy
25
  - task:
26
  type: natural-language-inference
27
  name: Natural Language Inference
 
31
  config: rte
32
  split: validation
33
  metrics:
34
+ - type: accuracy
 
35
  value: 0.7906137184115524
36
+ name: Accuracy
37
  verified: true
38
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWVhOWZkNGYyMWRmNzdmZTM5MTVmNzFhNjVlMzA1NWU4YjJjODk5ZjM4MTY1Yjg0MTc0MmRmZTNkMzIwZDAzNyIsInZlcnNpb24iOjF9.nFZpFXDSLEIcO-_Z43_5b08GIVQiU9hFUEZpTftW3h6_zqIYZSuM7jOIuDYS3YYWMz42NoH_kosEpJg7TK15Bg
39
+ - type: precision
40
  value: 0.7552447552447552
41
+ name: Precision
42
  verified: true
43
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDYxZTkzZjk1NDU0MjhmNzYxM2IzNzJjNjE1Y2UxYTQ0MTJmNjJlMmUzNGY3MDdiMDAyZjQ2MmE4ODExYjYxNiIsInZlcnNpb24iOjF9.98rxE2rgU5ECIv4MGzMnaPRRYg3kGLsG4pZbMuYeAFEfXqBU1K0i_G-_cU7oxIqGypNmMhYVhVxZfC7wS_saAw
44
+ - type: recall
45
  value: 0.8244274809160306
46
+ name: Recall
47
  verified: true
48
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTNhNDZiZjMzOWM0ZGJkODMzM2VmOGYxMTYyZDNjYTgwN2NiMDFlOGI4NzM5NjQ5ODc4MWM2YmM5MTZjMWFiOCIsInZlcnNpb24iOjF9.C9aEgIz392h-zFSd98CSmzQ7Y6N0Xq3VmGIMEq9aP3dQPPrtUfl9Ms_QMSgSyWMPDYHup3SAGAP0JmkiVeOoBg
49
+ - type: auc
50
  value: 0.8564258078008994
51
+ name: AUC
52
  verified: true
53
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWVlNGVhOTRkNjUxMGMwZmE0YzBjZDQ0YzQ0ODRmYTc0YjI0MDQ2NTNkOWQ2YjU3MmI5NzI4ZWIwMzBlNTQ1NyIsInZlcnNpb24iOjF9.hSyJjOktSt3AItNnVtgWO9jgHwtNbhv4_KrWEV1r_ywopvbpNmSG4yzaI9PZ_bQQ-4ZSmFM8zUYxCl656TWoDQ
54
+ - type: f1
55
  value: 0.7883211678832117
56
+ name: F1
57
  verified: true
58
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGI4Mzk1MTkyZGJkZjQ1MWZkZDIyZTA3OTU0YmZhNjI4NGUxMjk4ZGZhNjZkN2JmZWRmZGU3OWM5Zjc0ODg4NyIsInZlcnNpb24iOjF9.gkQh5Y4dm8NimTtI0i-gHAYTxFRNlOtdgz-NJW8EvNKeFNWYXqa495Q-KEnSBRv88RKiNQXBp-3fyttjhX2HCw
59
+ - type: loss
60
  value: 0.5560466051101685
61
+ name: loss
62
  verified: true
63
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjczNTgxODRlN2Q4NmUyOTdjNzE0ZTZkOWVjZDgzNTdhODAyNGVkM2M1M2I4MGM2ZWMyMDE0ODdhMzQ0N2E1NCIsInZlcnNpb24iOjF9.TfXjqAGtiIQ62HzMkEQmKMMcL9a9bvfBTJARVmTPlIdOOxxF-xuVLXSyFqq2ajhDJXmUEETXBcFzSon_zbHTCQ
64
  ---
65
 
66
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You