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

#17
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +32 -22
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  language: en
3
- inference: false
4
  tags:
5
  - text-generation
6
  - opt
7
- license: other
8
  commercial: false
9
  model-index:
10
  - name: inverse-scaling/opt-30b_eval
@@ -18,14 +18,16 @@ model-index:
18
  config: inverse-scaling--NeQA
19
  split: train
20
  metrics:
21
- - name: Accuracy
22
- type: accuracy
23
  value: 0.55
 
24
  verified: true
25
- - name: Loss
26
- type: loss
27
  value: 0.7019585407276948
 
28
  verified: true
 
29
  - task:
30
  type: zero-shot-classification
31
  name: Zero-Shot Text Classification
@@ -35,14 +37,16 @@ model-index:
35
  config: inverse-scaling--quote-repetition
36
  split: train
37
  metrics:
38
- - name: Accuracy
39
- type: accuracy
40
  value: 0.79
 
41
  verified: true
42
- - name: Loss
43
- type: loss
44
  value: 0.41041071306856103
 
45
  verified: true
 
46
  - task:
47
  type: zero-shot-classification
48
  name: Zero-Shot Text Classification
@@ -52,14 +56,16 @@ model-index:
52
  config: inverse-scaling--redefine-math
53
  split: train
54
  metrics:
55
- - name: Accuracy
56
- type: accuracy
57
  value: 0.6588888888888889
 
58
  verified: true
59
- - name: Loss
60
- type: loss
61
  value: 0.645329966363497
 
62
  verified: true
 
63
  - task:
64
  type: zero-shot-classification
65
  name: Zero-Shot Text Classification
@@ -69,14 +75,16 @@ model-index:
69
  config: inverse-scaling--hindsight-neglect-10shot
70
  split: train
71
  metrics:
72
- - name: Accuracy
73
- type: accuracy
74
  value: 0.35555555555555557
 
75
  verified: true
76
- - name: Loss
77
- type: loss
78
  value: 0.7992834513149564
 
79
  verified: true
 
80
  - task:
81
  type: zero-shot-classification
82
  name: Zero-Shot Text Classification
@@ -86,14 +94,16 @@ model-index:
86
  config: mathemakitten--winobias_antistereotype_test_v5
87
  split: test
88
  metrics:
89
- - name: Accuracy
90
- type: accuracy
91
  value: 0.3713592233009709
 
92
  verified: true
93
- - name: Loss
94
- type: loss
95
  value: 1.3576936555171002
 
96
  verified: true
 
97
  ---
98
 
99
  # OPT : Open Pre-trained Transformer Language Models
 
1
  ---
2
  language: en
3
+ license: other
4
  tags:
5
  - text-generation
6
  - opt
7
+ inference: false
8
  commercial: false
9
  model-index:
10
  - name: inverse-scaling/opt-30b_eval
 
18
  config: inverse-scaling--NeQA
19
  split: train
20
  metrics:
21
+ - type: accuracy
 
22
  value: 0.55
23
+ name: Accuracy
24
  verified: true
25
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2YyNWE2MzFmNGY3Y2Q0ZmM3NDI5YWY5MjdiNWRiMjRmYmE4ZDM4YzMzZWQyNDQ0ZGVlYjlkMWIyMThlZWZmNiIsInZlcnNpb24iOjF9.l1k3x_AcXaglNXFsuOFpoRPsKHP6GITNiqLGsCEwToId9I3eBks4JEzcqWzWFXir76oH0lAF1GnjmnAG1_2kDQ
26
+ - type: loss
27
  value: 0.7019585407276948
28
+ name: Loss
29
  verified: true
30
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjQ0ZDRhMWJjZjNlYjNhZDI5MmMzYzFiM2U2ZGZhY2VhOTdkNjAwNzkxMTY5NDdhMjE0ZjE1MDUyZDM3YTYyMiIsInZlcnNpb24iOjF9.ASg3Rqp-BSAU1cc-r63u2p_fwS-DJZtkskAyot-o3cPhNHeRMF4DOAE0UoQc7PnOSiqpUjUfkn2YOlCAqhrrBw
31
  - task:
32
  type: zero-shot-classification
33
  name: Zero-Shot Text Classification
 
37
  config: inverse-scaling--quote-repetition
38
  split: train
39
  metrics:
40
+ - type: accuracy
 
41
  value: 0.79
42
+ name: Accuracy
43
  verified: true
44
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjVkNmVhZWY2ZDg4MTNhNjA5M2IwZTlmZDc3ZDk0ODE3NmQyYTU0YTMyNWE2NmQzODk2ZDY0ODE4YzQxMWEwYSIsInZlcnNpb24iOjF9.T4pGsrDqa0B5wJmhCQiB_M1x54ydxVZ0kqA91Ntf-K76f7TTg16TTO9fEwLR8aZKbT3a47wN1a8As2l3bT0hDg
45
+ - type: loss
46
  value: 0.41041071306856103
47
+ name: Loss
48
  verified: true
49
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjkwOGFiMTdlNTI2ODY3YTc5MjZmZDc0YWI2NDIwYTc5ODgwNmY0NjkxYjgwYzljMjJmNGYyNmI1MzcwN2EzYiIsInZlcnNpb24iOjF9.hqCd9YFWQChfatU7KJAMPnIV7qFvxxmUVnnI6JrB5k8a-CnEfjc3x5Ypcehk2RdbeH0U4I9RWPPafRKhVzZcDg
50
  - task:
51
  type: zero-shot-classification
52
  name: Zero-Shot Text Classification
 
56
  config: inverse-scaling--redefine-math
57
  split: train
58
  metrics:
59
+ - type: accuracy
 
60
  value: 0.6588888888888889
61
+ name: Accuracy
62
  verified: true
63
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWJiYjNhMmI2Y2M2OGRhZjFjNTMwMTE3NmQ2NmJhODkyY2M3Yzk3YjcyZjUzNzE0MmE4MmIxZTU0N2NkN2Q2YSIsInZlcnNpb24iOjF9.CWcWlNJrbdh-4PLSep9B_E9Z3RaTFkuHKWx3C7tPy9bUjuOJeq8v0rg48SqSd4U2V0EfUxiyvkx_W2dR92m6DQ
64
+ - type: loss
65
  value: 0.645329966363497
66
+ name: Loss
67
  verified: true
68
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDhmMGVlYTY2YjQxODBkNmE3N2UwZDI3NGVkNGM3MzU1NzNkOWM0Zjg5M2Y1ZGJiMTU3NWQyZGEzNWNkMmUzMyIsInZlcnNpb24iOjF9.1hUXv7-fI1_VLWGEMooX6uyOJD_NywB-AqbvW1vfCouK4HCMGgGLZr6XAEi1JjWW6jM0BcR41kLBH09Yh5v5Dw
69
  - task:
70
  type: zero-shot-classification
71
  name: Zero-Shot Text Classification
 
75
  config: inverse-scaling--hindsight-neglect-10shot
76
  split: train
77
  metrics:
78
+ - type: accuracy
 
79
  value: 0.35555555555555557
80
+ name: Accuracy
81
  verified: true
82
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjExZTczY2Q5Y2QxMWE1YWU4MTUwN2MyNzQ4MGFmNmFiNzMxYTUzMWQzNDMzMDhiNjEyZGI4YWUzNzZkM2VlZSIsInZlcnNpb24iOjF9.y7hWqH23GPDyo9jQw3oHyqo2uDaFTLj8rRsjwce515i9uESj-8QIk84bDRV2QD2meclpk6SPe3iQCSokFrWoBw
83
+ - type: loss
84
  value: 0.7992834513149564
85
+ name: Loss
86
  verified: true
87
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWRlY2EzZDQ2ODJhN2JhOGY1MDI5MDUxYzBlMjg5Mzc1YzFkNDg3YTdmMzVkZmIxMDExNjMzNDQzNDAwOTFkOSIsInZlcnNpb24iOjF9.aZzEsysk1bytA5xuWthZpjchXhnQnDbd1AFBqW-7dBAjYAk7rngcu8aD8bbFnlO5QDuYc3wcBbwG00hxrqPZCw
88
  - task:
89
  type: zero-shot-classification
90
  name: Zero-Shot Text Classification
 
94
  config: mathemakitten--winobias_antistereotype_test_v5
95
  split: test
96
  metrics:
97
+ - type: accuracy
 
98
  value: 0.3713592233009709
99
+ name: Accuracy
100
  verified: true
101
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDRkMmM4ZGFjYjU2MDYxODlmMzE5NWNmMDhmMjhjMmZmYjA2YThkY2FhYTQ1Mjk0ZmQyZThlMmI3MWUwN2MyOSIsInZlcnNpb24iOjF9.lRwyFiJdt0FoZo_qYqmtr2MRzQmbt1PN4R3cLEjOunKnR0NYJWcJV66qMRK5iwGFJvs88_4hnRVTp9g1JP7uAQ
102
+ - type: loss
103
  value: 1.3576936555171002
104
+ name: Loss
105
  verified: true
106
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzczNzUwYTRmM2U3MWQzOTBhMjRkOTFiNGU0ZWVmOTg0MTE1ZmM1ZDkyNDY5OTI3MjA2MjEwOTQ1NTg3ZjNmMCIsInZlcnNpb24iOjF9.hVx0oXYBfVBOdFyjYzE1eRDc_hmmqcQqoO6cZIsSdV1QztQkD2EWzduXSLsDQKk1UHV2G-zCamu4ivstLSanCA
107
  ---
108
 
109
  # OPT : Open Pre-trained Transformer Language Models