MicPie autoevaluator HF staff commited on
Commit
25da13c
1 Parent(s): 15fe3b0

Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#14)

Browse files

- Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (1fb2e084e46a80f3fa6b29859f3661c912317c02)


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

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-66b_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: 0.5366666666666666
 
24
  verified: true
25
- - name: Loss
26
- type: loss
27
  value: 0.7120504426956177
 
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: 0.8366666666666667
 
41
  verified: true
42
- - name: Loss
43
- type: loss
44
  value: 0.3102515521908413
 
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: 0.6144444444444445
 
58
  verified: true
59
- - name: Loss
60
- type: loss
61
  value: 0.7022326097430455
 
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: 0.23174603174603176
 
75
  verified: true
76
- - name: Loss
77
- type: loss
78
  value: 0.8490466677953327
 
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: 0.33980582524271846
 
92
  verified: true
93
- - name: Loss
94
- type: loss
95
  value: 1.4462068147712868
 
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-66b_eval
 
18
  config: inverse-scaling--NeQA
19
  split: train
20
  metrics:
21
+ - type: accuracy
 
22
  value: 0.5366666666666666
23
+ name: Accuracy
24
  verified: true
25
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTkyZWE3YzYxOGEwZmU1NDVjYzcxYTYwYmFjNjljZGNiM2ZmNmVkNzc3YzE5YzZmNjM2YjRjOWI5YzljNDY0NyIsInZlcnNpb24iOjF9.XV9kdQe3pHJJMkCdmXegJ8t_GCOr4ul6bK5PcaUDJ3XtMP6i8qh09EEcI7HVzT934a3m5RmtlaoWsz76TmM1Cw
26
+ - type: loss
27
  value: 0.7120504426956177
28
+ name: Loss
29
  verified: true
30
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjBiYWZhMTJmZGVkMjIzMGVkYWRmNTIyZjgwN2JhMzNkYTE2ZDJjYWJlN2JlMDQwZmE0N2JlYzRlMmIyYTExOSIsInZlcnNpb24iOjF9.-qyaiEzkgDTFGEmgytF6VXdjDAGJqnSwjBpNTeIEoz99QWGdAW6qAn-PCMGfX8Zw-MA9_EF-Szi1VM1HVPtgDQ
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: 0.8366666666666667
42
+ name: Accuracy
43
  verified: true
44
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWYzNWYxYWYwMGU4YjIzODEwMmRmYjBhMGVkNzE5NjFiMzU0NzIzZDFlYTc3Y2Y1ZjlhMzE3MmI4NGYwZDFkNiIsInZlcnNpb24iOjF9.W6WKF0ajwmk4dRyBNuyv5qbn_Hl97RbAuxB6xV3BVoAYf4cym6TlCF5_9cCGWb7A--rAc1PLeSsaksSJL1H1DQ
45
+ - type: loss
46
  value: 0.3102515521908413
47
+ name: Loss
48
  verified: true
49
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjI3NmZhYjcwMzkyZDNhZWIyMDAyNmVkMWZmNjE1NDlmMWZjNGYzZTQyNTQ5NDkxN2IwNjhhMTgzMDM1ODA2NiIsInZlcnNpb24iOjF9.UfCBdy49wMMNOe_6oSgPJj2tt3yRgNRp3fmaA5T0Es7Xj3kKJetcDUCAgwQUdc96NtYLjT4SVIhC4OGU78F4Ag
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: 0.6144444444444445
61
+ name: Accuracy
62
  verified: true
63
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDRlOTdjYjhjNDEwMmNlNDdmMzRkY2MwMGU1YjU0M2ZiYTVkMmZkMTQ1ZTBkMTRmNDFjZDlkNDJhZGM1ZjUzNCIsInZlcnNpb24iOjF9.yJJSf6D3NBmdbow2cdqXT3Ye9vwVJk6lBsT8h3FaMZU52BG8et8X-IkpyTHbOZOFGAt-PAwhuzkf3pDIpn_YAQ
64
+ - type: loss
65
  value: 0.7022326097430455
66
+ name: Loss
67
  verified: true
68
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTI0ZWE3NDU2NTcwMzMxNzNmMmNlY2EzYmUyNDQ2OWJkMGM2ZmY4N2RkMWM5MjE5ZjU4MDE4NTM0Zjk1ZjgyYSIsInZlcnNpb24iOjF9.aYVojrgRucgKl8p3seX6FwmKeZ2My-6aC2MbxGUlPiGOwJi5Jcx4_z7hJ1d8tWjWZ24eI9vPhZZAFjD9Ekr5BQ
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: 0.23174603174603176
80
+ name: Accuracy
81
  verified: true
82
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGFiYWE5ZTNkNjY4YjBlYjI3ODI5NGY3NzExYzA0OWZmOWM4NWI0NGY5Y2FlNjQ1MmM4YWQ3MDlmZmVjYzZiYyIsInZlcnNpb24iOjF9.vZtvZnP37_xmBOWoxrtPZzv6WrJDnZ0zAOpRG6JtAuKBlWmvsDrxVIrrnScoyLsw-2ixe_xqojVepRjqnyBZCw
83
+ - type: loss
84
  value: 0.8490466677953327
85
+ name: Loss
86
  verified: true
87
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTc2Y2EzMjZlNmM4MjBjYWM0ZGFjODZhYzA1NDM1ODExOTZhYzk2NDM2N2ZjOTg3YzFjZmUwNDUzZmI0NDRkYyIsInZlcnNpb24iOjF9.79rOdptdpN1GwidNjsGeB05TYMMMK5cTQ1Y9W4vt_EqsQFOq5ZbwtM_pjIe0gQJIvcYvtYBjzt9rNJJ_GSSiCA
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: 0.33980582524271846
99
+ name: Accuracy
100
  verified: true
101
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGIyMmZlYWMwM2I3MDc4YzU3MjIwODI3MmQxYmI2OTFhNGRkZDllZjdiZmVjN2JlNGQ2N2E5ZmY3Y2U4YzQwYSIsInZlcnNpb24iOjF9.jbKQXavDYXixb_Iy4sfKR6qf6Dv4469gRSvM6fBymLq4c6nswEyX5_fHkbidwtjktQ0xOc3GYy7e-WQ2rGPBDA
102
+ - type: loss
103
  value: 1.4462068147712868
104
+ name: Loss
105
  verified: true
106
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTAzMWVlYzMwZmYzMmNjOGU0NjQzYzNmN2ZlNTMyNDc3MGFhYjY4MmYxNThhYjRiZDExNzE3YmZjNWU2MWU1MCIsInZlcnNpb24iOjF9.E5Ib1XRJqvbcwYomSSqciIAiVDxkyft2DzpPqkKbuSZGGN9T94Q8RBx4rvG3GaaRy8UE7REneDYgWMO99c35Aw
107
  ---
108
 
109
  # OPT : Open Pre-trained Transformer Language Models