autoevaluator HF staff commited on
Commit
e4d17e2
1 Parent(s): 3d93353

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 +38 -26
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-125m_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: 0.4666666666666667
 
24
  verified: true
25
- - name: Loss
26
- type: loss
27
  value: 0.9069941281403104
 
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: 0.96
 
41
  verified: true
42
- - name: Loss
43
- type: loss
44
  value: 0.04267331124324727
 
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: 0.7566666666666667
 
58
  verified: true
59
- - name: Loss
60
- type: loss
61
  value: 0.5209774699724383
 
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: 0.5047619047619047
 
75
  verified: true
76
- - name: Loss
77
- type: loss
78
  value: 0.8965487285916295
 
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_cot_v3
87
  split: test
88
  metrics:
89
- - name: Accuracy
90
- type: accuracy
91
  value: 0.47815533980582525
 
92
  verified: true
93
- - name: Loss
94
- type: loss
95
  value: 0.8500587756725001
 
96
  verified: true
 
97
  - task:
98
  type: zero-shot-classification
99
  name: Zero-Shot Text Classification
@@ -103,14 +113,16 @@ model-index:
103
  config: mathemakitten--winobias_antistereotype_test_v5
104
  split: test
105
  metrics:
106
- - name: Accuracy
107
- type: accuracy
108
  value: 0.5024271844660194
 
109
  verified: true
110
- - name: Loss
111
- type: loss
112
  value: 0.8860152396463484
 
113
  verified: true
 
114
  ---
115
 
116
  # 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-125m_eval
 
18
  config: inverse-scaling--NeQA
19
  split: train
20
  metrics:
21
+ - type: accuracy
 
22
  value: 0.4666666666666667
23
+ name: Accuracy
24
  verified: true
25
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjBkYzg3OGQ2NGEwMzE3MmRlNDNjOTQ5YjI2ZmY5ZmExYmMwZGMzOGU4MDM5NmUxMmM0MzlmNmU3OGMxOWNlNyIsInZlcnNpb24iOjF9.6hSSu8iq_f8MCiI3vaVEE2x-Z_7SfVSXu2vEIGggKG1Z1oC1E3-Y7VbZM7cMJKzRvcskLBFaRHYoaU2uZi5gCA
26
+ - type: loss
27
  value: 0.9069941281403104
28
+ name: Loss
29
  verified: true
30
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTNhMDE3NGEyY2UwN2M4ZTNlYjA0YjM1OWZiNWI4MWRjYmRkOGFjMDA2YjZkZWM0YjczMjRhZDIxMmQxMmQ3MCIsInZlcnNpb24iOjF9.ngIQdf8pOt8WcuIo6_vR5nsLCuazdU2605JI-cvjuG6uyBfAE7xWV-ZLqqVZ85cfpGGso1e3FDcnjNgCuS19CQ
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: 0.96
42
+ name: Accuracy
43
  verified: true
44
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzk1NTY4YmYzMzE3OGQ2OGM4NjljNmM0NTc0MWMxZTI3MGI3OTBkMzE3OTJkMjRiYzU2OGUwMjdhMTY1Y2M0MyIsInZlcnNpb24iOjF9.1uGnbKuVoPXeK2zF3nIqAPUeiWodBA78BhDgHk-8Kq9Vh6WtvcL0qwOvQVLjjPmL_7G56Y0d6cuXWycACwuhAQ
45
+ - type: loss
46
  value: 0.04267331124324727
47
+ name: Loss
48
  verified: true
49
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGI3MTBiODBlNjNlZGExNzBhMjgxNjNhNDQ5OGQ5YTBjMjQzNTMwNWQ3MDY3NWY2NzJjOGYzNmFjZTE2ODYzNyIsInZlcnNpb24iOjF9.OoXOKgtCjrB3iku_GtinmPFeFdMJWExa2N-VbKKoymMX9pQJ3Wh9cVbKWI2nTHsoTQI_lu_3s9ZjVVk7_v9zAA
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: 0.7566666666666667
61
+ name: Accuracy
62
  verified: true
63
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTRkMzAyYzcwOGZmNDVhMTMwOGQxOWVhZDE2NzVkMGRkNDJjNzFlMjZkNDFlZDMyZTA0YjYwNTBjNTBlODg2NCIsInZlcnNpb24iOjF9.Mxc3griLDkTEYTJyF0EamDwHEtzN2IkiXKYY9HmIl6HbHvLoJn9Qz1Ot6EE_T0VJbL11Ih7XOgELgiZ35XU3Cw
64
+ - type: loss
65
  value: 0.5209774699724383
66
+ name: Loss
67
  verified: true
68
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjZiZjIzZGUyOGFjODU2ZDk4N2ZmMjc5MmZkY2NmODAyNDhjODQ1MDZiMDc0NDdlM2VmZDc2ZWRhMmFjM2ZhMyIsInZlcnNpb24iOjF9.rWg9_9Z5YtqgO7H61K8w1cp_7GTGsyRpMhACpqioXSnQ6z0sL-rtkwb1QKjD0yQH3MEHr2Grwsh7iUmY0nWjDQ
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: 0.5047619047619047
80
+ name: Accuracy
81
  verified: true
82
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTAxMTI4OWNkNzQ0NTZjOGZhNWJmYjBlZGMyMjg2YjJjZWJjNzU1MmIzNWM5MTg5MzhjYmQ0YzI5NzM5NTVjZiIsInZlcnNpb24iOjF9.dzv4FTu8IIWWu8V497AzCWSjytzv_PnxriQ9aWOUd6AkQCOZQeCLrLYLifoK_BJ2SBcuBum6TS-Ukx9MalklAA
83
+ - type: loss
84
  value: 0.8965487285916295
85
+ name: Loss
86
  verified: true
87
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2ExZjE2ZWIxODBjZTA0OTI1NzI0NTRlMTIxNDI1YjA4OTM5YzVkMzc4N2MzZTc4ZTA4OTFiYTlkMjcyYjY0MiIsInZlcnNpb24iOjF9.FjnpzThx7mRfh1U_R12KCUJ2wDxjaEKQC3iSSVAvzP1xXLESxA4c014Xzucw1Ugaq_P8s5ySzlPgGUp7qqTtBA
88
  - task:
89
  type: zero-shot-classification
90
  name: Zero-Shot Text Classification
 
94
  config: mathemakitten--winobias_antistereotype_test_cot_v3
95
  split: test
96
  metrics:
97
+ - type: accuracy
 
98
  value: 0.47815533980582525
99
+ name: Accuracy
100
  verified: true
101
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDdkNmEwOTQwZTI4MzE4YjlmNjIwZTIxMWM3YWM1YzYyMWM1OTY1YmZkNjhjYmUyZjJjZjZkMTljNjZlMzUwYyIsInZlcnNpb24iOjF9.PLaVz67JgdncUXDz3BXmZC41HKVl3_D1Iz5cgygbn2y4OsfVyvsyvU3GFqKgPb-gvXT4xGMxkV0FvA28gjTGDw
102
+ - type: loss
103
  value: 0.8500587756725001
104
+ name: Loss
105
  verified: true
106
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODFjNjUwMWI2Y2UwNzQ0NDE4NTU1NGI3YzQyMDNhOWU3YjU0MGRhMjEyZjNkMzczYWU2MDY0NGIyZmM5MWY5OCIsInZlcnNpb24iOjF9.9VQeAZ_lvyKC2RNQ2GmqSrxXCz2W8NZz14JhF3j4boBHXRm1V07wml6uNW_GfDt6Qwiu5IZCqMdvCavacDUoDw
107
  - task:
108
  type: zero-shot-classification
109
  name: Zero-Shot Text Classification
 
113
  config: mathemakitten--winobias_antistereotype_test_v5
114
  split: test
115
  metrics:
116
+ - type: accuracy
 
117
  value: 0.5024271844660194
118
+ name: Accuracy
119
  verified: true
120
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDRjYzkzZDI1MDRjY2JiNDUyNGJmNmVlZTMxYmJjODIzNDc2NGI3MzBjN2RkNGRjZjg5ZjJiYjM1ODQyMjQyMyIsInZlcnNpb24iOjF9.uLQjZb34N0QHPgeMnJkPk3xG3VI4Z_djPpCvah29a9D0fOHMuqdqynnySODmwfdbKecEV5za8wUf6_ny4qktDQ
121
+ - type: loss
122
  value: 0.8860152396463484
123
+ name: Loss
124
  verified: true
125
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWIzODA0ZjExNzJiMDBjNzlkYzFjMzk2NGMxNzM0ODQyNmFhMDczM2EwMWU1N2VjMjcxNGEzMTdjN2IyNDJhNSIsInZlcnNpb24iOjF9.ipVZVlS7Rey-vsqEhAmOjcz4pkl85Brn8i1aTc4eSXQ2KgG5ScuAgeIVcxe3EbCSJsRkJowRqRqqWKBodiyAAQ
126
  ---
127
 
128
  # OPT : Open Pre-trained Transformer Language Models