autoevaluator HF staff commited on
Commit
a49eb28
1 Parent(s): 26e1596

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-6.7b_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: 0.54
 
24
  verified: true
25
- - name: Loss
26
- type: loss
27
  value: 0.740270353704691
 
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: 0.86
 
41
  verified: true
42
- - name: Loss
43
- type: loss
44
  value: 0.22016974209290055
 
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: 0.6733333333333333
 
58
  verified: true
59
- - name: Loss
60
- type: loss
61
  value: 0.638882334422734
 
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: 0.4666666666666667
 
75
  verified: true
76
- - name: Loss
77
- type: loss
78
  value: 0.7550815605928027
 
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: 0.3737864077669903
 
92
  verified: true
93
- - name: Loss
94
- type: loss
95
  value: 1.2823651640752816
 
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: 0.3859223300970874
 
109
  verified: true
110
- - name: Loss
111
- type: loss
112
  value: 1.295986159347468
 
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-6.7b_eval
 
18
  config: inverse-scaling--NeQA
19
  split: train
20
  metrics:
21
+ - type: accuracy
 
22
  value: 0.54
23
+ name: Accuracy
24
  verified: true
25
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWE0ZjA1NDg0YjYzNTZhYjIwZDRhNDcxYjNiYTQ1YTY2YWQ1YTUzZmIyMTlmYTljMGJiNjAyNzc0YTNiYWFhNCIsInZlcnNpb24iOjF9.eWcHC6dzOjnuF-mT6Z2G8Z1xCoow6iViE1Qy-VNKMSzIcJZcvgkZI0NhU50YMi4tOOZN2k92MATtbXtcZR5yCQ
26
+ - type: loss
27
  value: 0.740270353704691
28
+ name: Loss
29
  verified: true
30
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTY1M2ZlYTYzMjZhNTVmZjgyMWJiYmYxZGM2NjQxYjdlZDI3ZmZmODAxMTI5N2RmMjMyNzYzMWUxZTViNjM5YSIsInZlcnNpb24iOjF9.G3DqNVlNLP5uAmzOKa9hsxBBiSWXbrDesp3hIlQomYe2YsbWbYF0WssbFi7DXEu5hmj6yCN2E-olbEjzwZ2eBQ
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: 0.86
42
+ name: Accuracy
43
  verified: true
44
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzA0ZjJlZGUwOGNhNmE3MmMzMDY1YTM4ZjYzNDUwYjk1MTU2MmVhMGQzYjI3YzI0ZGMzMWFkODIyZWE5Mjk2ZCIsInZlcnNpb24iOjF9.pc3tzIMBv05ZBixkmRojnIzsdHLvYhZX_sJnNZ_t_oo61DrTUhYQYq3xikx8S5rIr5sWrLTbxWn3rAAXme0KAQ
45
+ - type: loss
46
  value: 0.22016974209290055
47
+ name: Loss
48
  verified: true
49
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWE5Njk4OWQ5Mzg3ODljMWM3MzhiNjBhNTk5ZGJjMDU3ZTJlZDZjZjBjYzdkMmMxZTJlMTJkMjg1OTA5ZWQxNSIsInZlcnNpb24iOjF9.NubehOGlzEURMYuTkvqzXmf1ENadam7uZ62YA1nv1DjAivd8VySmpLl-QnnZLcDbhduMZbRp4lMQbWG9Z26LAg
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: 0.6733333333333333
61
+ name: Accuracy
62
  verified: true
63
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTAyYjAwMzgyMDc2MmU1NDM0MmMyOWUyYzc3YTYxNzkyYzk2ZGZiMTk5NjlkODUwNDQ1NzFlMTU0Y2Y0ZGZlYSIsInZlcnNpb24iOjF9.VMxtPMY9qKk4eSjAlDb_jfg1nsf8eq1Oz5WnfUSC-VkXREQ6-f1qBooJc617t6U5apIbHnaW9XP3LTYrGzvUDQ
64
+ - type: loss
65
  value: 0.638882334422734
66
+ name: Loss
67
  verified: true
68
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDYwNWVmZGM5ZmM2MmY0Y2IzYzNhOTNkZmU2YTA2MWZlZTU1ZGI2OTM1YzJiNjViNzMwMjA0Y2Q0ODBlYTgzOSIsInZlcnNpb24iOjF9.YJujmeEYbf4ZOJ0w_Q24d7t5ksKST35aweNJSk6UYuCiV6uSIJhJUz_w8iFwo9ykM-EOXamL87dftlkyawgtBw
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: 0.4666666666666667
80
+ name: Accuracy
81
  verified: true
82
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjVlMzdkYTUxZmI1ZDBmMDdjM2VhMjA1ZTg0MGYzMzU0NzFlN2JmNDY2NDc0MmVlMjI3MDg1Y2Q5MDRhYWU1ZCIsInZlcnNpb24iOjF9.Z01fwvvUFNOWeUWexSpdmAUPYJIsYUV-eb1ybSEjQ3cb9ow2STMVgxp0PqaDJMVWKg30xIkARahsg8ci6QpbBw
83
+ - type: loss
84
  value: 0.7550815605928027
85
+ name: Loss
86
  verified: true
87
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWQyNmYwZjdkMTM1YjIxYzEwMmUwMWVlZTRjODQwYWExNDQ2MTgzYzA0ZTlkODcxYWIxMzdmNWE0NDdmNzcxYiIsInZlcnNpb24iOjF9.TtX2cKfatVMFX09l6DiuKFEa1vlDJUBPohSLmdQGh8QCTf-DrylUqARU8Ni5cSiSlidFF4n4IWIL0vQ941n6DQ
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: 0.3737864077669903
99
+ name: Accuracy
100
  verified: true
101
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTliMzU1NGIxMTUxYTM4NzVlYzI4YzljMDYyOWM1ZDdkMWMyNjIwOWQ4OGNhZWE3ZTljZGI0ZTA2ZWU3MjVmMiIsInZlcnNpb24iOjF9.dTlDpXOusgl6m3dn7XwfKeaxaVfU1VnEHWFeh7yBNSq5TyHPWbixlNumOWDjc-y9v8g0oWBXqWhT0KMQDaGVCQ
102
+ - type: loss
103
  value: 1.2823651640752816
104
+ name: Loss
105
  verified: true
106
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTRjZmU4YWNkNGEwMjNlMGEyYjA1ZjhjOGE3OTZiZTJlYjMyMjViMTYyYWQ1YTdlMmM1ZjU5NTFhOWU3NzM1OCIsInZlcnNpb24iOjF9.yGmOME0MrX0moaU5c2WYf8H7CFfSGsPuQ2qp9MCi_es5RQRWoCHeCcR5oLQ4RATmVpYdzocPxqrbeZfqxVIOAQ
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: 0.3859223300970874
118
+ name: Accuracy
119
  verified: true
120
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzZlZjIzNDM0Mzk5MmRlMTFlOWVlZjY3MDFmY2NhZjlkYWNmMWQ2MjdhOTg3YTg0OTI1YjY5YmYxMTc4YjYyOCIsInZlcnNpb24iOjF9.nCFVShWbHuHFKEdK5INjQSfLI9KQUNQZqqjqYCw_HVHSW0QHLIXdAb7_GDZJhCUTJ-JkBVCJFtEliA2Zw9GjAw
121
+ - type: loss
122
  value: 1.295986159347468
123
+ name: Loss
124
  verified: true
125
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWE3ZjhmYzM3NjRhMjc3OGU5NWQzY2Q1NzA2ZDBjN2Q1YmZkYzdiMDBhMmY1ZDM5NmU2YzQ2ZGZmZmYyMzg5NiIsInZlcnNpb24iOjF9.2UzIpqw83YQdGOqTKKP7ywqpNdgCDkR36lhkbja6qFsKyQctcg4vZgLXfMSfufWf1G_9iXqY8r-JiZadMdK3Dg
126
  ---
127
 
128
  # OPT : Open Pre-trained Transformer Language Models