autoevaluator HF staff commited on
Commit
20c20b8
1 Parent(s): 7d311b0

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 +44 -30
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-1.3b_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: 0.5133333333333333
 
24
  verified: true
25
- - name: Loss
26
- type: loss
27
  value: 0.7768662874648968
 
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: 0.95
 
41
  verified: true
42
- - name: Loss
43
- type: loss
44
  value: 0.08434048505476036
 
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: 0.6688888888888889
 
58
  verified: true
59
- - name: Loss
60
- type: loss
61
  value: 0.6386728600992096
 
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: 0.45396825396825397
 
75
  verified: true
76
- - name: Loss
77
- type: loss
78
  value: 0.8809041155236108
 
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_v1
87
  split: test
88
  metrics:
89
- - name: Accuracy
90
- type: accuracy
91
  value: 0.39563106796116504
 
92
  verified: true
93
- - name: Loss
94
- type: loss
95
  value: 1.294413821680473
 
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_cot_v3
104
  split: test
105
  metrics:
106
- - name: Accuracy
107
- type: accuracy
108
  value: 0.40048543689320387
 
109
  verified: true
110
- - name: Loss
111
- type: loss
112
  value: 1.1583690714066759
 
113
  verified: true
 
114
  - task:
115
  type: zero-shot-classification
116
  name: Zero-Shot Text Classification
@@ -120,14 +132,16 @@ model-index:
120
  config: mathemakitten--winobias_antistereotype_test_v5
121
  split: test
122
  metrics:
123
- - name: Accuracy
124
- type: accuracy
125
  value: 0.41504854368932037
 
126
  verified: true
127
- - name: Loss
128
- type: loss
129
  value: 1.2905146084796921
 
130
  verified: true
 
131
  ---
132
 
133
  # 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-1.3b_eval
 
18
  config: inverse-scaling--NeQA
19
  split: train
20
  metrics:
21
+ - type: accuracy
 
22
  value: 0.5133333333333333
23
+ name: Accuracy
24
  verified: true
25
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmE3ZjEyOTk1MjE5ODY5MGI3YzFmNmUzZjJlOGQxMDY5NDMwNmZlMDU3YTMxNzRmNzFlNjQ2NmZmZWVjZWJkYyIsInZlcnNpb24iOjF9.qm5eR4WCCEBXYHxMRIZygcuHZQrqffJcL64WoJE9KKEJl_w0hzoRZtQGyMPlud_R0P6dfKTyHY8-P31FyO5bDA
26
+ - type: loss
27
  value: 0.7768662874648968
28
+ name: Loss
29
  verified: true
30
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDg4ZmMzNDYzZDM2OWY2NDE1N2ExY2M4MjkzZjk4ODY1OTFiMmU1MzY2ZmIwNTUzMTIzMjk2OWMzOTkyYzIyYiIsInZlcnNpb24iOjF9.zd4HcEF_rqmjlanoUMQlVJ6qiJh0VGBoASxQltYSf1WG9ernfK-DWoG3K7FbcyA34xiln7YkFTsAfDk1bJ5lDw
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: 0.95
42
+ name: Accuracy
43
  verified: true
44
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmJjN2Y1OTI3ZDNiMTY3ZWEzMWNmYjI1OGFhNTE2NjJkNTNmZDllNDM0YjZiYjE2ODkyNTczOGY5YTk1MTQ1ZCIsInZlcnNpb24iOjF9.3AN_N2hszoYP16PjXB3JKJyxN9VNUZ3kPCbJjCLtrA9YhG5oaGK-pV2eLzVDYOLrQwedu3zeuAQY8k1QzY01Dg
45
+ - type: loss
46
  value: 0.08434048505476036
47
+ name: Loss
48
  verified: true
49
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGFiYTY3MTM5MzdlMDU4ZTI3YWM0NzYzMGFkNDk5NWU4MTcwNDc3MWJhNDUzMTVmMmQwOGY2MGMyZGZhYTVjNyIsInZlcnNpb24iOjF9.hMb_PRr3qDgiTxkFHKaWbam8g18q70nSUmNkc5clDQQuX4zMcA6URuGG09pNlmW7eYCkgEHmh9wXZIZjZsZUCg
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: 0.6688888888888889
61
+ name: Accuracy
62
  verified: true
63
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjI3OTk3YWUxMjcxY2I0MGRlYjNmOWQ4NzNlMjJjMzY0MDI1ZWQxMGQ2NTNlMWQyNmM2NmY4YTc4YWQ5N2E1ZCIsInZlcnNpb24iOjF9.wRij21b6f1DbpnkRmMaDthOVQdQGVFhxRJTXkbIPtzP7ih85jZ8l6WpDQGpoULMWEm2g880nZWsF-d2pX180Bw
64
+ - type: loss
65
  value: 0.6386728600992096
66
+ name: Loss
67
  verified: true
68
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDk4NjY3MGNjMmVkODRhZTcwYjQ3ZDk4M2I4YThkNzg0YzUxZDdiZjY0MmNjY2Y4N2NlZjY2ZjZhNjk5MmFkMyIsInZlcnNpb24iOjF9.Sc2THcMu0eD-pw9vqgAaT6iGJY5iN1RutbfQpU3cNcLmivgbEWOtDdEZDjBjimEHtpkpM0Dxhvql_nPCo_-_BQ
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: 0.45396825396825397
80
+ name: Accuracy
81
  verified: true
82
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWMyZWU4ODI2ZDA0ZjM3YTU2NTJiNzA1ZTFhMzc2MGYyMjEzOGVkYmY5ZmFkNzNkNTUwNDlhNDE3NWE3Y2E2ZSIsInZlcnNpb24iOjF9.goRx1LfVtEtjIQNT8oKikd49CQlBKFBb_Jwcz69XJoC_TF4iEiqxovfJwIdbLupxr1W0gnASWNXLY3qK60DiDg
83
+ - type: loss
84
  value: 0.8809041155236108
85
+ name: Loss
86
  verified: true
87
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDcxZTUwZTdlZTE3OWY1MDdjZTc1ODJhOTdmZDIyOTRmNWJjOTNjOWUzMjU3NzRkZGUwYTVkZDZiNzkzNzI5YiIsInZlcnNpb24iOjF9.Yg5_4sz7ManNO2Zg1xkKa-b_GNEITJ52OZPID_ODUxXia1B7zaM5YPjuovRCt7qN23eyq0t_BH4rHKFv_WG7DA
88
  - task:
89
  type: zero-shot-classification
90
  name: Zero-Shot Text Classification
 
94
  config: mathemakitten--winobias_antistereotype_test_cot_v1
95
  split: test
96
  metrics:
97
+ - type: accuracy
 
98
  value: 0.39563106796116504
99
+ name: Accuracy
100
  verified: true
101
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWQ4YjUyZTgxMWM3OWE0N2YwOTE2MTUxNDA1YmY1NjcyNDU0YThjM2QyMWU5OTc5YjVhZGRiOGM2NjAzNWVhNSIsInZlcnNpb24iOjF9.Y_-72Iv-10RZTK36JGMEKqU_ofvZAMmrEr5UzISEQV8MKJzx8HTqYl90I2YSkNLUzdK6c_PcAFuPYn6VkkJgDw
102
+ - type: loss
103
  value: 1.294413821680473
104
+ name: Loss
105
  verified: true
106
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDJmMDVhNmQwNGM2MDhmNDM5NmY3OGJjNjM1YWFjYzE3ZDM0YmQ0NGJhMzEyNGRiZTY2ZTZjMWE2ZmRhM2ZiMyIsInZlcnNpb24iOjF9.4lOFoVAXZcz-tkHTPeRSNBZw5egzmhy1RiVPyEprs36iQmmiAPNqKYwTqvKMY-IUoS-QzL0D7LstGCIjx9UVDg
107
  - task:
108
  type: zero-shot-classification
109
  name: Zero-Shot Text Classification
 
113
  config: mathemakitten--winobias_antistereotype_test_cot_v3
114
  split: test
115
  metrics:
116
+ - type: accuracy
 
117
  value: 0.40048543689320387
118
+ name: Accuracy
119
  verified: true
120
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWU1MzE4OTFkNGZkM2FmZDkwYmUyNDIzZGY0ZmNkODUxNWVmMmU2YzJiODAyMGY1YjQyZDQwOTEzOWJlMWU0NCIsInZlcnNpb24iOjF9.ZnaemvPodb4zs29b3cpDKmTAjQwOvWO-dmCat2cFnWtjbQE-sGW_YhECHU9L_WvzvL6OLR858DjFhopH_uoDAA
121
+ - type: loss
122
  value: 1.1583690714066759
123
+ name: Loss
124
  verified: true
125
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGNjM2NkM2I4ZDQ0MjYwZWVjMzhlZTgzYWQyM2I3ZmUzYWRlNTVjYzIxODE0Njg5MmVkYjRiM2MyODcyZjQ4ZiIsInZlcnNpb24iOjF9.RTQXfCmOWYhK8Zc04obVInuZawUbYhXzYRVLFo5l8HFbL6_GNcjI5Udm9frhyE4emvJeRI6FCl8Oj0xPjIM7Bg
126
  - task:
127
  type: zero-shot-classification
128
  name: Zero-Shot Text Classification
 
132
  config: mathemakitten--winobias_antistereotype_test_v5
133
  split: test
134
  metrics:
135
+ - type: accuracy
 
136
  value: 0.41504854368932037
137
+ name: Accuracy
138
  verified: true
139
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzQxZWMwYWMwZTBjMTcxYTYxOThkY2NhZjlhZTgxODM2MTEyNTUyODEyZjZhNDZjMjE5OWY1ZmM2OGY1MzEzZCIsInZlcnNpb24iOjF9._3PyP-HE1MPm8xglgp73aOAN63Lrf6niEwyYTG0nvz0rERBPdWY4AJNIIqk23AsapvYKyxuV2zrwceviWNp9AA
140
+ - type: loss
141
  value: 1.2905146084796921
142
+ name: Loss
143
  verified: true
144
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTc1YTZlYjU1MTFiOWVmYTU3YWY0YzVmZWRhYjlkMDU2ZWQ0ZGJlZDZmYWIxYTZmZWQ4ZGY4Nzc4NWY3MWNkYiIsInZlcnNpb24iOjF9.HBW6UGhoEBC_5iMTQjS6oRdQ7-wGXNd5165_OSuZ04HZiGCaF6Pe9sMtMIIZQbu4UlYySQtzm1071l4gcvnpBQ
145
  ---
146
 
147
  # OPT : Open Pre-trained Transformer Language Models