Hugging Face's logo

emrevrg
/
AUBIN-Mini

Text Classification
ONNX
Safetensors
onnxruntime
decision-model
typed-decisions
calibrated
cross-encoder
on-device
aubin
norovox
preview
Model card Files
xet
 Community
emrevrg commited on
Commit
b69e47f
·
verified ·
1 Parent(s): b097493

Upload results/kev_phone.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. results/kev_phone.json +213 -0
results/kev_phone.json ADDED
@@ -0,0 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kev_test": {
3
+ "all": {
4
+ "n": 1440,
5
+ "accuracy": 0.8465,
6
+ "brier": 0.2223,
7
+ "nll": 0.4676,
8
+ "ece15": 0.0389
9
+ },
10
+ "by_source": {
11
+ "agnews": {
12
+ "n": 116,
13
+ "accuracy": 0.9052,
14
+ "brier": 0.1645,
15
+ "nll": 0.307,
16
+ "ece15": 0.0963
17
+ },
18
+ "agnews_yn": {
19
+ "n": 184,
20
+ "accuracy": 0.9076,
21
+ "brier": 0.1117,
22
+ "nll": 0.1852,
23
+ "ece15": 0.0447
24
+ },
25
+ "amazon": {
26
+ "n": 80,
27
+ "accuracy": 0.5875,
28
+ "brier": 0.5296,
29
+ "nll": 0.9666,
30
+ "ece15": 0.1622
31
+ },
32
+ "banking77": {
33
+ "n": 116,
34
+ "accuracy": 0.7241,
35
+ "brier": 0.4177,
36
+ "nll": 1.6314,
37
+ "ece15": 0.1506
38
+ },
39
+ "boolq": {
40
+ "n": 80,
41
+ "accuracy": 0.75,
42
+ "brier": 0.3128,
43
+ "nll": 0.4669,
44
+ "ece15": 0.0898
45
+ },
46
+ "contrastive_age_eligibility": {
47
+ "n": 40,
48
+ "accuracy": 1.0,
49
+ "brier": 0.0007,
50
+ "nll": 0.0166,
51
+ "ece15": 0.0164
52
+ },
53
+ "contrastive_quantity_limit": {
54
+ "n": 40,
55
+ "accuracy": 1.0,
56
+ "brier": 0.0555,
57
+ "nll": 0.1379,
58
+ "ece15": 0.116
59
+ },
60
+ "contrastive_return_window": {
61
+ "n": 40,
62
+ "accuracy": 0.775,
63
+ "brier": 0.3046,
64
+ "nll": 0.4712,
65
+ "ece15": 0.1332
66
+ },
67
+ "contrastive_spend_threshold": {
68
+ "n": 76,
69
+ "accuracy": 1.0,
70
+ "brier": 0.0161,
71
+ "nll": 0.0647,
72
+ "ece15": 0.0587
73
+ },
74
+ "dbpedia14": {
75
+ "n": 116,
76
+ "accuracy": 0.9741,
77
+ "brier": 0.0705,
78
+ "nll": 0.1755,
79
+ "ece15": 0.0903
80
+ },
81
+ "imdb": {
82
+ "n": 80,
83
+ "accuracy": 0.95,
84
+ "brier": 0.0759,
85
+ "nll": 0.1222,
86
+ "ece15": 0.0291
87
+ },
88
+ "mnli": {
89
+ "n": 116,
90
+ "accuracy": 0.819,
91
+ "brier": 0.2673,
92
+ "nll": 0.4373,
93
+ "ece15": 0.0903
94
+ },
95
+ "sst5": {
96
+ "n": 80,
97
+ "accuracy": 0.5875,
98
+ "brier": 0.5512,
99
+ "nll": 0.9831,
100
+ "ece15": 0.079
101
+ },
102
+ "trec": {
103
+ "n": 116,
104
+ "accuracy": 0.9655,
105
+ "brier": 0.0869,
106
+ "nll": 0.2034,
107
+ "ece15": 0.0772
108
+ },
109
+ "yelp": {
110
+ "n": 80,
111
+ "accuracy": 0.6375,
112
+ "brier": 0.5006,
113
+ "nll": 0.8723,
114
+ "ece15": 0.1045
115
+ },
116
+ "yelp_yn": {
117
+ "n": 80,
118
+ "accuracy": 0.9375,
119
+ "brier": 0.1179,
120
+ "nll": 0.2119,
121
+ "ece15": 0.0568
122
+ }
123
+ }
124
+ },
125
+ "kev_transfer_test": {
126
+ "all": {
127
+ "n": 764,
128
+ "accuracy": 0.6217,
129
+ "brier": 0.5025,
130
+ "nll": 0.8912,
131
+ "ece15": 0.0645
132
+ },
133
+ "by_source": {
134
+ "composition_final_combination": {
135
+ "n": 32,
136
+ "accuracy": 0.5,
137
+ "brier": 0.5958,
138
+ "nll": 0.8063,
139
+ "ece15": 0.3364
140
+ },
141
+ "composition_final_exception": {
142
+ "n": 32,
143
+ "accuracy": 0.8125,
144
+ "brier": 0.5035,
145
+ "nll": 0.831,
146
+ "ece15": 0.412
147
+ },
148
+ "composition_final_negation": {
149
+ "n": 32,
150
+ "accuracy": 0.75,
151
+ "brier": 0.3688,
152
+ "nll": 0.5433,
153
+ "ece15": 0.1567
154
+ },
155
+ "contrastive_authorization": {
156
+ "n": 40,
157
+ "accuracy": 0.85,
158
+ "brier": 0.1749,
159
+ "nll": 0.2737,
160
+ "ece15": 0.1137
161
+ },
162
+ "contrastive_deadline": {
163
+ "n": 40,
164
+ "accuracy": 0.45,
165
+ "brier": 0.6749,
166
+ "nll": 1.147,
167
+ "ece15": 0.1301
168
+ },
169
+ "emotion": {
170
+ "n": 116,
171
+ "accuracy": 0.4914,
172
+ "brier": 0.6243,
173
+ "nll": 1.2895,
174
+ "ece15": 0.1511
175
+ },
176
+ "mmlu": {
177
+ "n": 116,
178
+ "accuracy": 0.3448,
179
+ "brier": 0.785,
180
+ "nll": 1.4887,
181
+ "ece15": 0.1803
182
+ },
183
+ "paws": {
184
+ "n": 80,
185
+ "accuracy": 0.55,
186
+ "brier": 0.6188,
187
+ "nll": 0.9489,
188
+ "ece15": 0.3222
189
+ },
190
+ "qnli": {
191
+ "n": 80,
192
+ "accuracy": 0.7875,
193
+ "brier": 0.2937,
194
+ "nll": 0.4669,
195
+ "ece15": 0.0924
196
+ },
197
+ "sciq": {
198
+ "n": 116,
199
+ "accuracy": 0.7845,
200
+ "brier": 0.3619,
201
+ "nll": 0.703,
202
+ "ece15": 0.1609
203
+ },
204
+ "tweet_offensive": {
205
+ "n": 80,
206
+ "accuracy": 0.775,
207
+ "brier": 0.306,
208
+ "nll": 0.465,
209
+ "ece15": 0.0611
210
+ }
211
+ }
212
+ }
213
+ }