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
f5d2dae
·
verified ·
1 Parent(s): b69e47f

Upload results/kev_nb4.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. results/kev_nb4.json +213 -0
results/kev_nb4.json ADDED
@@ -0,0 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kev_test": {
3
+ "all": {
4
+ "n": 1440,
5
+ "accuracy": 0.8458,
6
+ "brier": 0.2225,
7
+ "nll": 0.4678,
8
+ "ece15": 0.0324
9
+ },
10
+ "by_source": {
11
+ "agnews": {
12
+ "n": 116,
13
+ "accuracy": 0.9052,
14
+ "brier": 0.1647,
15
+ "nll": 0.3073,
16
+ "ece15": 0.085
17
+ },
18
+ "agnews_yn": {
19
+ "n": 184,
20
+ "accuracy": 0.9076,
21
+ "brier": 0.1125,
22
+ "nll": 0.1863,
23
+ "ece15": 0.0429
24
+ },
25
+ "amazon": {
26
+ "n": 80,
27
+ "accuracy": 0.5625,
28
+ "brier": 0.5299,
29
+ "nll": 0.9672,
30
+ "ece15": 0.1877
31
+ },
32
+ "banking77": {
33
+ "n": 116,
34
+ "accuracy": 0.7241,
35
+ "brier": 0.4187,
36
+ "nll": 1.6279,
37
+ "ece15": 0.1555
38
+ },
39
+ "boolq": {
40
+ "n": 80,
41
+ "accuracy": 0.75,
42
+ "brier": 0.3124,
43
+ "nll": 0.4652,
44
+ "ece15": 0.0903
45
+ },
46
+ "contrastive_age_eligibility": {
47
+ "n": 40,
48
+ "accuracy": 1.0,
49
+ "brier": 0.0007,
50
+ "nll": 0.0167,
51
+ "ece15": 0.0165
52
+ },
53
+ "contrastive_quantity_limit": {
54
+ "n": 40,
55
+ "accuracy": 1.0,
56
+ "brier": 0.0548,
57
+ "nll": 0.1371,
58
+ "ece15": 0.1155
59
+ },
60
+ "contrastive_return_window": {
61
+ "n": 40,
62
+ "accuracy": 0.775,
63
+ "brier": 0.3045,
64
+ "nll": 0.4712,
65
+ "ece15": 0.1041
66
+ },
67
+ "contrastive_spend_threshold": {
68
+ "n": 76,
69
+ "accuracy": 1.0,
70
+ "brier": 0.016,
71
+ "nll": 0.0656,
72
+ "ece15": 0.0597
73
+ },
74
+ "dbpedia14": {
75
+ "n": 116,
76
+ "accuracy": 0.9741,
77
+ "brier": 0.0709,
78
+ "nll": 0.1765,
79
+ "ece15": 0.0906
80
+ },
81
+ "imdb": {
82
+ "n": 80,
83
+ "accuracy": 0.95,
84
+ "brier": 0.0754,
85
+ "nll": 0.1218,
86
+ "ece15": 0.0352
87
+ },
88
+ "mnli": {
89
+ "n": 116,
90
+ "accuracy": 0.819,
91
+ "brier": 0.268,
92
+ "nll": 0.4385,
93
+ "ece15": 0.0878
94
+ },
95
+ "sst5": {
96
+ "n": 80,
97
+ "accuracy": 0.6,
98
+ "brier": 0.5512,
99
+ "nll": 0.9839,
100
+ "ece15": 0.0726
101
+ },
102
+ "trec": {
103
+ "n": 116,
104
+ "accuracy": 0.9655,
105
+ "brier": 0.0861,
106
+ "nll": 0.2029,
107
+ "ece15": 0.0776
108
+ },
109
+ "yelp": {
110
+ "n": 80,
111
+ "accuracy": 0.6375,
112
+ "brier": 0.501,
113
+ "nll": 0.8725,
114
+ "ece15": 0.0954
115
+ },
116
+ "yelp_yn": {
117
+ "n": 80,
118
+ "accuracy": 0.9375,
119
+ "brier": 0.1189,
120
+ "nll": 0.2139,
121
+ "ece15": 0.0668
122
+ }
123
+ }
124
+ },
125
+ "kev_transfer_test": {
126
+ "all": {
127
+ "n": 764,
128
+ "accuracy": 0.6165,
129
+ "brier": 0.5019,
130
+ "nll": 0.8903,
131
+ "ece15": 0.0591
132
+ },
133
+ "by_source": {
134
+ "composition_final_combination": {
135
+ "n": 32,
136
+ "accuracy": 0.4688,
137
+ "brier": 0.5948,
138
+ "nll": 0.8039,
139
+ "ece15": 0.3018
140
+ },
141
+ "composition_final_exception": {
142
+ "n": 32,
143
+ "accuracy": 0.8125,
144
+ "brier": 0.5028,
145
+ "nll": 0.8309,
146
+ "ece15": 0.411
147
+ },
148
+ "composition_final_negation": {
149
+ "n": 32,
150
+ "accuracy": 0.75,
151
+ "brier": 0.3708,
152
+ "nll": 0.5462,
153
+ "ece15": 0.1549
154
+ },
155
+ "contrastive_authorization": {
156
+ "n": 40,
157
+ "accuracy": 0.85,
158
+ "brier": 0.1782,
159
+ "nll": 0.2776,
160
+ "ece15": 0.0852
161
+ },
162
+ "contrastive_deadline": {
163
+ "n": 40,
164
+ "accuracy": 0.45,
165
+ "brier": 0.6756,
166
+ "nll": 1.148,
167
+ "ece15": 0.1014
168
+ },
169
+ "emotion": {
170
+ "n": 116,
171
+ "accuracy": 0.4914,
172
+ "brier": 0.6226,
173
+ "nll": 1.2882,
174
+ "ece15": 0.1468
175
+ },
176
+ "mmlu": {
177
+ "n": 116,
178
+ "accuracy": 0.319,
179
+ "brier": 0.7844,
180
+ "nll": 1.4858,
181
+ "ece15": 0.1872
182
+ },
183
+ "paws": {
184
+ "n": 80,
185
+ "accuracy": 0.55,
186
+ "brier": 0.6198,
187
+ "nll": 0.9515,
188
+ "ece15": 0.3177
189
+ },
190
+ "qnli": {
191
+ "n": 80,
192
+ "accuracy": 0.7875,
193
+ "brier": 0.2933,
194
+ "nll": 0.4659,
195
+ "ece15": 0.0883
196
+ },
197
+ "sciq": {
198
+ "n": 116,
199
+ "accuracy": 0.7845,
200
+ "brier": 0.3576,
201
+ "nll": 0.6977,
202
+ "ece15": 0.1656
203
+ },
204
+ "tweet_offensive": {
205
+ "n": 80,
206
+ "accuracy": 0.775,
207
+ "brier": 0.3071,
208
+ "nll": 0.4658,
209
+ "ece15": 0.0693
210
+ }
211
+ }
212
+ }
213
+ }