Hugging Face's logo

pig4431
/
YELP_BERT_5E

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
3
pig4431 commited on
Commit
b3901ec
·
1 Parent(s): 2e44b40

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +229 -0
README.md ADDED
@@ -0,0 +1,229 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - yelp_review_full
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: YELP_BERT_5E
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: yelp_review_full
17
+ type: yelp_review_full
18
+ config: yelp_review_full
19
+ split: train
20
+ args: yelp_review_full
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9733333333333334
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # YELP_BERT_5E
31
+
32
+ This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the yelp_review_full dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.1867
35
+ - Accuracy: 0.9733
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 2e-05
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 16
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 5
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 0.5555 | 0.03 | 50 | 0.5569 | 0.74 |
67
+ | 0.2815 | 0.06 | 100 | 0.1400 | 0.9533 |
68
+ | 0.2736 | 0.1 | 150 | 0.1366 | 0.9533 |
69
+ | 0.2444 | 0.13 | 200 | 0.1144 | 0.9667 |
70
+ | 0.1778 | 0.16 | 250 | 0.1739 | 0.9533 |
71
+ | 0.1656 | 0.19 | 300 | 0.1073 | 0.96 |
72
+ | 0.1777 | 0.22 | 350 | 0.1001 | 0.9733 |
73
+ | 0.1915 | 0.26 | 400 | 0.1545 | 0.94 |
74
+ | 0.1983 | 0.29 | 450 | 0.1158 | 0.94 |
75
+ | 0.1858 | 0.32 | 500 | 0.0831 | 0.9667 |
76
+ | 0.2024 | 0.35 | 550 | 0.1088 | 0.96 |
77
+ | 0.1638 | 0.38 | 600 | 0.1047 | 0.9533 |
78
+ | 0.1333 | 0.42 | 650 | 0.1596 | 0.9467 |
79
+ | 0.245 | 0.45 | 700 | 0.1273 | 0.96 |
80
+ | 0.1786 | 0.48 | 750 | 0.1001 | 0.9667 |
81
+ | 0.1859 | 0.51 | 800 | 0.1125 | 0.9467 |
82
+ | 0.1764 | 0.54 | 850 | 0.0963 | 0.9533 |
83
+ | 0.2151 | 0.58 | 900 | 0.0904 | 0.9533 |
84
+ | 0.1152 | 0.61 | 950 | 0.1119 | 0.9667 |
85
+ | 0.1564 | 0.64 | 1000 | 0.0788 | 0.9667 |
86
+ | 0.1691 | 0.67 | 1050 | 0.0791 | 0.9733 |
87
+ | 0.1748 | 0.7 | 1100 | 0.0805 | 0.9667 |
88
+ | 0.1531 | 0.74 | 1150 | 0.0839 | 0.9667 |
89
+ | 0.1426 | 0.77 | 1200 | 0.0957 | 0.9467 |
90
+ | 0.1563 | 0.8 | 1250 | 0.1194 | 0.96 |
91
+ | 0.1666 | 0.83 | 1300 | 0.1029 | 0.96 |
92
+ | 0.1912 | 0.86 | 1350 | 0.0908 | 0.96 |
93
+ | 0.1822 | 0.9 | 1400 | 0.0788 | 0.9733 |
94
+ | 0.1339 | 0.93 | 1450 | 0.1134 | 0.96 |
95
+ | 0.1512 | 0.96 | 1500 | 0.0739 | 0.9733 |
96
+ | 0.1198 | 0.99 | 1550 | 0.0811 | 0.9733 |
97
+ | 0.1118 | 1.02 | 1600 | 0.0819 | 0.9733 |
98
+ | 0.1508 | 1.06 | 1650 | 0.1114 | 0.9667 |
99
+ | 0.0757 | 1.09 | 1700 | 0.1202 | 0.9667 |
100
+ | 0.0959 | 1.12 | 1750 | 0.1077 | 0.9667 |
101
+ | 0.0849 | 1.15 | 1800 | 0.1009 | 0.9733 |
102
+ | 0.0792 | 1.18 | 1850 | 0.0994 | 0.9733 |
103
+ | 0.0651 | 1.22 | 1900 | 0.1192 | 0.9733 |
104
+ | 0.0909 | 1.25 | 1950 | 0.1129 | 0.9667 |
105
+ | 0.0815 | 1.28 | 2000 | 0.1037 | 0.9733 |
106
+ | 0.0933 | 1.31 | 2050 | 0.0884 | 0.98 |
107
+ | 0.0998 | 1.34 | 2100 | 0.0860 | 0.9733 |
108
+ | 0.1099 | 1.38 | 2150 | 0.0793 | 0.98 |
109
+ | 0.0712 | 1.41 | 2200 | 0.0831 | 0.9867 |
110
+ | 0.1126 | 1.44 | 2250 | 0.0681 | 0.98 |
111
+ | 0.0731 | 1.47 | 2300 | 0.1019 | 0.9667 |
112
+ | 0.1021 | 1.5 | 2350 | 0.0659 | 0.9733 |
113
+ | 0.089 | 1.54 | 2400 | 0.0832 | 0.9733 |
114
+ | 0.0967 | 1.57 | 2450 | 0.0766 | 0.98 |
115
+ | 0.1015 | 1.6 | 2500 | 0.0803 | 0.9733 |
116
+ | 0.0956 | 1.63 | 2550 | 0.0781 | 0.9667 |
117
+ | 0.0896 | 1.66 | 2600 | 0.1033 | 0.9667 |
118
+ | 0.0925 | 1.7 | 2650 | 0.1036 | 0.9667 |
119
+ | 0.1326 | 1.73 | 2700 | 0.0892 | 0.9667 |
120
+ | 0.0884 | 1.76 | 2750 | 0.0913 | 0.9667 |
121
+ | 0.1061 | 1.79 | 2800 | 0.0821 | 0.9733 |
122
+ | 0.1031 | 1.82 | 2850 | 0.0935 | 0.9733 |
123
+ | 0.0873 | 1.86 | 2900 | 0.1058 | 0.9733 |
124
+ | 0.0957 | 1.89 | 2950 | 0.1025 | 0.9733 |
125
+ | 0.1149 | 1.92 | 3000 | 0.0675 | 0.98 |
126
+ | 0.0876 | 1.95 | 3050 | 0.1050 | 0.9667 |
127
+ | 0.0951 | 1.98 | 3100 | 0.0765 | 0.9733 |
128
+ | 0.0643 | 2.02 | 3150 | 0.0691 | 0.98 |
129
+ | 0.0551 | 2.05 | 3200 | 0.0765 | 0.98 |
130
+ | 0.0609 | 2.08 | 3250 | 0.0717 | 0.98 |
131
+ | 0.0268 | 2.11 | 3300 | 0.0780 | 0.98 |
132
+ | 0.0338 | 2.14 | 3350 | 0.0980 | 0.9733 |
133
+ | 0.0287 | 2.18 | 3400 | 0.1118 | 0.9733 |
134
+ | 0.0456 | 2.21 | 3450 | 0.1186 | 0.9733 |
135
+ | 0.0294 | 2.24 | 3500 | 0.1162 | 0.9733 |
136
+ | 0.0551 | 2.27 | 3550 | 0.1057 | 0.98 |
137
+ | 0.0445 | 2.3 | 3600 | 0.1042 | 0.9733 |
138
+ | 0.0233 | 2.34 | 3650 | 0.1164 | 0.9733 |
139
+ | 0.0695 | 2.37 | 3700 | 0.1189 | 0.9733 |
140
+ | 0.0524 | 2.4 | 3750 | 0.1198 | 0.9667 |
141
+ | 0.0457 | 2.43 | 3800 | 0.1479 | 0.9733 |
142
+ | 0.0289 | 2.46 | 3850 | 0.1214 | 0.9733 |
143
+ | 0.0432 | 2.5 | 3900 | 0.1740 | 0.9733 |
144
+ | 0.0425 | 2.53 | 3950 | 0.1167 | 0.9733 |
145
+ | 0.022 | 2.56 | 4000 | 0.1667 | 0.9733 |
146
+ | 0.063 | 2.59 | 4050 | 0.1392 | 0.9733 |
147
+ | 0.0388 | 2.62 | 4100 | 0.1376 | 0.9733 |
148
+ | 0.0759 | 2.66 | 4150 | 0.1400 | 0.9733 |
149
+ | 0.0526 | 2.69 | 4200 | 0.1232 | 0.9733 |
150
+ | 0.049 | 2.72 | 4250 | 0.1247 | 0.9667 |
151
+ | 0.0397 | 2.75 | 4300 | 0.1288 | 0.9667 |
152
+ | 0.0346 | 2.78 | 4350 | 0.1243 | 0.9733 |
153
+ | 0.0525 | 2.82 | 4400 | 0.1405 | 0.9733 |
154
+ | 0.0566 | 2.85 | 4450 | 0.1145 | 0.98 |
155
+ | 0.029 | 2.88 | 4500 | 0.1246 | 0.9733 |
156
+ | 0.043 | 2.91 | 4550 | 0.1308 | 0.9733 |
157
+ | 0.0613 | 2.94 | 4600 | 0.1125 | 0.9733 |
158
+ | 0.0704 | 2.98 | 4650 | 0.0872 | 0.98 |
159
+ | 0.0169 | 3.01 | 4700 | 0.1046 | 0.9733 |
160
+ | 0.0277 | 3.04 | 4750 | 0.1193 | 0.9733 |
161
+ | 0.0159 | 3.07 | 4800 | 0.1107 | 0.98 |
162
+ | 0.0013 | 3.1 | 4850 | 0.1342 | 0.9733 |
163
+ | 0.0063 | 3.13 | 4900 | 0.1425 | 0.9733 |
164
+ | 0.0131 | 3.17 | 4950 | 0.1261 | 0.98 |
165
+ | 0.0071 | 3.2 | 5000 | 0.1424 | 0.9733 |
166
+ | 0.0315 | 3.23 | 5050 | 0.1347 | 0.9733 |
167
+ | 0.0045 | 3.26 | 5100 | 0.1582 | 0.9733 |
168
+ | 0.0107 | 3.29 | 5150 | 0.1426 | 0.9733 |
169
+ | 0.014 | 3.33 | 5200 | 0.1298 | 0.98 |
170
+ | 0.0281 | 3.36 | 5250 | 0.1485 | 0.9733 |
171
+ | 0.0101 | 3.39 | 5300 | 0.1340 | 0.9733 |
172
+ | 0.0002 | 3.42 | 5350 | 0.1635 | 0.9733 |
173
+ | 0.0358 | 3.45 | 5400 | 0.1853 | 0.9733 |
174
+ | 0.0107 | 3.49 | 5450 | 0.1812 | 0.96 |
175
+ | 0.0157 | 3.52 | 5500 | 0.1828 | 0.9667 |
176
+ | 0.0336 | 3.55 | 5550 | 0.1839 | 0.9733 |
177
+ | 0.0095 | 3.58 | 5600 | 0.2067 | 0.9667 |
178
+ | 0.0216 | 3.61 | 5650 | 0.2004 | 0.9667 |
179
+ | 0.0136 | 3.65 | 5700 | 0.1892 | 0.9667 |
180
+ | 0.0041 | 3.68 | 5750 | 0.2082 | 0.9667 |
181
+ | 0.0411 | 3.71 | 5800 | 0.1835 | 0.9667 |
182
+ | 0.0233 | 3.74 | 5850 | 0.1713 | 0.9733 |
183
+ | 0.0078 | 3.77 | 5900 | 0.2228 | 0.9667 |
184
+ | 0.01 | 3.81 | 5950 | 0.2097 | 0.9667 |
185
+ | 0.0063 | 3.84 | 6000 | 0.2105 | 0.9667 |
186
+ | 0.0132 | 3.87 | 6050 | 0.2070 | 0.9667 |
187
+ | 0.0134 | 3.9 | 6100 | 0.1995 | 0.9667 |
188
+ | 0.0278 | 3.93 | 6150 | 0.1663 | 0.9733 |
189
+ | 0.0211 | 3.97 | 6200 | 0.1534 | 0.9667 |
190
+ | 0.0237 | 4.0 | 6250 | 0.1954 | 0.9667 |
191
+ | 0.0201 | 4.03 | 6300 | 0.1684 | 0.96 |
192
+ | 0.0013 | 4.06 | 6350 | 0.2022 | 0.9667 |
193
+ | 0.0002 | 4.09 | 6400 | 0.1783 | 0.9667 |
194
+ | 0.011 | 4.13 | 6450 | 0.2207 | 0.9667 |
195
+ | 0.0117 | 4.16 | 6500 | 0.1916 | 0.9667 |
196
+ | 0.0083 | 4.19 | 6550 | 0.1900 | 0.96 |
197
+ | 0.007 | 4.22 | 6600 | 0.1782 | 0.9733 |
198
+ | 0.0074 | 4.25 | 6650 | 0.2034 | 0.9667 |
199
+ | 0.0004 | 4.29 | 6700 | 0.1852 | 0.9667 |
200
+ | 0.0002 | 4.32 | 6750 | 0.2156 | 0.9667 |
201
+ | 0.0069 | 4.35 | 6800 | 0.2257 | 0.9667 |
202
+ | 0.0056 | 4.38 | 6850 | 0.2214 | 0.9667 |
203
+ | 0.016 | 4.41 | 6900 | 0.2035 | 0.9667 |
204
+ | 0.0055 | 4.45 | 6950 | 0.1800 | 0.9733 |
205
+ | 0.0 | 4.48 | 7000 | 0.1819 | 0.9733 |
206
+ | 0.0001 | 4.51 | 7050 | 0.1867 | 0.9733 |
207
+ | 0.0 | 4.54 | 7100 | 0.1880 | 0.9733 |
208
+ | 0.0006 | 4.57 | 7150 | 0.2108 | 0.9667 |
209
+ | 0.0024 | 4.61 | 7200 | 0.2087 | 0.9667 |
210
+ | 0.0003 | 4.64 | 7250 | 0.1992 | 0.9733 |
211
+ | 0.0 | 4.67 | 7300 | 0.2050 | 0.9667 |
212
+ | 0.0037 | 4.7 | 7350 | 0.1899 | 0.9733 |
213
+ | 0.0109 | 4.73 | 7400 | 0.1832 | 0.9733 |
214
+ | 0.0108 | 4.77 | 7450 | 0.1861 | 0.9733 |
215
+ | 0.0159 | 4.8 | 7500 | 0.1795 | 0.9733 |
216
+ | 0.004 | 4.83 | 7550 | 0.1767 | 0.9733 |
217
+ | 0.0012 | 4.86 | 7600 | 0.1888 | 0.9733 |
218
+ | 0.0076 | 4.89 | 7650 | 0.1894 | 0.9733 |
219
+ | 0.0113 | 4.93 | 7700 | 0.1870 | 0.9733 |
220
+ | 0.0007 | 4.96 | 7750 | 0.1869 | 0.9733 |
221
+ | 0.0099 | 4.99 | 7800 | 0.1867 | 0.9733 |
222
+
223
+
224
+ ### Framework versions
225
+
226
+ - Transformers 4.24.0
227
+ - Pytorch 1.13.0
228
+ - Datasets 2.3.2
229
+ - Tokenizers 0.13.2