Hugging Face's logo

Etelis
/
YELP_ELECTRA_5E

Text Classification
Transformers
PyTorch
electra
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
1
Etelis commited on
Commit
1103787
·
1 Parent(s): a820861

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_ELECTRA_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: 0.96
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_ELECTRA_5E
31
+
32
+ This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on the yelp_review_full dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.1658
35
+ - Accuracy: 0.96
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: 1e-05
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 8
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
+ | 0.6872 | 0.03 | 50 | 0.6751 | 0.5867 |
67
+ | 0.6407 | 0.06 | 100 | 0.5811 | 0.86 |
68
+ | 0.5551 | 0.1 | 150 | 0.4980 | 0.8667 |
69
+ | 0.4784 | 0.13 | 200 | 0.3889 | 0.9333 |
70
+ | 0.412 | 0.16 | 250 | 0.3349 | 0.9333 |
71
+ | 0.3826 | 0.19 | 300 | 0.3138 | 0.9133 |
72
+ | 0.3629 | 0.22 | 350 | 0.2568 | 0.96 |
73
+ | 0.335 | 0.26 | 400 | 0.2352 | 0.9333 |
74
+ | 0.2966 | 0.29 | 450 | 0.1907 | 0.9667 |
75
+ | 0.2776 | 0.32 | 500 | 0.1898 | 0.96 |
76
+ | 0.2428 | 0.35 | 550 | 0.1771 | 0.9533 |
77
+ | 0.2577 | 0.38 | 600 | 0.1610 | 0.96 |
78
+ | 0.2252 | 0.42 | 650 | 0.1503 | 0.96 |
79
+ | 0.2273 | 0.45 | 700 | 0.1425 | 0.9667 |
80
+ | 0.2155 | 0.48 | 750 | 0.1417 | 0.96 |
81
+ | 0.2681 | 0.51 | 800 | 0.1682 | 0.94 |
82
+ | 0.195 | 0.54 | 850 | 0.1527 | 0.96 |
83
+ | 0.2133 | 0.58 | 900 | 0.1480 | 0.9533 |
84
+ | 0.1996 | 0.61 | 950 | 0.1516 | 0.9533 |
85
+ | 0.2123 | 0.64 | 1000 | 0.1645 | 0.94 |
86
+ | 0.2263 | 0.67 | 1050 | 0.1449 | 0.96 |
87
+ | 0.1941 | 0.7 | 1100 | 0.1445 | 0.96 |
88
+ | 0.2273 | 0.74 | 1150 | 0.1389 | 0.96 |
89
+ | 0.2156 | 0.77 | 1200 | 0.1541 | 0.9533 |
90
+ | 0.193 | 0.8 | 1250 | 0.1512 | 0.9533 |
91
+ | 0.1851 | 0.83 | 1300 | 0.1949 | 0.92 |
92
+ | 0.2041 | 0.86 | 1350 | 0.1531 | 0.96 |
93
+ | 0.1924 | 0.9 | 1400 | 0.1640 | 0.9533 |
94
+ | 0.2453 | 0.93 | 1450 | 0.1639 | 0.9467 |
95
+ | 0.1774 | 0.96 | 1500 | 0.1729 | 0.9467 |
96
+ | 0.1999 | 0.99 | 1550 | 0.1618 | 0.94 |
97
+ | 0.1998 | 1.02 | 1600 | 0.1628 | 0.9467 |
98
+ | 0.1607 | 1.06 | 1650 | 0.1608 | 0.94 |
99
+ | 0.1878 | 1.09 | 1700 | 0.1659 | 0.9467 |
100
+ | 0.1702 | 1.12 | 1750 | 0.1694 | 0.9467 |
101
+ | 0.1711 | 1.15 | 1800 | 0.1666 | 0.9467 |
102
+ | 0.1517 | 1.18 | 1850 | 0.1560 | 0.9533 |
103
+ | 0.1521 | 1.22 | 1900 | 0.1662 | 0.9467 |
104
+ | 0.2297 | 1.25 | 1950 | 0.2137 | 0.94 |
105
+ | 0.2046 | 1.28 | 2000 | 0.1793 | 0.94 |
106
+ | 0.1869 | 1.31 | 2050 | 0.1673 | 0.9467 |
107
+ | 0.1684 | 1.34 | 2100 | 0.1730 | 0.9467 |
108
+ | 0.1359 | 1.38 | 2150 | 0.1817 | 0.94 |
109
+ | 0.1595 | 1.41 | 2200 | 0.1709 | 0.9467 |
110
+ | 0.1458 | 1.44 | 2250 | 0.1660 | 0.94 |
111
+ | 0.1518 | 1.47 | 2300 | 0.1735 | 0.9467 |
112
+ | 0.1239 | 1.5 | 2350 | 0.1514 | 0.9533 |
113
+ | 0.2183 | 1.54 | 2400 | 0.1644 | 0.9467 |
114
+ | 0.1678 | 1.57 | 2450 | 0.1578 | 0.9467 |
115
+ | 0.1516 | 1.6 | 2500 | 0.1562 | 0.9467 |
116
+ | 0.2575 | 1.63 | 2550 | 0.1516 | 0.9467 |
117
+ | 0.1576 | 1.66 | 2600 | 0.1684 | 0.9533 |
118
+ | 0.1134 | 1.7 | 2650 | 0.1691 | 0.96 |
119
+ | 0.2075 | 1.73 | 2700 | 0.1586 | 0.96 |
120
+ | 0.1425 | 1.76 | 2750 | 0.1516 | 0.96 |
121
+ | 0.1426 | 1.79 | 2800 | 0.1499 | 0.96 |
122
+ | 0.1295 | 1.82 | 2850 | 0.1563 | 0.96 |
123
+ | 0.1253 | 1.86 | 2900 | 0.1576 | 0.9533 |
124
+ | 0.1801 | 1.89 | 2950 | 0.1563 | 0.9533 |
125
+ | 0.1513 | 1.92 | 3000 | 0.1522 | 0.96 |
126
+ | 0.1204 | 1.95 | 3050 | 0.1604 | 0.9533 |
127
+ | 0.2055 | 1.98 | 3100 | 0.1483 | 0.96 |
128
+ | 0.1461 | 2.02 | 3150 | 0.1532 | 0.96 |
129
+ | 0.1044 | 2.05 | 3200 | 0.1540 | 0.96 |
130
+ | 0.116 | 2.08 | 3250 | 0.1604 | 0.96 |
131
+ | 0.1098 | 2.11 | 3300 | 0.1632 | 0.96 |
132
+ | 0.1259 | 2.14 | 3350 | 0.1640 | 0.96 |
133
+ | 0.1137 | 2.18 | 3400 | 0.1684 | 0.9533 |
134
+ | 0.135 | 2.21 | 3450 | 0.1568 | 0.9467 |
135
+ | 0.1819 | 2.24 | 3500 | 0.1497 | 0.96 |
136
+ | 0.1612 | 2.27 | 3550 | 0.1569 | 0.96 |
137
+ | 0.1699 | 2.3 | 3600 | 0.1594 | 0.96 |
138
+ | 0.1488 | 2.34 | 3650 | 0.1727 | 0.96 |
139
+ | 0.1079 | 2.37 | 3700 | 0.1830 | 0.9533 |
140
+ | 0.1209 | 2.4 | 3750 | 0.1657 | 0.96 |
141
+ | 0.1619 | 2.43 | 3800 | 0.1556 | 0.96 |
142
+ | 0.1544 | 2.46 | 3850 | 0.1627 | 0.96 |
143
+ | 0.1717 | 2.5 | 3900 | 0.1597 | 0.96 |
144
+ | 0.1198 | 2.53 | 3950 | 0.1470 | 0.9467 |
145
+ | 0.0922 | 2.56 | 4000 | 0.1643 | 0.96 |
146
+ | 0.1399 | 2.59 | 4050 | 0.1577 | 0.9467 |
147
+ | 0.1491 | 2.62 | 4100 | 0.1557 | 0.96 |
148
+ | 0.146 | 2.66 | 4150 | 0.1596 | 0.96 |
149
+ | 0.1617 | 2.69 | 4200 | 0.1608 | 0.96 |
150
+ | 0.1463 | 2.72 | 4250 | 0.1601 | 0.9467 |
151
+ | 0.1342 | 2.75 | 4300 | 0.1624 | 0.96 |
152
+ | 0.1492 | 2.78 | 4350 | 0.1586 | 0.96 |
153
+ | 0.1672 | 2.82 | 4400 | 0.1582 | 0.96 |
154
+ | 0.1403 | 2.85 | 4450 | 0.1572 | 0.96 |
155
+ | 0.1173 | 2.88 | 4500 | 0.1630 | 0.96 |
156
+ | 0.1345 | 2.91 | 4550 | 0.1571 | 0.96 |
157
+ | 0.171 | 2.94 | 4600 | 0.1562 | 0.96 |
158
+ | 0.125 | 2.98 | 4650 | 0.1477 | 0.9533 |
159
+ | 0.1494 | 3.01 | 4700 | 0.1404 | 0.96 |
160
+ | 0.1234 | 3.04 | 4750 | 0.1494 | 0.96 |
161
+ | 0.0926 | 3.07 | 4800 | 0.1538 | 0.96 |
162
+ | 0.1188 | 3.1 | 4850 | 0.1565 | 0.96 |
163
+ | 0.0986 | 3.13 | 4900 | 0.1679 | 0.96 |
164
+ | 0.1242 | 3.17 | 4950 | 0.1686 | 0.96 |
165
+ | 0.1193 | 3.2 | 5000 | 0.1688 | 0.96 |
166
+ | 0.1548 | 3.23 | 5050 | 0.1639 | 0.96 |
167
+ | 0.1216 | 3.26 | 5100 | 0.1601 | 0.96 |
168
+ | 0.1068 | 3.29 | 5150 | 0.1799 | 0.94 |
169
+ | 0.1582 | 3.33 | 5200 | 0.1594 | 0.96 |
170
+ | 0.1454 | 3.36 | 5250 | 0.1594 | 0.96 |
171
+ | 0.1631 | 3.39 | 5300 | 0.1555 | 0.96 |
172
+ | 0.1323 | 3.42 | 5350 | 0.1548 | 0.9667 |
173
+ | 0.145 | 3.45 | 5400 | 0.1573 | 0.9667 |
174
+ | 0.1221 | 3.49 | 5450 | 0.1611 | 0.96 |
175
+ | 0.1034 | 3.52 | 5500 | 0.1653 | 0.96 |
176
+ | 0.1096 | 3.55 | 5550 | 0.1688 | 0.96 |
177
+ | 0.096 | 3.58 | 5600 | 0.1690 | 0.9533 |
178
+ | 0.1228 | 3.61 | 5650 | 0.1671 | 0.9533 |
179
+ | 0.1133 | 3.65 | 5700 | 0.1710 | 0.9533 |
180
+ | 0.0939 | 3.68 | 5750 | 0.1772 | 0.96 |
181
+ | 0.1252 | 3.71 | 5800 | 0.1706 | 0.9533 |
182
+ | 0.0726 | 3.74 | 5850 | 0.1685 | 0.96 |
183
+ | 0.1144 | 3.77 | 5900 | 0.1696 | 0.9533 |
184
+ | 0.0902 | 3.81 | 5950 | 0.1753 | 0.9533 |
185
+ | 0.1462 | 3.84 | 6000 | 0.1699 | 0.96 |
186
+ | 0.1019 | 3.87 | 6050 | 0.1677 | 0.96 |
187
+ | 0.1374 | 3.9 | 6100 | 0.1727 | 0.96 |
188
+ | 0.1246 | 3.93 | 6150 | 0.1711 | 0.96 |
189
+ | 0.1026 | 3.97 | 6200 | 0.1728 | 0.96 |
190
+ | 0.1081 | 4.0 | 6250 | 0.1745 | 0.96 |
191
+ | 0.1014 | 4.03 | 6300 | 0.1760 | 0.9533 |
192
+ | 0.1047 | 4.06 | 6350 | 0.1726 | 0.96 |
193
+ | 0.0989 | 4.09 | 6400 | 0.1748 | 0.96 |
194
+ | 0.117 | 4.13 | 6450 | 0.1736 | 0.96 |
195
+ | 0.1499 | 4.16 | 6500 | 0.1755 | 0.96 |
196
+ | 0.0911 | 4.19 | 6550 | 0.1761 | 0.96 |
197
+ | 0.1165 | 4.22 | 6600 | 0.1734 | 0.96 |
198
+ | 0.1072 | 4.25 | 6650 | 0.1693 | 0.96 |
199
+ | 0.1166 | 4.29 | 6700 | 0.1703 | 0.96 |
200
+ | 0.0987 | 4.32 | 6750 | 0.1715 | 0.9467 |
201
+ | 0.0996 | 4.35 | 6800 | 0.1700 | 0.96 |
202
+ | 0.1267 | 4.38 | 6850 | 0.1633 | 0.96 |
203
+ | 0.1374 | 4.41 | 6900 | 0.1642 | 0.9667 |
204
+ | 0.0699 | 4.45 | 6950 | 0.1628 | 0.96 |
205
+ | 0.0773 | 4.48 | 7000 | 0.1642 | 0.96 |
206
+ | 0.0903 | 4.51 | 7050 | 0.1649 | 0.96 |
207
+ | 0.1357 | 4.54 | 7100 | 0.1641 | 0.96 |
208
+ | 0.1252 | 4.57 | 7150 | 0.1659 | 0.9667 |
209
+ | 0.1013 | 4.61 | 7200 | 0.1663 | 0.96 |
210
+ | 0.1071 | 4.64 | 7250 | 0.1653 | 0.96 |
211
+ | 0.1094 | 4.67 | 7300 | 0.1671 | 0.96 |
212
+ | 0.1103 | 4.7 | 7350 | 0.1650 | 0.96 |
213
+ | 0.1169 | 4.73 | 7400 | 0.1656 | 0.96 |
214
+ | 0.0858 | 4.77 | 7450 | 0.1651 | 0.96 |
215
+ | 0.0925 | 4.8 | 7500 | 0.1669 | 0.96 |
216
+ | 0.1572 | 4.83 | 7550 | 0.1663 | 0.96 |
217
+ | 0.1125 | 4.86 | 7600 | 0.1655 | 0.96 |
218
+ | 0.1011 | 4.89 | 7650 | 0.1654 | 0.96 |
219
+ | 0.1307 | 4.93 | 7700 | 0.1656 | 0.96 |
220
+ | 0.1195 | 4.96 | 7750 | 0.1656 | 0.96 |
221
+ | 0.1004 | 4.99 | 7800 | 0.1658 | 0.96 |
222
+
223
+
224
+ ### Framework versions
225
+
226
+ - Transformers 4.24.0
227
+ - Pytorch 1.13.0
228
+ - Datasets 2.7.1
229
+ - Tokenizers 0.13.2