Hugging Face's logo

simonycl
/
best_model-yelp_polarity-32-42

Text Classification
Transformers
PyTorch
albert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
simonycl commited on
Commit
836e588
·
1 Parent(s): 16f729e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +210 -0
README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: best_model-yelp_polarity-32-42
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # best_model-yelp_polarity-32-42
17
+
18
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5496
21
+ - Accuracy: 0.9531
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 500
47
+ - num_epochs: 150
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 2 | 0.5517 | 0.9531 |
54
+ | No log | 2.0 | 4 | 0.5516 | 0.9531 |
55
+ | No log | 3.0 | 6 | 0.5516 | 0.9531 |
56
+ | No log | 4.0 | 8 | 0.5515 | 0.9531 |
57
+ | 0.2601 | 5.0 | 10 | 0.5513 | 0.9531 |
58
+ | 0.2601 | 6.0 | 12 | 0.5511 | 0.9531 |
59
+ | 0.2601 | 7.0 | 14 | 0.5510 | 0.9531 |
60
+ | 0.2601 | 8.0 | 16 | 0.5508 | 0.9531 |
61
+ | 0.2601 | 9.0 | 18 | 0.5505 | 0.9531 |
62
+ | 0.2238 | 10.0 | 20 | 0.5500 | 0.9531 |
63
+ | 0.2238 | 11.0 | 22 | 0.5494 | 0.9531 |
64
+ | 0.2238 | 12.0 | 24 | 0.5484 | 0.9531 |
65
+ | 0.2238 | 13.0 | 26 | 0.5471 | 0.9531 |
66
+ | 0.2238 | 14.0 | 28 | 0.5456 | 0.9531 |
67
+ | 0.1513 | 15.0 | 30 | 0.5442 | 0.9531 |
68
+ | 0.1513 | 16.0 | 32 | 0.5426 | 0.9531 |
69
+ | 0.1513 | 17.0 | 34 | 0.5409 | 0.9531 |
70
+ | 0.1513 | 18.0 | 36 | 0.5380 | 0.9531 |
71
+ | 0.1513 | 19.0 | 38 | 0.5359 | 0.9531 |
72
+ | 0.0647 | 20.0 | 40 | 0.5331 | 0.9531 |
73
+ | 0.0647 | 21.0 | 42 | 0.5336 | 0.9531 |
74
+ | 0.0647 | 22.0 | 44 | 0.5345 | 0.9531 |
75
+ | 0.0647 | 23.0 | 46 | 0.5373 | 0.9531 |
76
+ | 0.0647 | 24.0 | 48 | 0.5391 | 0.9531 |
77
+ | 0.0382 | 25.0 | 50 | 0.5404 | 0.9531 |
78
+ | 0.0382 | 26.0 | 52 | 0.5413 | 0.9531 |
79
+ | 0.0382 | 27.0 | 54 | 0.5420 | 0.9531 |
80
+ | 0.0382 | 28.0 | 56 | 0.5425 | 0.9531 |
81
+ | 0.0382 | 29.0 | 58 | 0.5433 | 0.9531 |
82
+ | 0.0 | 30.0 | 60 | 0.5438 | 0.9531 |
83
+ | 0.0 | 31.0 | 62 | 0.5441 | 0.9531 |
84
+ | 0.0 | 32.0 | 64 | 0.5444 | 0.9531 |
85
+ | 0.0 | 33.0 | 66 | 0.5446 | 0.9531 |
86
+ | 0.0 | 34.0 | 68 | 0.5440 | 0.9531 |
87
+ | 0.0085 | 35.0 | 70 | 0.5435 | 0.9531 |
88
+ | 0.0085 | 36.0 | 72 | 0.5430 | 0.9531 |
89
+ | 0.0085 | 37.0 | 74 | 0.5425 | 0.9531 |
90
+ | 0.0085 | 38.0 | 76 | 0.5421 | 0.9531 |
91
+ | 0.0085 | 39.0 | 78 | 0.5418 | 0.9531 |
92
+ | 0.0 | 40.0 | 80 | 0.5415 | 0.9531 |
93
+ | 0.0 | 41.0 | 82 | 0.5412 | 0.9531 |
94
+ | 0.0 | 42.0 | 84 | 0.5410 | 0.9531 |
95
+ | 0.0 | 43.0 | 86 | 0.5408 | 0.9531 |
96
+ | 0.0 | 44.0 | 88 | 0.5407 | 0.9531 |
97
+ | 0.0 | 45.0 | 90 | 0.5406 | 0.9531 |
98
+ | 0.0 | 46.0 | 92 | 0.5404 | 0.9531 |
99
+ | 0.0 | 47.0 | 94 | 0.5404 | 0.9531 |
100
+ | 0.0 | 48.0 | 96 | 0.5403 | 0.9531 |
101
+ | 0.0 | 49.0 | 98 | 0.5403 | 0.9531 |
102
+ | 0.0 | 50.0 | 100 | 0.5403 | 0.9531 |
103
+ | 0.0 | 51.0 | 102 | 0.5404 | 0.9531 |
104
+ | 0.0 | 52.0 | 104 | 0.5404 | 0.9531 |
105
+ | 0.0 | 53.0 | 106 | 0.5405 | 0.9531 |
106
+ | 0.0 | 54.0 | 108 | 0.5408 | 0.9531 |
107
+ | 0.0 | 55.0 | 110 | 0.5413 | 0.9531 |
108
+ | 0.0 | 56.0 | 112 | 0.5418 | 0.9531 |
109
+ | 0.0 | 57.0 | 114 | 0.5421 | 0.9531 |
110
+ | 0.0 | 58.0 | 116 | 0.5425 | 0.9531 |
111
+ | 0.0 | 59.0 | 118 | 0.5427 | 0.9531 |
112
+ | 0.0 | 60.0 | 120 | 0.5429 | 0.9531 |
113
+ | 0.0 | 61.0 | 122 | 0.5431 | 0.9531 |
114
+ | 0.0 | 62.0 | 124 | 0.5433 | 0.9531 |
115
+ | 0.0 | 63.0 | 126 | 0.5435 | 0.9531 |
116
+ | 0.0 | 64.0 | 128 | 0.5436 | 0.9531 |
117
+ | 0.0 | 65.0 | 130 | 0.5437 | 0.9531 |
118
+ | 0.0 | 66.0 | 132 | 0.5439 | 0.9531 |
119
+ | 0.0 | 67.0 | 134 | 0.5439 | 0.9531 |
120
+ | 0.0 | 68.0 | 136 | 0.5440 | 0.9531 |
121
+ | 0.0 | 69.0 | 138 | 0.5441 | 0.9531 |
122
+ | 0.0 | 70.0 | 140 | 0.5442 | 0.9531 |
123
+ | 0.0 | 71.0 | 142 | 0.5443 | 0.9531 |
124
+ | 0.0 | 72.0 | 144 | 0.5443 | 0.9531 |
125
+ | 0.0 | 73.0 | 146 | 0.5444 | 0.9531 |
126
+ | 0.0 | 74.0 | 148 | 0.5440 | 0.9531 |
127
+ | 0.0 | 75.0 | 150 | 0.5436 | 0.9531 |
128
+ | 0.0 | 76.0 | 152 | 0.5433 | 0.9531 |
129
+ | 0.0 | 77.0 | 154 | 0.5430 | 0.9531 |
130
+ | 0.0 | 78.0 | 156 | 0.5428 | 0.9531 |
131
+ | 0.0 | 79.0 | 158 | 0.5427 | 0.9531 |
132
+ | 0.0 | 80.0 | 160 | 0.5426 | 0.9531 |
133
+ | 0.0 | 81.0 | 162 | 0.5424 | 0.9531 |
134
+ | 0.0 | 82.0 | 164 | 0.5422 | 0.9531 |
135
+ | 0.0 | 83.0 | 166 | 0.5420 | 0.9531 |
136
+ | 0.0 | 84.0 | 168 | 0.5420 | 0.9531 |
137
+ | 0.0 | 85.0 | 170 | 0.5419 | 0.9531 |
138
+ | 0.0 | 86.0 | 172 | 0.5419 | 0.9531 |
139
+ | 0.0 | 87.0 | 174 | 0.5419 | 0.9531 |
140
+ | 0.0 | 88.0 | 176 | 0.5419 | 0.9531 |
141
+ | 0.0 | 89.0 | 178 | 0.5420 | 0.9531 |
142
+ | 0.0 | 90.0 | 180 | 0.5420 | 0.9531 |
143
+ | 0.0 | 91.0 | 182 | 0.5421 | 0.9531 |
144
+ | 0.0 | 92.0 | 184 | 0.5422 | 0.9531 |
145
+ | 0.0 | 93.0 | 186 | 0.5423 | 0.9531 |
146
+ | 0.0 | 94.0 | 188 | 0.5427 | 0.9531 |
147
+ | 0.0 | 95.0 | 190 | 0.5430 | 0.9531 |
148
+ | 0.0 | 96.0 | 192 | 0.5433 | 0.9531 |
149
+ | 0.0 | 97.0 | 194 | 0.5436 | 0.9531 |
150
+ | 0.0 | 98.0 | 196 | 0.5438 | 0.9531 |
151
+ | 0.0 | 99.0 | 198 | 0.5440 | 0.9531 |
152
+ | 0.0 | 100.0 | 200 | 0.5442 | 0.9531 |
153
+ | 0.0 | 101.0 | 202 | 0.5444 | 0.9531 |
154
+ | 0.0 | 102.0 | 204 | 0.5446 | 0.9531 |
155
+ | 0.0 | 103.0 | 206 | 0.5448 | 0.9531 |
156
+ | 0.0 | 104.0 | 208 | 0.5449 | 0.9531 |
157
+ | 0.0 | 105.0 | 210 | 0.5451 | 0.9531 |
158
+ | 0.0 | 106.0 | 212 | 0.5452 | 0.9531 |
159
+ | 0.0 | 107.0 | 214 | 0.5453 | 0.9531 |
160
+ | 0.0 | 108.0 | 216 | 0.5455 | 0.9531 |
161
+ | 0.0 | 109.0 | 218 | 0.5457 | 0.9531 |
162
+ | 0.0 | 110.0 | 220 | 0.5459 | 0.9531 |
163
+ | 0.0 | 111.0 | 222 | 0.5461 | 0.9531 |
164
+ | 0.0 | 112.0 | 224 | 0.5462 | 0.9531 |
165
+ | 0.0 | 113.0 | 226 | 0.5464 | 0.9531 |
166
+ | 0.0 | 114.0 | 228 | 0.5465 | 0.9531 |
167
+ | 0.0 | 115.0 | 230 | 0.5466 | 0.9531 |
168
+ | 0.0 | 116.0 | 232 | 0.5467 | 0.9531 |
169
+ | 0.0 | 117.0 | 234 | 0.5468 | 0.9531 |
170
+ | 0.0 | 118.0 | 236 | 0.5469 | 0.9531 |
171
+ | 0.0 | 119.0 | 238 | 0.5470 | 0.9531 |
172
+ | 0.0 | 120.0 | 240 | 0.5471 | 0.9531 |
173
+ | 0.0 | 121.0 | 242 | 0.5472 | 0.9531 |
174
+ | 0.0 | 122.0 | 244 | 0.5473 | 0.9531 |
175
+ | 0.0 | 123.0 | 246 | 0.5474 | 0.9531 |
176
+ | 0.0 | 124.0 | 248 | 0.5475 | 0.9531 |
177
+ | 0.0 | 125.0 | 250 | 0.5475 | 0.9531 |
178
+ | 0.0 | 126.0 | 252 | 0.5476 | 0.9531 |
179
+ | 0.0 | 127.0 | 254 | 0.5477 | 0.9531 |
180
+ | 0.0 | 128.0 | 256 | 0.5478 | 0.9531 |
181
+ | 0.0 | 129.0 | 258 | 0.5479 | 0.9531 |
182
+ | 0.0 | 130.0 | 260 | 0.5480 | 0.9531 |
183
+ | 0.0 | 131.0 | 262 | 0.5480 | 0.9531 |
184
+ | 0.0 | 132.0 | 264 | 0.5481 | 0.9531 |
185
+ | 0.0 | 133.0 | 266 | 0.5482 | 0.9531 |
186
+ | 0.0 | 134.0 | 268 | 0.5483 | 0.9531 |
187
+ | 0.0 | 135.0 | 270 | 0.5484 | 0.9531 |
188
+ | 0.0 | 136.0 | 272 | 0.5485 | 0.9531 |
189
+ | 0.0 | 137.0 | 274 | 0.5486 | 0.9531 |
190
+ | 0.0 | 138.0 | 276 | 0.5487 | 0.9531 |
191
+ | 0.0 | 139.0 | 278 | 0.5487 | 0.9531 |
192
+ | 0.0 | 140.0 | 280 | 0.5488 | 0.9531 |
193
+ | 0.0 | 141.0 | 282 | 0.5489 | 0.9531 |
194
+ | 0.0 | 142.0 | 284 | 0.5490 | 0.9531 |
195
+ | 0.0 | 143.0 | 286 | 0.5491 | 0.9531 |
196
+ | 0.0 | 144.0 | 288 | 0.5491 | 0.9531 |
197
+ | 0.0 | 145.0 | 290 | 0.5492 | 0.9531 |
198
+ | 0.0 | 146.0 | 292 | 0.5493 | 0.9531 |
199
+ | 0.0 | 147.0 | 294 | 0.5494 | 0.9531 |
200
+ | 0.0 | 148.0 | 296 | 0.5494 | 0.9531 |
201
+ | 0.0 | 149.0 | 298 | 0.5495 | 0.9531 |
202
+ | 0.0 | 150.0 | 300 | 0.5496 | 0.9531 |
203
+
204
+
205
+ ### Framework versions
206
+
207
+ - Transformers 4.32.0.dev0
208
+ - Pytorch 2.0.1+cu118
209
+ - Datasets 2.4.0
210
+ - Tokenizers 0.13.3