<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-sst-2-32-13
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5606
- Accuracy: 0.625
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 150
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 2 | 0.6827 | 0.6875 |
| No log | 2.0 | 4 | 0.6826 | 0.6875 |
| No log | 3.0 | 6 | 0.6822 | 0.7031 |
| No log | 4.0 | 8 | 0.6818 | 0.6719 |
| 0.6948 | 5.0 | 10 | 0.6812 | 0.6719 |
| 0.6948 | 6.0 | 12 | 0.6805 | 0.6406 |
| 0.6948 | 7.0 | 14 | 0.6797 | 0.6406 |
| 0.6948 | 8.0 | 16 | 0.6789 | 0.6406 |
| 0.6948 | 9.0 | 18 | 0.6779 | 0.6562 |
| 0.6864 | 10.0 | 20 | 0.6768 | 0.6562 |
| 0.6864 | 11.0 | 22 | 0.6755 | 0.6562 |
| 0.6864 | 12.0 | 24 | 0.6741 | 0.6875 |
| 0.6864 | 13.0 | 26 | 0.6726 | 0.6719 |
| 0.6864 | 14.0 | 28 | 0.6710 | 0.6719 |
| 0.6517 | 15.0 | 30 | 0.6694 | 0.7031 |
| 0.6517 | 16.0 | 32 | 0.6676 | 0.6875 |
| 0.6517 | 17.0 | 34 | 0.6657 | 0.6719 |
| 0.6517 | 18.0 | 36 | 0.6643 | 0.625 |
| 0.6517 | 19.0 | 38 | 0.6636 | 0.6094 |
| 0.6027 | 20.0 | 40 | 0.6642 | 0.5938 |
| 0.6027 | 21.0 | 42 | 0.6632 | 0.5781 |
| 0.6027 | 22.0 | 44 | 0.6607 | 0.5781 |
| 0.6027 | 23.0 | 46 | 0.6582 | 0.6094 |
| 0.6027 | 24.0 | 48 | 0.6562 | 0.6406 |
| 0.4998 | 25.0 | 50 | 0.6546 | 0.6094 |
| 0.4998 | 26.0 | 52 | 0.6503 | 0.5938 |
| 0.4998 | 27.0 | 54 | 0.6450 | 0.6094 |
| 0.4998 | 28.0 | 56 | 0.6395 | 0.6094 |
| 0.4998 | 29.0 | 58 | 0.6362 | 0.5938 |
| 0.3593 | 30.0 | 60 | 0.6380 | 0.5938 |
| 0.3593 | 31.0 | 62 | 0.6361 | 0.5938 |
| 0.3593 | 32.0 | 64 | 0.6348 | 0.5938 |
| 0.3593 | 33.0 | 66 | 0.6327 | 0.625 |
| 0.3593 | 34.0 | 68 | 0.6301 | 0.6094 |
| 0.2483 | 35.0 | 70 | 0.6347 | 0.6094 |
| 0.2483 | 36.0 | 72 | 0.6401 | 0.5938 |
| 0.2483 | 37.0 | 74 | 0.6468 | 0.5781 |
| 0.2483 | 38.0 | 76 | 0.6533 | 0.5781 |
| 0.2483 | 39.0 | 78 | 0.6600 | 0.5938 |
| 0.1735 | 40.0 | 80 | 0.6621 | 0.5938 |
| 0.1735 | 41.0 | 82 | 0.6652 | 0.5938 |
| 0.1735 | 42.0 | 84 | 0.6745 | 0.6094 |
| 0.1735 | 43.0 | 86 | 0.6849 | 0.6094 |
| 0.1735 | 44.0 | 88 | 0.6956 | 0.5938 |
| 0.111 | 45.0 | 90 | 0.7087 | 0.5938 |
| 0.111 | 46.0 | 92 | 0.7238 | 0.5938 |
| 0.111 | 47.0 | 94 | 0.7376 | 0.5938 |
| 0.111 | 48.0 | 96 | 0.7506 | 0.5938 |
| 0.111 | 49.0 | 98 | 0.7646 | 0.6094 |
| 0.0691 | 50.0 | 100 | 0.7817 | 0.6094 |
| 0.0691 | 51.0 | 102 | 0.8015 | 0.625 |
| 0.0691 | 52.0 | 104 | 0.8277 | 0.625 |
| 0.0691 | 53.0 | 106 | 0.8582 | 0.625 |
| 0.0691 | 54.0 | 108 | 0.8849 | 0.625 |
| 0.0395 | 55.0 | 110 | 0.9094 | 0.625 |
| 0.0395 | 56.0 | 112 | 0.9309 | 0.625 |
| 0.0395 | 57.0 | 114 | 0.9525 | 0.625 |
| 0.0395 | 58.0 | 116 | 0.9740 | 0.6094 |
| 0.0395 | 59.0 | 118 | 0.9959 | 0.6094 |
| 0.0213 | 60.0 | 120 | 1.0209 | 0.6094 |
| 0.0213 | 61.0 | 122 | 1.0452 | 0.625 |
| 0.0213 | 62.0 | 124 | 1.0680 | 0.625 |
| 0.0213 | 63.0 | 126 | 1.0908 | 0.625 |
| 0.0213 | 64.0 | 128 | 1.1149 | 0.6094 |
| 0.0129 | 65.0 | 130 | 1.1381 | 0.625 |
| 0.0129 | 66.0 | 132 | 1.1590 | 0.625 |
| 0.0129 | 67.0 | 134 | 1.1787 | 0.625 |
| 0.0129 | 68.0 | 136 | 1.1960 | 0.625 |
| 0.0129 | 69.0 | 138 | 1.2125 | 0.625 |
| 0.0093 | 70.0 | 140 | 1.2267 | 0.625 |
| 0.0093 | 71.0 | 142 | 1.2399 | 0.625 |
| 0.0093 | 72.0 | 144 | 1.2516 | 0.625 |
| 0.0093 | 73.0 | 146 | 1.2626 | 0.625 |
| 0.0093 | 74.0 | 148 | 1.2726 | 0.6406 |
| 0.0071 | 75.0 | 150 | 1.2825 | 0.6406 |
| 0.0071 | 76.0 | 152 | 1.2921 | 0.625 |
| 0.0071 | 77.0 | 154 | 1.3016 | 0.625 |
| 0.0071 | 78.0 | 156 | 1.3104 | 0.625 |
| 0.0071 | 79.0 | 158 | 1.3177 | 0.625 |
| 0.0059 | 80.0 | 160 | 1.3243 | 0.625 |
| 0.0059 | 81.0 | 162 | 1.3311 | 0.625 |
| 0.0059 | 82.0 | 164 | 1.3377 | 0.625 |
| 0.0059 | 83.0 | 166 | 1.3446 | 0.625 |
| 0.0059 | 84.0 | 168 | 1.3519 | 0.625 |
| 0.0051 | 85.0 | 170 | 1.3590 | 0.625 |
| 0.0051 | 86.0 | 172 | 1.3662 | 0.625 |
| 0.0051 | 87.0 | 174 | 1.3731 | 0.625 |
| 0.0051 | 88.0 | 176 | 1.3801 | 0.625 |
| 0.0051 | 89.0 | 178 | 1.3867 | 0.625 |
| 0.0045 | 90.0 | 180 | 1.3929 | 0.625 |
| 0.0045 | 91.0 | 182 | 1.3988 | 0.625 |
| 0.0045 | 92.0 | 184 | 1.4048 | 0.625 |
| 0.0045 | 93.0 | 186 | 1.4110 | 0.625 |
| 0.0045 | 94.0 | 188 | 1.4171 | 0.625 |
| 0.0042 | 95.0 | 190 | 1.4231 | 0.625 |
| 0.0042 | 96.0 | 192 | 1.4290 | 0.625 |
| 0.0042 | 97.0 | 194 | 1.4346 | 0.625 |
| 0.0042 | 98.0 | 196 | 1.4401 | 0.625 |
| 0.0042 | 99.0 | 198 | 1.4454 | 0.625 |
| 0.0037 | 100.0 | 200 | 1.4506 | 0.625 |
| 0.0037 | 101.0 | 202 | 1.4555 | 0.625 |
| 0.0037 | 102.0 | 204 | 1.4604 | 0.625 |
| 0.0037 | 103.0 | 206 | 1.4650 | 0.625 |
| 0.0037 | 104.0 | 208 | 1.4690 | 0.625 |
| 0.0034 | 105.0 | 210 | 1.4728 | 0.625 |
| 0.0034 | 106.0 | 212 | 1.4765 | 0.625 |
| 0.0034 | 107.0 | 214 | 1.4802 | 0.625 |
| 0.0034 | 108.0 | 216 | 1.4836 | 0.625 |
| 0.0034 | 109.0 | 218 | 1.4870 | 0.625 |
| 0.0033 | 110.0 | 220 | 1.4903 | 0.625 |
| 0.0033 | 111.0 | 222 | 1.4936 | 0.625 |
| 0.0033 | 112.0 | 224 | 1.4969 | 0.625 |
| 0.0033 | 113.0 | 226 | 1.5002 | 0.625 |
| 0.0033 | 114.0 | 228 | 1.5036 | 0.625 |
| 0.0031 | 115.0 | 230 | 1.5069 | 0.625 |
| 0.0031 | 116.0 | 232 | 1.5100 | 0.625 |
| 0.0031 | 117.0 | 234 | 1.5130 | 0.625 |
| 0.0031 | 118.0 | 236 | 1.5161 | 0.625 |
| 0.0031 | 119.0 | 238 | 1.5190 | 0.625 |
| 0.003 | 120.0 | 240 | 1.5216 | 0.625 |
| 0.003 | 121.0 | 242 | 1.5242 | 0.625 |
| 0.003 | 122.0 | 244 | 1.5269 | 0.625 |
| 0.003 | 123.0 | 246 | 1.5295 | 0.625 |
| 0.003 | 124.0 | 248 | 1.5321 | 0.625 |
| 0.0028 | 125.0 | 250 | 1.5345 | 0.625 |
| 0.0028 | 126.0 | 252 | 1.5367 | 0.625 |
| 0.0028 | 127.0 | 254 | 1.5386 | 0.625 |
| 0.0028 | 128.0 | 256 | 1.5405 | 0.625 |
| 0.0028 | 129.0 | 258 | 1.5422 | 0.625 |
| 0.0027 | 130.0 | 260 | 1.5438 | 0.625 |
| 0.0027 | 131.0 | 262 | 1.5453 | 0.625 |
| 0.0027 | 132.0 | 264 | 1.5468 | 0.625 |
| 0.0027 | 133.0 | 266 | 1.5482 | 0.625 |
| 0.0027 | 134.0 | 268 | 1.5495 | 0.625 |
| 0.0027 | 135.0 | 270 | 1.5507 | 0.625 |
| 0.0027 | 136.0 | 272 | 1.5518 | 0.625 |
| 0.0027 | 137.0 | 274 | 1.5529 | 0.625 |
| 0.0027 | 138.0 | 276 | 1.5539 | 0.625 |
| 0.0027 | 139.0 | 278 | 1.5549 | 0.625 |
| 0.0026 | 140.0 | 280 | 1.5557 | 0.625 |
| 0.0026 | 141.0 | 282 | 1.5565 | 0.625 |
| 0.0026 | 142.0 | 284 | 1.5573 | 0.625 |
| 0.0026 | 143.0 | 286 | 1.5580 | 0.625 |
| 0.0026 | 144.0 | 288 | 1.5587 | 0.625 |
| 0.0025 | 145.0 | 290 | 1.5593 | 0.625 |
| 0.0025 | 146.0 | 292 | 1.5597 | 0.625 |
| 0.0025 | 147.0 | 294 | 1.5601 | 0.625 |
| 0.0025 | 148.0 | 296 | 1.5603 | 0.625 |
| 0.0025 | 149.0 | 298 | 1.5605 | 0.625 |
| 0.0026 | 150.0 | 300 | 1.5606 | 0.625 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.4.0
- Tokenizers 0.13.3
