<!-- 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-2-64-13
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: 1.1906
- Accuracy: 0.7812
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 | 4 | 0.6896 | 0.6094 |
| No log | 2.0 | 8 | 0.6884 | 0.6094 |
| 0.7032 | 3.0 | 12 | 0.6865 | 0.6016 |
| 0.7032 | 4.0 | 16 | 0.6836 | 0.6172 |
| 0.6985 | 5.0 | 20 | 0.6801 | 0.6484 |
| 0.6985 | 6.0 | 24 | 0.6758 | 0.6094 |
| 0.6985 | 7.0 | 28 | 0.6702 | 0.6641 |
| 0.6762 | 8.0 | 32 | 0.6630 | 0.7109 |
| 0.6762 | 9.0 | 36 | 0.6541 | 0.6875 |
| 0.6336 | 10.0 | 40 | 0.6457 | 0.6094 |
| 0.6336 | 11.0 | 44 | 0.6332 | 0.6406 |
| 0.6336 | 12.0 | 48 | 0.6204 | 0.6484 |
| 0.574 | 13.0 | 52 | 0.6191 | 0.625 |
| 0.574 | 14.0 | 56 | 0.6103 | 0.625 |
| 0.4443 | 15.0 | 60 | 0.5704 | 0.6719 |
| 0.4443 | 16.0 | 64 | 0.5639 | 0.6562 |
| 0.4443 | 17.0 | 68 | 0.5667 | 0.6875 |
| 0.3245 | 18.0 | 72 | 0.5509 | 0.7031 |
| 0.3245 | 19.0 | 76 | 0.5315 | 0.7109 |
| 0.2226 | 20.0 | 80 | 0.5254 | 0.7266 |
| 0.2226 | 21.0 | 84 | 0.5252 | 0.7578 |
| 0.2226 | 22.0 | 88 | 0.5177 | 0.7422 |
| 0.1465 | 23.0 | 92 | 0.5220 | 0.7422 |
| 0.1465 | 24.0 | 96 | 0.5320 | 0.7422 |
| 0.0857 | 25.0 | 100 | 0.5444 | 0.75 |
| 0.0857 | 26.0 | 104 | 0.5613 | 0.75 |
| 0.0857 | 27.0 | 108 | 0.5824 | 0.7578 |
| 0.0485 | 28.0 | 112 | 0.6097 | 0.7656 |
| 0.0485 | 29.0 | 116 | 0.6377 | 0.7578 |
| 0.0251 | 30.0 | 120 | 0.6674 | 0.7656 |
| 0.0251 | 31.0 | 124 | 0.6924 | 0.7578 |
| 0.0251 | 32.0 | 128 | 0.7150 | 0.7656 |
| 0.0146 | 33.0 | 132 | 0.7351 | 0.7656 |
| 0.0146 | 34.0 | 136 | 0.7557 | 0.7656 |
| 0.01 | 35.0 | 140 | 0.7747 | 0.7656 |
| 0.01 | 36.0 | 144 | 0.7929 | 0.7656 |
| 0.01 | 37.0 | 148 | 0.8073 | 0.7578 |
| 0.0075 | 38.0 | 152 | 0.8195 | 0.7734 |
| 0.0075 | 39.0 | 156 | 0.8316 | 0.7656 |
| 0.0061 | 40.0 | 160 | 0.8418 | 0.7656 |
| 0.0061 | 41.0 | 164 | 0.8550 | 0.7656 |
| 0.0061 | 42.0 | 168 | 0.8673 | 0.7656 |
| 0.005 | 43.0 | 172 | 0.8791 | 0.7734 |
| 0.005 | 44.0 | 176 | 0.8911 | 0.7812 |
| 0.0044 | 45.0 | 180 | 0.9022 | 0.7734 |
| 0.0044 | 46.0 | 184 | 0.9113 | 0.7734 |
| 0.0044 | 47.0 | 188 | 0.9195 | 0.7734 |
| 0.0039 | 48.0 | 192 | 0.9268 | 0.7734 |
| 0.0039 | 49.0 | 196 | 0.9340 | 0.7656 |
| 0.0034 | 50.0 | 200 | 0.9405 | 0.7656 |
| 0.0034 | 51.0 | 204 | 0.9480 | 0.7656 |
| 0.0034 | 52.0 | 208 | 0.9575 | 0.7656 |
| 0.0031 | 53.0 | 212 | 0.9649 | 0.7656 |
| 0.0031 | 54.0 | 216 | 0.9711 | 0.7656 |
| 0.0028 | 55.0 | 220 | 0.9775 | 0.7656 |
| 0.0028 | 56.0 | 224 | 0.9822 | 0.7656 |
| 0.0028 | 57.0 | 228 | 0.9865 | 0.7578 |
| 0.0025 | 58.0 | 232 | 0.9903 | 0.7656 |
| 0.0025 | 59.0 | 236 | 0.9945 | 0.7656 |
| 0.0024 | 60.0 | 240 | 0.9989 | 0.7656 |
| 0.0024 | 61.0 | 244 | 1.0031 | 0.7656 |
| 0.0024 | 62.0 | 248 | 1.0074 | 0.7656 |
| 0.0022 | 63.0 | 252 | 1.0114 | 0.7734 |
| 0.0022 | 64.0 | 256 | 1.0152 | 0.7734 |
| 0.0021 | 65.0 | 260 | 1.0186 | 0.7812 |
| 0.0021 | 66.0 | 264 | 1.0223 | 0.7734 |
| 0.0021 | 67.0 | 268 | 1.0254 | 0.7812 |
| 0.0019 | 68.0 | 272 | 1.0290 | 0.7812 |
| 0.0019 | 69.0 | 276 | 1.0333 | 0.7812 |
| 0.0019 | 70.0 | 280 | 1.0378 | 0.7812 |
| 0.0019 | 71.0 | 284 | 1.0419 | 0.7812 |
| 0.0019 | 72.0 | 288 | 1.0464 | 0.7812 |
| 0.0017 | 73.0 | 292 | 1.0507 | 0.7812 |
| 0.0017 | 74.0 | 296 | 1.0549 | 0.7812 |
| 0.0016 | 75.0 | 300 | 1.0586 | 0.7812 |
| 0.0016 | 76.0 | 304 | 1.0618 | 0.7812 |
| 0.0016 | 77.0 | 308 | 1.0650 | 0.7812 |
| 0.0015 | 78.0 | 312 | 1.0684 | 0.7812 |
| 0.0015 | 79.0 | 316 | 1.0719 | 0.7812 |
| 0.0015 | 80.0 | 320 | 1.0752 | 0.7812 |
| 0.0015 | 81.0 | 324 | 1.0784 | 0.7812 |
| 0.0015 | 82.0 | 328 | 1.0815 | 0.7891 |
| 0.0014 | 83.0 | 332 | 1.0845 | 0.7891 |
| 0.0014 | 84.0 | 336 | 1.0877 | 0.7891 |
| 0.0014 | 85.0 | 340 | 1.0909 | 0.7891 |
| 0.0014 | 86.0 | 344 | 1.0940 | 0.7891 |
| 0.0014 | 87.0 | 348 | 1.0971 | 0.7891 |
| 0.0013 | 88.0 | 352 | 1.1001 | 0.7891 |
| 0.0013 | 89.0 | 356 | 1.1030 | 0.7891 |
| 0.0012 | 90.0 | 360 | 1.1057 | 0.7891 |
| 0.0012 | 91.0 | 364 | 1.1088 | 0.7891 |
| 0.0012 | 92.0 | 368 | 1.1120 | 0.7891 |
| 0.0012 | 93.0 | 372 | 1.1151 | 0.7891 |
| 0.0012 | 94.0 | 376 | 1.1183 | 0.7891 |
| 0.0011 | 95.0 | 380 | 1.1211 | 0.7891 |
| 0.0011 | 96.0 | 384 | 1.1238 | 0.7891 |
| 0.0011 | 97.0 | 388 | 1.1267 | 0.7891 |
| 0.0011 | 98.0 | 392 | 1.1297 | 0.7891 |
| 0.0011 | 99.0 | 396 | 1.1324 | 0.7891 |
| 0.0011 | 100.0 | 400 | 1.1349 | 0.7891 |
| 0.0011 | 101.0 | 404 | 1.1373 | 0.7891 |
| 0.0011 | 102.0 | 408 | 1.1395 | 0.7891 |
| 0.001 | 103.0 | 412 | 1.1415 | 0.7891 |
| 0.001 | 104.0 | 416 | 1.1433 | 0.7891 |
| 0.001 | 105.0 | 420 | 1.1451 | 0.7891 |
| 0.001 | 106.0 | 424 | 1.1471 | 0.7812 |
| 0.001 | 107.0 | 428 | 1.1491 | 0.7812 |
| 0.001 | 108.0 | 432 | 1.1512 | 0.7812 |
| 0.001 | 109.0 | 436 | 1.1531 | 0.7812 |
| 0.001 | 110.0 | 440 | 1.1549 | 0.7812 |
| 0.001 | 111.0 | 444 | 1.1566 | 0.7812 |
| 0.001 | 112.0 | 448 | 1.1583 | 0.7812 |
| 0.001 | 113.0 | 452 | 1.1598 | 0.7812 |
| 0.001 | 114.0 | 456 | 1.1613 | 0.7812 |
| 0.0009 | 115.0 | 460 | 1.1628 | 0.7812 |
| 0.0009 | 116.0 | 464 | 1.1642 | 0.7812 |
| 0.0009 | 117.0 | 468 | 1.1657 | 0.7812 |
| 0.0009 | 118.0 | 472 | 1.1672 | 0.7812 |
| 0.0009 | 119.0 | 476 | 1.1686 | 0.7812 |
| 0.0008 | 120.0 | 480 | 1.1700 | 0.7812 |
| 0.0008 | 121.0 | 484 | 1.1713 | 0.7812 |
| 0.0008 | 122.0 | 488 | 1.1727 | 0.7812 |
| 0.0009 | 123.0 | 492 | 1.1742 | 0.7812 |
| 0.0009 | 124.0 | 496 | 1.1757 | 0.7812 |
| 0.0009 | 125.0 | 500 | 1.1770 | 0.7812 |
| 0.0009 | 126.0 | 504 | 1.1783 | 0.7812 |
| 0.0009 | 127.0 | 508 | 1.1795 | 0.7812 |
| 0.0008 | 128.0 | 512 | 1.1805 | 0.7812 |
| 0.0008 | 129.0 | 516 | 1.1815 | 0.7812 |
| 0.0009 | 130.0 | 520 | 1.1823 | 0.7812 |
| 0.0009 | 131.0 | 524 | 1.1832 | 0.7812 |
| 0.0009 | 132.0 | 528 | 1.1840 | 0.7812 |
| 0.0008 | 133.0 | 532 | 1.1847 | 0.7812 |
| 0.0008 | 134.0 | 536 | 1.1854 | 0.7812 |
| 0.0008 | 135.0 | 540 | 1.1861 | 0.7812 |
| 0.0008 | 136.0 | 544 | 1.1867 | 0.7812 |
| 0.0008 | 137.0 | 548 | 1.1872 | 0.7812 |
| 0.0008 | 138.0 | 552 | 1.1876 | 0.7812 |
| 0.0008 | 139.0 | 556 | 1.1881 | 0.7812 |
| 0.0008 | 140.0 | 560 | 1.1885 | 0.7812 |
| 0.0008 | 141.0 | 564 | 1.1888 | 0.7812 |
| 0.0008 | 142.0 | 568 | 1.1891 | 0.7812 |
| 0.0008 | 143.0 | 572 | 1.1895 | 0.7812 |
| 0.0008 | 144.0 | 576 | 1.1897 | 0.7812 |
| 0.0008 | 145.0 | 580 | 1.1900 | 0.7812 |
| 0.0008 | 146.0 | 584 | 1.1902 | 0.7812 |
| 0.0008 | 147.0 | 588 | 1.1904 | 0.7812 |
| 0.0008 | 148.0 | 592 | 1.1905 | 0.7812 |
| 0.0008 | 149.0 | 596 | 1.1906 | 0.7812 |
| 0.0008 | 150.0 | 600 | 1.1906 | 0.7812 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.4.0
- Tokenizers 0.13.3
