This model is a fine-tuned version of
distilbert-base-uncased on the None dataset.
It achieves the following results on the evaluation set:
|
|:-------------:|:-----:|:----:|:---------------:|:------------:|:------:|
| No log | 1.0 | 414 | 8.8075 | 0.2791 | 0.1218 |
| 9.1738 | 2.0 | 828 | 7.7356 | 0.2814 | 0.1286 |
| 7.3001 | 3.0 | 1242 | 6.6748 | 0.2814 | 0.1346 |
| 6.0371 | 4.0 | 1656 | 5.6375 | 0.3012 | 0.1810 |
| 4.898 | 5.0 | 2070 | 4.6651 | 0.3488 | 0.2830 |
| 4.898 | 6.0 | 2484 | 3.7891 | 0.3919 | 0.3600 |
| 3.8534 | 7.0 | 2898 | 3.0231 | 0.4326 | 0.4271 |
| 2.9318 | 8.0 | 3312 | 2.3765 | 0.4767 | 0.4881 |
| 2.2018 | 9.0 | 3726 | 1.8644 | 0.5163 | 0.5362 |
| 1.6561 | 10.0 | 4140 | 1.5070 | 0.5547 | 0.5772 |
| 1.3598 | 11.0 | 4554 | 1.3376 | 0.5965 | 0.6162 |
| 1.3598 | 12.0 | 4968 | 1.3128 | 0.5895 | 0.6097 |
| 1.2704 | 13.0 | 5382 | 1.0599 | 0.6337 | 0.6515 |
| 1.1448 | 14.0 | 5796 | 0.9554 | 0.6570 | 0.6723 |
| 0.9513 | 15.0 | 6210 | 0.8642 | 0.6965 | 0.7018 |
| 0.8368 | 16.0 | 6624 | 0.8353 | 0.7070 | 0.7136 |
| 0.7607 | 17.0 | 7038 | 0.8036 | 0.7558 | 0.7552 |
| 0.7607 | 18.0 | 7452 | 0.7971 | 0.7919 | 0.7840 |
| 0.6982 | 19.0 | 7866 | 0.8153 | 0.7709 | 0.7719 |
| 0.6449 | 20.0 | 8280 | 0.7852 | 0.7919 | 0.7851 |
| 0.5748 | 21.0 | 8694 | 0.7964 | 0.7849 | 0.7801 |
| 0.545 | 22.0 | 9108 | 0.8217 | 0.7965 | 0.7861 |
