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 | 2.1700 | 0.7140 | 0.6107 |
| 3.0791 | 2.0 | 828 | 1.8606 | 0.6674 | 0.5934 |
| 2.2628 | 3.0 | 1242 | 1.6506 | 0.6244 | 0.5875 |
| 1.9009 | 4.0 | 1656 | 1.5491 | 0.5907 | 0.5741 |
| 1.7106 | 5.0 | 2070 | 1.3944 | 0.6616 | 0.6175 |
| 1.7106 | 6.0 | 2484 | 1.2659 | 0.7093 | 0.6405 |
| 1.4298 | 7.0 | 2898 | 1.0533 | 0.7128 | 0.6614 |
| 1.088 | 8.0 | 3312 | 0.8825 | 0.7128 | 0.6797 |
| 0.8339 | 9.0 | 3726 | 0.7896 | 0.7267 | 0.7034 |
| 0.6551 | 10.0 | 4140 | 0.7736 | 0.7360 | 0.7306 |
| 0.5637 | 11.0 | 4554 | 0.7400 | 0.8070 | 0.8025 |
| 0.5637 | 12.0 | 4968 | 0.7152 | 0.8035 | 0.8055 |
| 0.4821 | 13.0 | 5382 | 0.7421 | 0.8070 | 0.8072 |
| 0.4184 | 14.0 | 5796 | 0.7307 | 0.8023 | 0.8038 |
