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 | 0.3916 | 0.8384 | 0.8280 |
| 0.5073 | 2.0 | 828 | 0.3771 | 0.8430 | 0.8427 |
| 0.405 | 3.0 | 1242 | 0.3609 | 0.8628 | 0.8582 |
| 0.3764 | 4.0 | 1656 | 0.3601 | 0.8547 | 0.8489 |
| 0.3444 | 5.0 | 2070 | 0.3787 | 0.8488 | 0.8470 |
| 0.3444 | 6.0 | 2484 | 0.3927 | 0.8442 | 0.8340 |