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 | 0.3913 | 0.8477 | 0.8405 |
| 0.5047 | 2.0 | 828 | 0.3886 | 0.8314 | 0.8329 |
| 0.402 | 3.0 | 1242 | 0.3704 | 0.8547 | 0.8478 |
| 0.3722 | 4.0 | 1656 | 0.3670 | 0.85 | 0.8467 |
| 0.339 | 5.0 | 2070 | 0.3816 | 0.8488 | 0.8486 |
| 0.339 | 6.0 | 2484 | 0.4015 | 0.8477 | 0.8392 |