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 | 0.3907 | 0.8488 | 0.8412 |
| 0.5041 | 2.0 | 828 | 0.3855 | 0.8291 | 0.8310 |
| 0.4028 | 3.0 | 1242 | 0.3643 | 0.8558 | 0.8500 |
| 0.3734 | 4.0 | 1656 | 0.3622 | 0.8535 | 0.8510 |
| 0.3381 | 5.0 | 2070 | 0.3859 | 0.8395 | 0.8399 |
| 0.3381 | 6.0 | 2484 | 0.4044 | 0.8512 | 0.8443 |