Downloads · 30 days
17
28% of all-time downloads
Billwzl/20split_dataset_version2
20split_dataset_version2 is a fill-mask model from Billwzl. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
17
28% of all-time downloads
All-time downloads
60
Public
Repo size
804 MB
Likes
0
Public
Click a slice to open those files.
.bin268 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7621 | 1.0 | 11851 | 2.5216 |
| 2.5466 | 2.0 | 23702 | 2.4157 |
| 2.4505 | 3.0 | 35553 | 2.3592 |
| 2.3798 | 4.0 | 47404 | 2.3028 |
| 2.3178 | 5.0 | 59255 | 2.2768 |
| 2.272 | 6.0 | 71106 | 2.2366 |
| 2.2323 | 7.0 | 82957 | 2.2128 |
| 2.1928 | 8.0 | 94808 | 2.1797 |
| 2.157 | 9.0 | 106659 | 2.1667 |
| 2.1292 | 10.0 | 118510 | 2.1392 |
| 2.0978 | 11.0 | 130361 | 2.1280 |
| 2.0725 | 12.0 | 142212 | 2.1106 |
| 2.052 | 13.0 | 154063 | 2.0944 |
| 2.0268 | 14.0 | 165914 | 2.0804 |
| 2.0121 | 15.0 | 177765 | 2.0698 |
| 1.9997 | 16.0 | 189616 | 2.0626 |