Downloads · 30 days
9
3% of all-time downloads
Billwzl/20split_dataset_version1
20split_dataset_version1 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
9
3% of all-time downloads
All-time downloads
332
Public
Repo size
536 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 |
|---|---|---|---|
| 2.7475 | 1.0 | 11851 | 2.5194 |
| 2.5528 | 2.0 | 23702 | 2.4191 |
| 2.4649 | 3.0 | 35553 | 2.3646 |
| 2.4038 | 4.0 | 47404 | 2.3289 |
| 2.3632 | 5.0 | 59255 | 2.2922 |
| 2.3273 | 6.0 | 71106 | 2.2739 |
| 2.2964 | 7.0 | 82957 | 2.2494 |
| 2.2732 | 8.0 | 94808 | 2.2217 |
| 2.2526 | 9.0 | 106659 | 2.2149 |
| 2.2369 | 10.0 | 118510 | 2.2029 |
| 2.222 | 11.0 | 130361 | 2.2020 |
| 2.2135 | 12.0 | 142212 | 2.1942 |