Downloads · 30 days
11
9% of all-time downloads
gc394/da_distilbert
da_distilbert is a fill-mask model from gc394. 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
11
9% of all-time downloads
All-time downloads
125
Public
Parameters
67M
15.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors268 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 |
|---|---|---|---|
| No log | 1.0 | 130 | 2.0998 |
| No log | 2.0 | 260 | 1.9483 |
| No log | 3.0 | 390 | 1.8376 |
| 2.1352 | 4.0 | 520 | 1.8386 |
| 2.1352 | 5.0 | 650 | 1.7713 |
| 2.1352 | 6.0 | 780 | 1.7591 |
| 2.1352 | 7.0 | 910 | 1.7380 |
| 1.8059 | 8.0 | 1040 | 1.6942 |
| 1.8059 | 9.0 | 1170 | 1.6574 |
| 1.8059 | 10.0 | 1300 | 1.6882 |
| 1.8059 | 11.0 | 1430 | 1.6419 |
| 1.7023 | 12.0 | 1560 | 1.6442 |
| 1.7023 | 13.0 | 1690 | 1.6709 |
| 1.7023 | 14.0 | 1820 | 1.6300 |
| 1.7023 | 15.0 | 1950 | 1.6165 |