Downloads · 30 days
10
4% of all-time downloads
Xessen/bert-turkish-from-scratch-3
bert-turkish-from-scratch-3 is a fill-mask model from Xessen. Use it when you need the model to fill a missing word. It is set up for transformers.
probably proofread and complete it, then remove this comment. --
Downloads · 30 days
10
4% of all-time downloads
All-time downloads
259
Public
Repo size
543 MB
Likes
0
Public
Click a slice to open those files.
.h5543 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of on an unknown 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:
| Train Loss | Train Accuracy | Epoch |
|---|---|---|
| 0.5533 | 0.9384 | 0 |
| 0.2784 | 0.9611 | 1 |
| 0.1598 | 0.9801 | 2 |
| 0.1423 | 0.9827 | 3 |
| 0.1348 | 0.9838 | 4 |
| 0.1292 | 0.9841 | 5 |
| 0.1238 | 0.9844 | 6 |
| 0.1186 | 0.9848 | 7 |
| 0.1145 | 0.9851 | 8 |
| 0.1112 | 0.9853 | 9 |