Downloads · 30 days
6
13% of all-time downloads
jojoUla/bert-large-cased-finetuned-low10-0-cased-DA-20
bert-large-cased-finetuned-low10-0-cased-DA-20 is a fill-mask model from jojoUla. 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
6
13% of all-time downloads
All-time downloads
45
Public
Repo size
2.7 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of bert-large-cased 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:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9248 | 1.0 | 1 | 1.0349 |
| 1.9585 | 2.0 | 2 | 1.1866 |
| 3.2777 | 3.0 | 3 | 1.4471 |
| 0.8177 | 4.0 | 4 | 3.6448 |
| 0.8142 | 5.0 | 5 | 3.3777 |
| 1.2679 | 6.0 | 6 | 3.3755 |
| 3.0205 | 7.0 | 7 | 1.4410 |
| 1.902 | 8.0 | 8 | 2.0879 |
| 1.5332 | 9.0 | 9 | 1.2120 |
| 1.2021 | 10.0 | 10 | 1.3473 |
| 1.017 | 11.0 | 11 | 1.7179 |
| 0.9292 | 12.0 | 12 | 4.3621 |
| 2.6595 | 13.0 | 13 | 0.5600 |
| 1.2934 | 14.0 | 14 | 0.5098 |
| 0.3334 | 15.0 | 15 | 2.2589 |
| 0.778 | 16.0 | 16 | 1.4632 |
| 0.9396 | 17.0 | 17 | 0.8874 |
| 1.8881 | 18.0 | 18 | 3.0849 |
| 0.9685 | 19.0 | 19 | 4.1051 |
| 1.4742 | 20.0 | 20 | 1.4036 |