Downloads · 30 days
4
11% of all-time downloads
jojoUla/bert-large-cased-finetuned-lowR100-0-cased-DA-20
bert-large-cased-finetuned-lowR100-0-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
4
11% of all-time downloads
All-time downloads
35
Public
Repo size
4 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 |
|---|---|---|---|
| No log | 1.0 | 1 | 1.8723 |
| 0.732 | 2.0 | 2 | 3.5381 |
| 0.732 | 3.0 | 3 | 2.1417 |
| 0.7987 | 4.0 | 4 | 2.2899 |
| 0.7987 | 5.0 | 5 | 1.7517 |
| 0.9115 | 6.0 | 6 | 2.3830 |
| 0.9115 | 7.0 | 7 | 3.4545 |
| 0.9239 | 8.0 | 8 | 2.7875 |
| 0.9239 | 9.0 | 9 | 2.1550 |
| 1.1331 | 10.0 | 10 | 1.9010 |
| 1.1331 | 11.0 | 11 | 2.6686 |
| 1.1203 | 12.0 | 12 | 1.8346 |
| 1.1203 | 13.0 | 13 | 2.3677 |
| 0.9392 | 14.0 | 14 | 1.3718 |
| 0.9392 | 15.0 | 15 | 2.2553 |
| 0.8844 | 16.0 | 16 | 3.4245 |
| 0.8844 | 17.0 | 17 | 2.5895 |
| 0.8565 | 18.0 | 18 | 2.7765 |
| 0.8565 | 19.0 | 19 | 1.7891 |
| 0.9602 | 20.0 | 20 | 2.0496 |