Downloads · 30 days
7
16% of all-time downloads
jojoUla/bert-large-cased-finetuned-low100-0-cased-DA-20
bert-large-cased-finetuned-low100-0-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
7
16% of all-time downloads
All-time downloads
43
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 |
|---|---|---|---|
| 3.1166 | 1.0 | 1 | 2.8426 |
| 3.3165 | 2.0 | 2 | 3.5737 |
| 2.9474 | 3.0 | 3 | 4.5615 |
| 2.8754 | 4.0 | 4 | 3.1920 |
| 2.5889 | 5.0 | 5 | 1.3226 |
| 2.6482 | 6.0 | 6 | 2.0844 |
| 3.2225 | 7.0 | 7 | 2.7027 |
| 2.5846 | 8.0 | 8 | 1.8894 |
| 2.5211 | 9.0 | 9 | 3.6235 |
| 2.8645 | 10.0 | 10 | 2.7545 |
| 2.2606 | 11.0 | 11 | 2.2238 |
| 2.3737 | 12.0 | 12 | 1.8809 |
| 2.5521 | 13.0 | 13 | 2.3081 |
| 2.4012 | 14.0 | 14 | 2.0904 |
| 2.1854 | 15.0 | 15 | 1.5814 |
| 2.1068 | 16.0 | 16 | 2.8540 |
| 2.4657 | 17.0 | 17 | 2.3973 |
| 2.4053 | 18.0 | 18 | 2.5062 |
| 1.813 | 19.0 | 19 | 2.7394 |
| 2.1094 | 20.0 | 20 | 1.8084 |