Downloads · 30 days
4
10% of all-time downloads
bert-base-uncased-lm
iewaij/bert-base-uncased-lm
bert-base-uncased-lm is a fill-mask model from iewaij. 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. --
All-time downloads
39
Public
Repo size
438 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Aug 26, 2022
- Updated
- Aug 26, 2022
- SHA
- b8e0ed74
Try a prompt
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-lm-all
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8646
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6625 | 1.0 | 1194 | 1.3270 |
| 1.3001 | 2.0 | 2388 | 1.1745 |
| 1.1694 | 3.0 | 3582 | 1.1133 |
| 1.0901 | 4.0 | 4776 | 1.0547 |
| 1.0309 | 5.0 | 5970 | 0.9953 |
| 0.9842 | 6.0 | 7164 | 0.9997 |
| 0.9396 | 7.0 | 8358 | 0.9707 |
| 0.8997 | 8.0 | 9552 | 0.9324 |
| 0.8633 | 9.0 | 10746 | 0.9145 |
| 0.8314 | 10.0 | 11940 | 0.9047 |
| 0.812 | 11.0 | 13134 | 0.8954 |
| 0.7841 | 12.0 | 14328 | 0.8940 |
| 0.7616 | 13.0 | 15522 | 0.8555 |
| 0.7508 | 14.0 | 16716 | 0.8711 |
| 0.7333 | 15.0 | 17910 | 0.8351 |
| 0.7299 | 16.0 | 19104 | 0.8646 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Aug 26, 2022
- Updated
- Aug 26, 2022