Downloads · 30 days
6
1% of all-time downloads
bert-tagalog-base-uncased-WWM-ner-v1
scostiniano/bert-tagalog-base-uncased-WWM-ner-v1
bert-tagalog-base-uncased-WWM-ner-v1 is a token classification model from scostiniano. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as gpl-3.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
432
Public
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin434 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- gpl-3.0
- Model type
- bert
- Access
- Public
- Created
- Nov 24, 2022
- Updated
- Nov 24, 2022
- SHA
- 93a887b6
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-tagalog-base-uncased-WWM-ner-v1
This model is a fine-tuned version of jcblaise/bert-tagalog-base-uncased-WWM on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2838
- Precision: 0.9280
- Recall: 0.9153
- F1: 0.9216
- Accuracy: 0.9509
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 205 | 0.4812 | 0.6267 | 0.6367 | 0.6317 | 0.8502 |
| No log | 2.0 | 410 | 0.2683 | 0.8322 | 0.8289 | 0.8305 | 0.9228 |
| 0.4348 | 3.0 | 615 | 0.2377 | 0.9020 | 0.8846 | 0.8932 | 0.9398 |
| 0.4348 | 4.0 | 820 | 0.2566 | 0.8906 | 0.8977 | 0.8941 | 0.9439 |
| 0.0549 | 5.0 | 1025 | 0.2587 | 0.9249 | 0.9034 | 0.9140 | 0.9469 |
| 0.0549 | 6.0 | 1230 | 0.2616 | 0.8988 | 0.9136 | 0.9061 | 0.9469 |
| 0.0549 | 7.0 | 1435 | 0.2716 | 0.9102 | 0.9164 | 0.9133 | 0.9497 |
| 0.011 | 8.0 | 1640 | 0.2929 | 0.9317 | 0.9147 | 0.9231 | 0.9507 |
| 0.011 | 9.0 | 1845 | 0.2819 | 0.9280 | 0.9153 | 0.9216 | 0.9512 |
| 0.0043 | 10.0 | 2050 | 0.2838 | 0.9280 | 0.9153 | 0.9216 | 0.9509 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- gpl-3.0
- Created
- Nov 24, 2022
- Updated
- Nov 24, 2022