Downloads · 30 days
20
48% of all-time downloads
BEREL-finetuned-DSS-pos_cls
yonatanlou/BEREL-finetuned-DSS-pos_cls
BEREL-finetuned-DSS-pos_cls is a token classification model from yonatanlou. Use it when you need labels on individual words, such as names. 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
42
Public
Parameters
184M
5.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors735 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Dec 15, 2024
- Updated
- Dec 15, 2024
- SHA
- c5193b88
Try a prompt
Base models
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. -->
BEREL-finetuned-DSS-pos_cls
This model is a fine-tuned version of dicta-il/BEREL on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1876
- Precision: 0.9281
- Recall: 0.9278
- F1: 0.9280
- Accuracy: 0.9441
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.3317 | 1.0 | 197 | 0.3461 | 0.8773 | 0.8770 | 0.8771 | 0.9027 |
| 0.342 | 2.0 | 394 | 0.2581 | 0.9040 | 0.9025 | 0.9033 | 0.9242 |
| 0.2562 | 3.0 | 591 | 0.2226 | 0.9149 | 0.9154 | 0.9152 | 0.9339 |
| 0.2104 | 4.0 | 788 | 0.2096 | 0.9172 | 0.9190 | 0.9181 | 0.9361 |
| 0.1944 | 5.0 | 985 | 0.1991 | 0.9221 | 0.9224 | 0.9222 | 0.9393 |
| 0.1798 | 6.0 | 1182 | 0.1922 | 0.9252 | 0.9247 | 0.9250 | 0.9417 |
| 0.1678 | 7.0 | 1379 | 0.1900 | 0.9267 | 0.9271 | 0.9269 | 0.9433 |
| 0.1625 | 8.0 | 1576 | 0.1876 | 0.9281 | 0.9278 | 0.9280 | 0.9441 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Tokenizers 0.20.3
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Dec 15, 2024
- Updated
- Dec 15, 2024