Downloads · 30 days
5
5% of all-time downloads
b3r-test-double-epochs
cp-gustavo/b3r-test-double-epochs
b3r-test-double-epochs is a token classification model from cp-gustavo. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
98
Public
Parameters
108M
5.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors431 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Sep 27, 2025
- Updated
- Sep 28, 2025
- SHA
- a5bc252e
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. -->
b3r-test-double-epochs
This model is a fine-tuned version of dmis-lab/biobert-v1.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9408
- Precision: 0.5917
- Recall: 0.6428
- F1: 0.6162
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: 0.00012839450868399685
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1685473261668876
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.5993 | 1.0 | 330 | 0.5521 | 0.5410 | 0.5446 | 0.5427 |
| 0.4982 | 2.0 | 660 | 0.5276 | 0.5480 | 0.5814 | 0.5642 |
| 0.3952 | 3.0 | 990 | 0.5216 | 0.5421 | 0.6360 | 0.5853 |
| 0.2878 | 4.0 | 1320 | 0.5500 | 0.5777 | 0.6196 | 0.5980 |
| 0.2036 | 5.0 | 1650 | 0.5743 | 0.5768 | 0.6255 | 0.6001 |
| 0.1445 | 6.0 | 1980 | 0.6425 | 0.5837 | 0.6364 | 0.6089 |
| 0.0996 | 7.0 | 2310 | 0.7054 | 0.5721 | 0.6392 | 0.6038 |
| 0.0693 | 8.0 | 2640 | 0.7551 | 0.5849 | 0.6414 | 0.6119 |
| 0.048 | 9.0 | 2970 | 0.8148 | 0.5867 | 0.6357 | 0.6102 |
| 0.0323 | 10.0 | 3300 | 0.8739 | 0.5906 | 0.6421 | 0.6153 |
| 0.0225 | 11.0 | 3630 | 0.9206 | 0.5901 | 0.6421 | 0.6150 |
| 0.0169 | 12.0 | 3960 | 0.9408 | 0.5917 | 0.6428 | 0.6162 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Sep 27, 2025
- Updated
- Sep 28, 2025