Downloads · 30 days
7
35% of all-time downloads
CeLLaTeNER-bioformer8l-tapt-orig-v1
OTAR3088/CeLLaTeNER-bioformer8l-tapt-orig-v1
CeLLaTeNER-bioformer8l-tapt-orig-v1 is a token classification model from OTAR3088. 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
20
Public
Parameters
42.3M
169 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors169 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026
- SHA
- b31ea0f5
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. -->
CeLLaTe-Bioformers-8l-tapt-adapted-base
This model is a fine-tuned version of Mardiyyah/CeLLaTe-bioformer-8l-tapt-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0667
- Precision: 0.7140
- Recall: 0.7169
- F1: 0.7155
- Accuracy: 0.9791
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: 3407
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: 0.01
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.5836 | 0.3802 | 100 | 0.1275 | 0.3320 | 0.2983 | 0.3143 | 0.9534 |
| 0.1223 | 0.7605 | 200 | 0.0995 | 0.5071 | 0.3019 | 0.3785 | 0.9632 |
| 0.0755 | 1.1407 | 300 | 0.0694 | 0.5865 | 0.6869 | 0.6327 | 0.9745 |
| 0.0555 | 1.5209 | 400 | 0.0675 | 0.7193 | 0.6556 | 0.6860 | 0.9779 |
| 0.0458 | 1.9011 | 500 | 0.0639 | 0.6918 | 0.7187 | 0.7050 | 0.9787 |
| 0.0382 | 2.2814 | 600 | 0.0667 | 0.7140 | 0.7169 | 0.7155 | 0.9791 |
| 0.0343 | 2.6616 | 700 | 0.0720 | 0.5821 | 0.6266 | 0.6035 | 0.9709 |
| 0.0316 | 3.0418 | 800 | 0.0664 | 0.6772 | 0.6641 | 0.6706 | 0.9773 |
| 0.0254 | 3.4221 | 900 | 0.0783 | 0.6913 | 0.6100 | 0.6481 | 0.9763 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.21.0
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026