Downloads · 30 days
7
32% of all-time downloads
CeLLaTeNER-2class-pubmedbert-tapt-orig-v1
OTAR3088/CeLLaTeNER-2class-pubmedbert-tapt-orig-v1
CeLLaTeNER-2class-pubmedbert-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 mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
22
Public
Parameters
109M
436 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors436 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026
- SHA
- f5322d2a
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-PubMedBERT-tapt-adapted-base
This model is a fine-tuned version of Mardiyyah/CeLLaTe-pubmedbert-tapt-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0619
- Precision: 0.7896
- Recall: 0.7029
- F1: 0.7437
- Accuracy: 0.9830
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 |
|---|---|---|---|---|---|---|---|
| 0.5126 | 0.3802 | 100 | 0.1116 | 0.2188 | 0.1788 | 0.1968 | 0.9578 |
| 0.0895 | 0.7605 | 200 | 0.0686 | 0.6673 | 0.6217 | 0.6437 | 0.9805 |
| 0.0553 | 1.1407 | 300 | 0.0620 | 0.7445 | 0.6968 | 0.7198 | 0.9829 |
| 0.0414 | 1.5209 | 400 | 0.0548 | 0.7329 | 0.7267 | 0.7298 | 0.9827 |
| 0.0358 | 1.9011 | 500 | 0.0590 | 0.69 | 0.7578 | 0.7223 | 0.9823 |
| 0.0302 | 2.2814 | 600 | 0.0616 | 0.7896 | 0.7029 | 0.7437 | 0.9830 |
| 0.0271 | 2.6616 | 700 | 0.0553 | 0.7224 | 0.7193 | 0.7209 | 0.9813 |
| 0.0264 | 3.0418 | 800 | 0.0609 | 0.7711 | 0.7090 | 0.7387 | 0.9833 |
| 0.0187 | 3.4221 | 900 | 0.0712 | 0.7979 | 0.6937 | 0.7422 | 0.9831 |
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
- mit
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026