Downloads · 30 days
10
45% of all-time downloads
CeLLaTeNER-bioformer16l-tapt-orig-v1
OTAR3088/CeLLaTeNER-bioformer16l-tapt-orig-v1
CeLLaTeNER-bioformer16l-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
22
Public
Parameters
41.4M
166 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors166 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
- 6609f616
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-16l-tapt-adapted-base
This model is a fine-tuned version of Mardiyyah/CeLLaTe-bioformer-16l-tapt-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0684
- Precision: 0.7789
- Recall: 0.7482
- F1: 0.7632
- Accuracy: 0.9820
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 |
|---|---|---|---|---|---|---|---|
| 0.5296 | 0.3802 | 100 | 0.1177 | 0.3241 | 0.1677 | 0.2210 | 0.9551 |
| 0.1027 | 0.7605 | 200 | 0.0823 | 0.6897 | 0.5309 | 0.5999 | 0.9757 |
| 0.065 | 1.1407 | 300 | 0.0668 | 0.6816 | 0.6547 | 0.6679 | 0.9780 |
| 0.0496 | 1.5209 | 400 | 0.0616 | 0.7427 | 0.7294 | 0.7360 | 0.9803 |
| 0.0429 | 1.9011 | 500 | 0.0623 | 0.7439 | 0.7312 | 0.7375 | 0.9808 |
| 0.0365 | 2.2814 | 600 | 0.0611 | 0.7625 | 0.7379 | 0.75 | 0.9816 |
| 0.0322 | 2.6616 | 700 | 0.0743 | 0.6614 | 0.6158 | 0.6378 | 0.9747 |
| 0.0318 | 3.0418 | 800 | 0.0618 | 0.7755 | 0.7509 | 0.7630 | 0.9818 |
| 0.0254 | 3.4221 | 900 | 0.0734 | 0.8032 | 0.7044 | 0.7505 | 0.9808 |
| 0.0244 | 3.8023 | 1000 | 0.0732 | 0.8126 | 0.7156 | 0.7610 | 0.9816 |
| 0.0222 | 4.1825 | 1100 | 0.0683 | 0.7789 | 0.7482 | 0.7632 | 0.9820 |
| 0.0201 | 4.5627 | 1200 | 0.0733 | 0.7472 | 0.7071 | 0.7266 | 0.9802 |
| 0.0191 | 4.9430 | 1300 | 0.0750 | 0.7923 | 0.7115 | 0.7498 | 0.9807 |
| 0.0162 | 5.3232 | 1400 | 0.0816 | 0.7923 | 0.6945 | 0.7402 | 0.9806 |
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