Downloads · 30 days
38
41% of all-time downloads
CeLLaTe-tapt-bioformer8l-tokenizer-original-baseline
Mardiyyah/CeLLaTe-tapt-bioformer8l-tokenizer-original-baseline
CeLLaTe-tapt-bioformer8l-tokenizer-original-baseline is a fill-mask model from Mardiyyah. Use it when you need the model to fill a missing word. 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
92
Public
Parameters
42.6M
340 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors170 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jul 23, 2026
- Updated
- Jul 25, 2026
- SHA
- 6d3a9666
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-tapt-bioformer8l-tokenizer-original-baseline
This model is a fine-tuned version of bioformers/bioformer-8l on the Mardiyyah/TAPT_CeLLaTe2.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.2722
- Accuracy: 0.7347
- Perplexity: 3.5686
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 3407
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Perplexity |
|---|---|---|---|---|---|
| 1.5349 | 1.0 | 15 | 1.3280 | 0.7276 | 3.7735 |
| 1.5213 | 2.0 | 30 | 1.3337 | 0.7250 | 3.7951 |
| 1.502 | 3.0 | 45 | 1.3018 | 0.7293 | 3.6761 |
| 1.4556 | 4.0 | 60 | 1.2751 | 0.7323 | 3.5791 |
| 1.427 | 5.0 | 75 | 1.2503 | 0.7345 | 3.4915 |
| 1.4093 | 6.0 | 90 | 1.2736 | 0.7306 | 3.5738 |
| 1.3945 | 7.0 | 105 | 1.2271 | 0.7417 | 3.4113 |
| 1.3647 | 8.0 | 120 | 1.2762 | 0.7303 | 3.5831 |
| 1.3637 | 9.0 | 135 | 1.2751 | 0.7307 | 3.5789 |
| 1.343 | 10.0 | 150 | 1.2356 | 0.7370 | 3.4403 |
| 1.3183 | 11.0 | 165 | 1.2591 | 0.7341 | 3.5221 |
| 1.317 | 12.0 | 180 | 1.2573 | 0.7373 | 3.5158 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.21.0
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- en
- Created
- Jul 23, 2026
- Updated
- Jul 25, 2026