Downloads · 30 days
44
44% of all-time downloads
CeLLaTe-tapt-bioformer16l-tokenizer-original-baseline
Mardiyyah/CeLLaTe-tapt-bioformer16l-tokenizer-original-baseline
CeLLaTe-tapt-bioformer16l-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
100
Public
Parameters
41.6M
6.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt4 GB · 63%
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
- 68b085e8
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-bioformer16l-tokenizer-original-baseline
This model is a fine-tuned version of bioformers/bioformer-16l on the Mardiyyah/TAPT_CeLLaTe2.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.2118
- Accuracy: 0.7444
- Perplexity: 3.3596
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 |
|---|---|---|---|---|---|
| 1.47 | 1.0 | 15 | 1.2742 | 0.7351 | 3.5759 |
| 1.4645 | 2.0 | 30 | 1.2752 | 0.7331 | 3.5796 |
| 1.444 | 3.0 | 45 | 1.2506 | 0.7410 | 3.4925 |
| 1.4036 | 4.0 | 60 | 1.2267 | 0.7429 | 3.4099 |
| 1.3737 | 5.0 | 75 | 1.2051 | 0.7453 | 3.3370 |
| 1.3584 | 6.0 | 90 | 1.2133 | 0.7444 | 3.3645 |
| 1.3457 | 7.0 | 105 | 1.1860 | 0.7500 | 3.2738 |
| 1.3146 | 8.0 | 120 | 1.2254 | 0.7464 | 3.4055 |
| 1.3081 | 9.0 | 135 | 1.2281 | 0.7422 | 3.4146 |
| 1.2906 | 10.0 | 150 | 1.1861 | 0.7476 | 3.2744 |
| 1.2644 | 11.0 | 165 | 1.2125 | 0.7460 | 3.3618 |
| 1.2665 | 12.0 | 180 | 1.2033 | 0.7491 | 3.3310 |
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