Downloads · 30 days
35
41% of all-time downloads
CeLLaTe-tapt-pubmedbert-tokenizer-adapted_v2_lr-2e5
Mardiyyah/CeLLaTe-tapt-pubmedbert-tokenizer-adapted_v2_lr-2e5
CeLLaTe-tapt-pubmedbert-tokenizer-adapted_v2_lr-2e5 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
86
Public
Parameters
110M
880 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors442 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jul 21, 2026
- Updated
- Jul 21, 2026
- SHA
- 939d54dd
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-pubmedbert-tokenizer-adapted_v2_lr-2e5
This model is a fine-tuned version of microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext on the Mardiyyah/TAPT_CeLLaTe2.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.1498
- Accuracy: 0.7645
- Perplexity: 3.1576
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: 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 |
|---|---|---|---|---|---|
| 1.3593 | 1.0 | 14 | 1.2054 | 0.7589 | 3.3382 |
| 1.3738 | 2.0 | 28 | 1.2002 | 0.7611 | 3.3209 |
| 1.3468 | 3.0 | 42 | 1.1980 | 0.7585 | 3.3135 |
| 1.3319 | 4.0 | 56 | 1.2181 | 0.7557 | 3.3808 |
| 1.3085 | 5.0 | 70 | 1.2109 | 0.7581 | 3.3565 |
| 1.2994 | 6.0 | 84 | 1.2024 | 0.7545 | 3.3279 |
| 1.2836 | 7.0 | 98 | 1.1483 | 0.7640 | 3.1530 |
| 1.2806 | 8.0 | 112 | 1.2058 | 0.7517 | 3.3393 |
| 1.254 | 9.0 | 126 | 1.1481 | 0.7611 | 3.1522 |
| 1.247 | 10.0 | 140 | 1.1739 | 0.7567 | 3.2345 |
| 1.2627 | 11.0 | 154 | 1.1571 | 0.7559 | 3.1807 |
| 1.2227 | 12.0 | 168 | 1.1721 | 0.7587 | 3.2287 |
| 1.2235 | 13.0 | 182 | 1.2401 | 0.7522 | 3.4560 |
| 1.2163 | 14.0 | 196 | 1.1925 | 0.7567 | 3.2953 |
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 21, 2026
- Updated
- Jul 21, 2026