Downloads · 30 days
25
30% of all-time downloads
CeLLaTe-tapt-pubmedbert-tokenizer-adapted_v2
Mardiyyah/CeLLaTe-tapt-pubmedbert-tokenizer-adapted_v2
CeLLaTe-tapt-pubmedbert-tokenizer-adapted_v2 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
84
Public
Parameters
110M
1.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jul 20, 2026
- Updated
- Jul 21, 2026
- SHA
- 44c88276
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
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: 1.0382
- Accuracy: 0.7691
- Perplexity: 2.8240
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: 5e-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 |
|---|---|---|---|---|---|
| 1.2084 | 1.0 | 14 | 1.0521 | 0.7681 | 2.8636 |
| 1.1946 | 2.0 | 28 | 1.0386 | 0.7696 | 2.8253 |
| 1.1586 | 3.0 | 42 | 1.0498 | 0.7687 | 2.8572 |
| 1.1324 | 4.0 | 56 | 1.0643 | 0.7652 | 2.8989 |
| 1.155 | 5.0 | 70 | 1.0055 | 0.7768 | 2.7334 |
| 1.1254 | 6.0 | 84 | 0.9817 | 0.7778 | 2.6691 |
| 1.1211 | 7.0 | 98 | 1.0599 | 0.7684 | 2.8862 |
| 1.0968 | 8.0 | 112 | 1.0617 | 0.7659 | 2.8912 |
| 1.0885 | 9.0 | 126 | 1.0601 | 0.7627 | 2.8868 |
| 1.0577 | 10.0 | 140 | 1.0537 | 0.7705 | 2.8683 |
| 1.0454 | 11.0 | 154 | 1.0260 | 0.7684 | 2.7898 |
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 20, 2026
- Updated
- Jul 21, 2026