Downloads · 30 days
9
21% of all-time downloads
TAPT-V2-biomed_roberta_base
Mardiyyah/TAPT-V2-biomed_roberta_base
TAPT-V2-biomed_roberta_base 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
42
Public
Parameters
125M
499 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors499 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Nov 10, 2025
- Updated
- Nov 10, 2025
- SHA
- aebffb34
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. -->
TAPT-V2-biomed_roberta_base
This model is a fine-tuned version of allenai/biomed_roberta_base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.3766
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: 16
- eval_batch_size: 16
- seed: 42
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.8813 | 1.0 | 584 | 5.8254 |
| 5.616 | 2.0 | 1168 | 5.4221 |
| 5.2846 | 3.0 | 1752 | 5.0635 |
| 5.0121 | 4.0 | 2336 | 4.7765 |
| 4.814 | 5.0 | 2920 | 4.6518 |
| 4.6602 | 6.0 | 3504 | 4.5539 |
| 4.566 | 7.0 | 4088 | 4.4802 |
| 4.4826 | 8.0 | 4672 | 4.4628 |
| 4.4094 | 9.0 | 5256 | 4.3637 |
| 4.3667 | 10.0 | 5840 | 4.3197 |
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
- roberta
- Created
- Nov 10, 2025
- Updated
- Nov 10, 2025