Downloads · 30 days
33
14% of all-time downloads
deberta-v3-hybrid-detector_12
Yuvrajg2107/deberta-v3-hybrid-detector_12
deberta-v3-hybrid-detector_12 is a text classification model from Yuvrajg2107. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
233
Public
Parameters
142M
25.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.1 GB · 50%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- Dec 25, 2025
- Updated
- Dec 26, 2025
- SHA
- 58965ed8
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. -->
deberta-v3-hybrid-detector_12
This model is a fine-tuned version of microsoft/deberta-v3-small on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.9553
- Loss: 0.0432
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: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.0616 | 0.0667 | 500 | 0.8034 | 0.1604 |
| 0.0299 | 0.1333 | 1000 | 0.9175 | 0.0660 |
| 0.025 | 0.2 | 1500 | 0.8977 | 0.0927 |
| 0.0214 | 0.2667 | 2000 | 0.9478 | 0.0440 |
| 0.0197 | 0.3333 | 2500 | 0.8927 | 0.1201 |
| 0.018 | 0.4 | 3000 | 0.9510 | 0.0436 |
| 0.0163 | 0.4667 | 3500 | 0.9623 | 0.0352 |
| 0.0152 | 0.5333 | 4000 | 0.936 | 0.0679 |
| 0.0132 | 0.6 | 4500 | 0.8901 | 0.1139 |
| 0.0127 | 0.6667 | 5000 | 0.9468 | 0.0523 |
| 0.0113 | 0.7333 | 5500 | 0.9455 | 0.0515 |
| 0.0113 | 0.8 | 6000 | 0.9580 | 0.0387 |
| 0.0091 | 0.8667 | 6500 | 0.9319 | 0.0847 |
| 0.0107 | 0.9333 | 7000 | 0.9407 | 0.0630 |
| 0.0102 | 1.0 | 7500 | 0.9553 | 0.0432 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.6.0+cu124
- Datasets 4.4.2
- Tokenizers 0.22.1
- Task
- Text Classification
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Created
- Dec 25, 2025
- Updated
- Dec 26, 2025