Downloads · 30 days
7
35% of all-time downloads
FIRE-deberta-small-v3-v3
avinasht/FIRE-deberta-small-v3-v3
FIRE-deberta-small-v3-v3 is a machine learning model from avinasht. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
20
Public
Parameters
142M
568 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors568 MB · 100%
At a glance
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- Nov 22, 2025
- Updated
- Nov 22, 2025
- SHA
- e0eed564
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. -->
FIRE-deberta-small-v3-v3
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:
- Loss: 0.5291
- Accuracy: 0.9306
- F1: 0.9306
- Precision: 0.9307
- Recall: 0.9306
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.1809 | 1.0 | 3169 | 0.6323 | 0.8865 | 0.8853 | 0.8946 | 0.8865 |
| 0.7809 | 2.0 | 6338 | 0.6816 | 0.8953 | 0.8954 | 0.8976 | 0.8953 |
| 0.9375 | 3.0 | 9507 | 0.5352 | 0.9117 | 0.9118 | 0.9126 | 0.9117 |
| 0.6445 | 4.0 | 12676 | 0.4555 | 0.9231 | 0.9231 | 0.9231 | 0.9231 |
| 0.0006 | 5.0 | 15845 | 0.6403 | 0.9218 | 0.9217 | 0.9225 | 0.9218 |
| 0.0007 | 6.0 | 19014 | 0.6209 | 0.9105 | 0.9106 | 0.9131 | 0.9105 |
| 0.0029 | 7.0 | 22183 | 0.5291 | 0.9306 | 0.9306 | 0.9307 | 0.9306 |
| 0.0002 | 8.0 | 25352 | 0.5479 | 0.9281 | 0.9281 | 0.9281 | 0.9281 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.19.1
- Type
- deberta-v2
- License
- mit
- Created
- Nov 22, 2025
- Updated
- Nov 22, 2025