Downloads · 30 days
16
8% of all-time downloads
patent-deberta-v3-large
KamilHugsFaces/patent-deberta-v3-large
patent-deberta-v3-large is a text classification model from KamilHugsFaces. 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
189
Public
Parameters
435M
1.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- Oct 12, 2025
- Updated
- Oct 12, 2025
- SHA
- d5d2bca6
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. -->
patent-deberta-v3-large
This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9284
- Accuracy: 0.6942
- F1: 0.6674
- Precision: 0.6640
- Recall: 0.6942
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.0058 | 1.0 | 1563 | 0.9943 | 0.6676 | 0.6403 | 0.6325 | 0.6676 |
| 0.852 | 2.0 | 3126 | 0.9098 | 0.7026 | 0.6749 | 0.6662 | 0.7026 |
| 0.6888 | 3.0 | 4689 | 0.9676 | 0.6952 | 0.6711 | 0.6720 | 0.6952 |
| 0.5699 | 4.0 | 6252 | 1.0500 | 0.6928 | 0.6802 | 0.6745 | 0.6928 |
| 0.4614 | 5.0 | 7815 | 1.1473 | 0.689 | 0.6797 | 0.6742 | 0.689 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu128
- Datasets 4.2.0
- Tokenizers 0.22.1
- Task
- Text Classification
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Created
- Oct 12, 2025
- Updated
- Oct 12, 2025