Downloads · 30 days
3
6% of all-time downloads
patent-bert-v2-lowlr
KamilHugsFaces/patent-bert-v2-lowlr
patent-bert-v2-lowlr 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
49
Public
Parameters
109M
438 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Oct 12, 2025
- Updated
- Oct 12, 2025
- SHA
- 0a3ceb03
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-bert-v2-lowlr
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9764
- Accuracy: 0.6702
- F1: 0.6449
- Precision: 0.6405
- Recall: 0.6702
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: 16
- eval_batch_size: 16
- seed: 42
- 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 |
|---|---|---|---|---|---|---|---|
| 1.0508 | 1.0 | 1563 | 1.0089 | 0.6574 | 0.6288 | 0.6320 | 0.6574 |
| 0.8873 | 2.0 | 3126 | 0.9479 | 0.6748 | 0.6499 | 0.6428 | 0.6748 |
| 0.7307 | 3.0 | 4689 | 0.9747 | 0.6736 | 0.6529 | 0.6452 | 0.6736 |
| 0.6351 | 4.0 | 6252 | 1.0198 | 0.6716 | 0.6600 | 0.6528 | 0.6716 |
| 0.5399 | 5.0 | 7815 | 1.1036 | 0.6658 | 0.6524 | 0.6450 | 0.6658 |
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
- bert
- License
- apache-2.0
- Created
- Oct 12, 2025
- Updated
- Oct 12, 2025