Downloads · 30 days
9
20% of all-time downloads
polish-roberta-base-v2-danger
julasms/polish-roberta-base-v2-danger
polish-roberta-base-v2-danger is a text classification model from julasms. 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
45
Public
Parameters
124M
498 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors498 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- roberta
- Access
- Public
- Created
- Nov 3, 2025
- Updated
- Nov 3, 2025
- SHA
- 89b5379b
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. -->
polish-roberta-base-v2-danger
This model is a fine-tuned version of sdadas/polish-roberta-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7781
- Accuracy: 0.86
- Auc: 0.896
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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc |
|---|---|---|---|---|---|
| 0.6504 | 1.0 | 25 | 0.5626 | 0.7 | 0.799 |
| 0.4193 | 2.0 | 50 | 0.5370 | 0.77 | 0.858 |
| 0.2406 | 3.0 | 75 | 0.4971 | 0.78 | 0.88 |
| 0.1759 | 4.0 | 100 | 0.6343 | 0.84 | 0.904 |
| 0.0636 | 5.0 | 125 | 0.9575 | 0.8 | 0.899 |
| 0.0466 | 6.0 | 150 | 0.6445 | 0.87 | 0.912 |
| 0.018 | 7.0 | 175 | 0.8138 | 0.84 | 0.909 |
| 0.0195 | 8.0 | 200 | 0.7916 | 0.86 | 0.895 |
| 0.0174 | 9.0 | 225 | 0.7876 | 0.86 | 0.9 |
| 0.0153 | 10.0 | 250 | 0.7781 | 0.86 | 0.896 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.3.0
- Tokenizers 0.22.1
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- apache-2.0
- Created
- Nov 3, 2025
- Updated
- Nov 3, 2025