Downloads · 30 days
1
3% of all-time downloads
xlm-roberta-tass-2025-II-bs4
shaka03/xlm-roberta-tass-2025-II-bs4
xlm-roberta-tass-2025-II-bs4 is a text classification model from shaka03. 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
29
Public
Parameters
560M
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.2 GB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Nov 5, 2025
- Updated
- Nov 5, 2025
- SHA
- 2db41143
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. -->
xlm-roberta-tass-2025-II-bs4
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8514
- F1 Macro: 0.6648
- F1 Weighted: 0.6662
- Accuracy: 0.6680
- Recall: 0.6662
- Precision: 0.6639
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
- 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_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy | Recall | Precision |
|---|---|---|---|---|---|---|---|---|
| 1.0793 | 1.0 | 961 | 0.9587 | 0.4644 | 0.4692 | 0.4932 | 0.4812 | 0.5046 |
| 0.885 | 2.0 | 1922 | 0.9063 | 0.6741 | 0.6761 | 0.6753 | 0.6759 | 0.6734 |
| 0.7823 | 3.0 | 2883 | 1.1295 | 0.6662 | 0.6699 | 0.6899 | 0.6812 | 0.6917 |
| 0.7395 | 4.0 | 3844 | 1.1755 | 0.6911 | 0.6939 | 0.6941 | 0.6865 | 0.7002 |
| 0.6483 | 5.0 | 4805 | 1.5552 | 0.6931 | 0.6957 | 0.6951 | 0.6924 | 0.6938 |
| 0.503 | 6.0 | 5766 | 1.7285 | 0.6967 | 0.7007 | 0.7003 | 0.6953 | 0.6985 |
| 0.3769 | 7.0 | 6727 | 1.9969 | 0.6825 | 0.6854 | 0.6837 | 0.6804 | 0.6855 |
| 0.2776 | 8.0 | 7688 | 2.2777 | 0.6801 | 0.6825 | 0.6785 | 0.6781 | 0.6868 |
| 0.2029 | 9.0 | 8649 | 2.4857 | 0.6767 | 0.6789 | 0.6774 | 0.6746 | 0.6797 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Task
- Text Classification
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- Nov 5, 2025
- Updated
- Nov 5, 2025