Downloads · 30 days
5
23% of all-time downloads
sentiment-xlm-roberta-large-3class
Carlosdca/sentiment-xlm-roberta-large-3class
sentiment-xlm-roberta-large-3class is a text classification model from Carlosdca. 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
22
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 18, 2025
- Updated
- Nov 18, 2025
- SHA
- 8ab949db
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. -->
sentiment-xlm-roberta-large-3class
This model is a fine-tuned version of xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8392
- Accuracy: 0.8703
- F1 Macro: 0.8677
- F1 Weighted: 0.8705
- Precision Macro: 0.8665
- Recall Macro: 0.8693
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | Accuracy | F1 Macro | F1 Weighted | Precision Macro | Recall Macro |
|---|---|---|---|---|---|---|---|---|
| 0.6641 | 1.0 | 328 | 0.6322 | 0.8308 | 0.8231 | 0.8286 | 0.8349 | 0.8178 |
| 0.489 | 2.0 | 656 | 0.4652 | 0.8552 | 0.8490 | 0.8535 | 0.8596 | 0.8437 |
| 0.4518 | 3.0 | 984 | 0.4756 | 0.8247 | 0.8113 | 0.8188 | 0.8472 | 0.8028 |
| 0.3819 | 4.0 | 1312 | 0.5282 | 0.8659 | 0.8610 | 0.8649 | 0.8674 | 0.8572 |
| 0.3149 | 5.0 | 1640 | 0.5208 | 0.8720 | 0.8674 | 0.8710 | 0.8738 | 0.8634 |
| 0.2452 | 6.0 | 1968 | 0.7271 | 0.8735 | 0.8672 | 0.8715 | 0.8836 | 0.8601 |
| 0.1568 | 7.0 | 2296 | 0.8084 | 0.8735 | 0.8708 | 0.8736 | 0.8703 | 0.8713 |
| 0.1011 | 8.0 | 2624 | 0.7953 | 0.8765 | 0.8740 | 0.8767 | 0.8732 | 0.8749 |
| 0.079 | 9.0 | 2952 | 0.9481 | 0.8674 | 0.8655 | 0.8679 | 0.8637 | 0.8692 |
| 0.0472 | 10.0 | 3280 | 0.9520 | 0.8720 | 0.8694 | 0.8721 | 0.8685 | 0.8704 |
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 18, 2025
- Updated
- Nov 18, 2025