Downloads · 30 days
3
11% of all-time downloads
sentiment-XLM-RoBERTa-es-2025_II-bs8-v2
Elkin5/sentiment-XLM-RoBERTa-es-2025_II-bs8-v2
sentiment-XLM-RoBERTa-es-2025_II-bs8-v2 is a text classification model from Elkin5. 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
28
Public
Parameters
560M
4.5 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 21, 2025
- Updated
- Nov 28, 2025
- SHA
- 99b8b86a
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-es-2025_II-bs8-v2
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: 1.3380
- F1 Macro: 0.6668
- F1 Weighted: 0.6690
- Accuracy: 0.6754
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: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- 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_ratio: 0.15
- num_epochs: 10
- label_smoothing_factor: 0.05
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy |
|---|---|---|---|---|---|---|
| 1.0962 | 1.0 | 283 | 0.9958 | 0.5006 | 0.4857 | 0.5088 |
| 0.8202 | 2.0 | 566 | 0.7568 | 0.6688 | 0.6727 | 0.6733 |
| 0.5657 | 3.0 | 849 | 0.8673 | 0.6757 | 0.6808 | 0.6868 |
| 0.3377 | 4.0 | 1132 | 1.2669 | 0.6513 | 0.6497 | 0.6452 |
| 0.2314 | 5.0 | 1415 | 1.2683 | 0.6774 | 0.6796 | 0.6837 |
| 0.1552 | 6.0 | 1698 | 1.8657 | 0.6745 | 0.6778 | 0.6764 |
| 0.1167 | 7.0 | 1981 | 1.9835 | 0.6708 | 0.6733 | 0.6743 |
| 0.0798 | 8.0 | 2264 | 2.2425 | 0.6746 | 0.6767 | 0.6764 |
| 0.0539 | 9.0 | 2547 | 2.3357 | 0.6726 | 0.6761 | 0.6764 |
| 0.0388 | 10.0 | 2830 | 2.3609 | 0.6692 | 0.6715 | 0.6733 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Task
- Text Classification
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- Nov 21, 2025
- Updated
- Nov 28, 2025