Downloads · 30 days
4
10% of all-time downloads
xlm-roberta-sentiment-shp
chechdop/xlm-roberta-sentiment-shp
xlm-roberta-sentiment-shp is a text classification model from chechdop. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
40
Public
Parameters
278M
2.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 98%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- xlm-roberta
- Access
- Public
- Created
- Nov 20, 2025
- Updated
- Dec 5, 2025
- SHA
- b865df18
Try a prompt
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-sentiment-shp-tokenizer-vocab
This model was trained on the AmericasNLP-2025 dataset for the Task1: Machine Translation in Shipibo-Konibo (shp). It is finetuned on the XLM-Roberta-Base model. It achieves the following results on the evaluation set:
- Loss: 1.2232
- Accuracy: 0.5823
- Precision: 0.5818
- Recall: 0.5823
- F1: 0.5773
- Balanced Accuracy: 0.5507
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
- lr_scheduler_warmup_steps: 500
- num_epochs: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Balanced Accuracy |
|---|---|---|---|---|---|---|---|---|
| 0.8192 | 1.0 | 2902 | 0.8489 | 0.6340 | 0.6084 | 0.6340 | 0.6083 | 0.4798 |
| 0.8388 | 2.0 | 5804 | 0.7590 | 0.6857 | 0.6758 | 0.6857 | 0.6604 | 0.5380 |
| 0.6252 | 3.0 | 8706 | 0.8490 | 0.6930 | 0.6947 | 0.6930 | 0.6756 | 0.5712 |
| 0.7868 | 4.0 | 11608 | 0.9270 | 0.6930 | 0.6987 | 0.6930 | 0.6836 | 0.5969 |
| 0.5892 | 5.0 | 14510 | 0.8853 | 0.7019 | 0.7048 | 0.7019 | 0.6998 | 0.6292 |
| 0.719 | 6.0 | 17412 | 1.0641 | 0.7043 | 0.6994 | 0.7043 | 0.7010 | 0.6249 |
| 0.6805 | 7.0 | 20314 | 1.2283 | 0.7126 | 0.7139 | 0.7126 | 0.7043 | 0.6181 |
| 0.7471 | 8.0 | 23216 | 1.3237 | 0.7057 | 0.6988 | 0.7057 | 0.6983 | 0.6102 |
| 0.6011 | 9.0 | 26118 | 1.3071 | 0.7085 | 0.6965 | 0.7085 | 0.6944 | 0.5885 |
| 0.5917 | 10.0 | 29020 | 1.5666 | 0.6888 | 0.6925 | 0.6888 | 0.6901 | 0.6241 |
| 0.5057 | 11.0 | 31922 | 1.5296 | 0.7112 | 0.7027 | 0.7112 | 0.6877 | 0.5637 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu129
- Datasets 4.2.0
- Tokenizers 0.22.1
- Task
- Text Classification
- Library
- transformers
- Type
- xlm-roberta
- Created
- Nov 20, 2025
- Updated
- Dec 5, 2025