metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: sentiment-roberta-es-2025_II
results: []
sentiment-roberta-es-2025_II
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: 0.7531
- F1 Macro: 0.6781
- F1 Weighted: 0.6803
- Accuracy: 0.6819
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: 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy |
|---|---|---|---|---|---|---|
| 1.107 | 1.0 | 241 | 0.8921 | 0.5078 | 0.5163 | 0.5921 |
| 0.7969 | 2.0 | 482 | 0.7448 | 0.6745 | 0.6803 | 0.6816 |
| 0.6555 | 3.0 | 723 | 0.7315 | 0.7003 | 0.7042 | 0.7045 |
| 0.5117 | 4.0 | 964 | 0.8501 | 0.6990 | 0.7001 | 0.6982 |
| 0.3872 | 5.0 | 1205 | 0.9107 | 0.6765 | 0.6756 | 0.6701 |
| 0.3068 | 6.0 | 1446 | 0.9950 | 0.6910 | 0.6926 | 0.6920 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1