XLMRoberta-Sarcasmo-2026-10e-32bs
This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll02-spanish on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5109
- F1 Macro: 0.9335
- F1 Weighted: 0.9370
- Accuracy: 0.9372
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: 32
- eval_batch_size: 32
- 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_steps: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy |
|---|---|---|---|---|---|---|
| 0.3370 | 1.0 | 478 | 0.2828 | 0.8733 | 0.8812 | 0.8827 |
| 0.2064 | 2.0 | 956 | 0.2205 | 0.9144 | 0.9188 | 0.9188 |
| 0.1413 | 3.0 | 1434 | 0.2378 | 0.9163 | 0.9212 | 0.9220 |
| 0.1152 | 4.0 | 1912 | 0.2420 | 0.9234 | 0.9278 | 0.9283 |
| 0.0851 | 5.0 | 2390 | 0.3587 | 0.9321 | 0.9356 | 0.9356 |
| 0.0688 | 6.0 | 2868 | 0.3573 | 0.9308 | 0.9347 | 0.9351 |
| 0.0474 | 7.0 | 3346 | 0.3658 | 0.9395 | 0.9428 | 0.9429 |
| 0.0144 | 8.0 | 3824 | 0.4905 | 0.9339 | 0.9375 | 0.9377 |
| 0.0314 | 9.0 | 4302 | 0.5222 | 0.9303 | 0.9340 | 0.9340 |
| 0.0087 | 10.0 | 4780 | 0.5109 | 0.9335 | 0.9370 | 0.9372 |
Framework versions
- Transformers 5.13.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2