xlm-roberta-sarcasmo-bs16-ep6
This model is a fine-tuned version of xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4425
- F1 Macro: 0.9336
- F1 Weighted: 0.9369
- 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: 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_steps: 0.1
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy |
|---|---|---|---|---|---|---|
| 0.3016 | 1.0 | 955 | 0.2454 | 0.8965 | 0.9023 | 0.9034 |
| 0.2845 | 2.0 | 1910 | 0.2021 | 0.9229 | 0.9265 | 0.9264 |
| 0.1830 | 3.0 | 2865 | 0.2926 | 0.9170 | 0.9216 | 0.9225 |
| 0.1165 | 4.0 | 3820 | 0.3813 | 0.9264 | 0.9302 | 0.9306 |
| 0.0719 | 5.0 | 4775 | 0.4109 | 0.9327 | 0.9362 | 0.9366 |
| 0.0735 | 6.0 | 5730 | 0.4425 | 0.9336 | 0.9369 | 0.9372 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2