xlm-roberta-base-rus-noaug
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1776
- F1: 0.8139
- Roc Auc: 0.8817
- Accuracy: 0.7437
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.4354 | 1.0 | 84 | 0.4392 | 0.0 | 0.5 | 0.1608 |
| 0.3744 | 2.0 | 168 | 0.3579 | 0.2399 | 0.5998 | 0.3668 |
| 0.2949 | 3.0 | 252 | 0.2638 | 0.5115 | 0.7243 | 0.5879 |
| 0.2211 | 4.0 | 336 | 0.2227 | 0.6541 | 0.7716 | 0.6231 |
| 0.1898 | 5.0 | 420 | 0.1879 | 0.7815 | 0.8500 | 0.7286 |
| 0.1404 | 6.0 | 504 | 0.1775 | 0.8031 | 0.8641 | 0.7236 |
| 0.1202 | 7.0 | 588 | 0.1729 | 0.8105 | 0.8719 | 0.7387 |
| 0.1083 | 8.0 | 672 | 0.1776 | 0.8139 | 0.8817 | 0.7437 |
| 0.0828 | 9.0 | 756 | 0.1818 | 0.7988 | 0.8619 | 0.7387 |
| 0.0686 | 10.0 | 840 | 0.1755 | 0.8079 | 0.8678 | 0.7538 |
| 0.0691 | 11.0 | 924 | 0.1860 | 0.8050 | 0.8704 | 0.7337 |
| 0.059 | 12.0 | 1008 | 0.1695 | 0.8078 | 0.8700 | 0.7387 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0