xlmroberta-ner-prostata-bs16
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: 0.0624
- Precision: 0.9564
- Recall: 0.9676
- F1: 0.9620
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 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
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 2.5372 | 1.0 | 98 | 0.5433 | 0.5675 | 0.5929 | 0.5799 |
| 0.5009 | 2.0 | 196 | 0.1689 | 0.8851 | 0.9126 | 0.8987 |
| 0.2155 | 3.0 | 294 | 0.0911 | 0.9178 | 0.9469 | 0.9321 |
| 0.1244 | 4.0 | 392 | 0.0734 | 0.9525 | 0.9605 | 0.9565 |
| 0.0930 | 5.0 | 490 | 0.0563 | 0.9560 | 0.9702 | 0.9631 |
| 0.0789 | 6.0 | 588 | 0.0509 | 0.9695 | 0.9683 | 0.9689 |
| 0.0637 | 7.0 | 686 | 0.0472 | 0.9722 | 0.9741 | 0.9732 |
| 0.0530 | 8.0 | 784 | 0.0441 | 0.9729 | 0.9761 | 0.9745 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2