beto-ner-prostata-bs32
This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0693
- Precision: 0.9459
- Recall: 0.9574
- F1: 0.9517
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 49 | 0.5470 | 0.6546 | 0.6699 | 0.6622 |
| 1.9728 | 2.0 | 98 | 0.2010 | 0.8442 | 0.8803 | 0.8619 |
| 0.4078 | 3.0 | 147 | 0.1027 | 0.9227 | 0.9353 | 0.9290 |
| 0.1808 | 4.0 | 196 | 0.0787 | 0.9341 | 0.9540 | 0.9440 |
| 0.1123 | 5.0 | 245 | 0.0636 | 0.9545 | 0.9638 | 0.9591 |
| 0.0836 | 6.0 | 294 | 0.0606 | 0.9613 | 0.9657 | 0.9635 |
| 0.0661 | 7.0 | 343 | 0.0542 | 0.9665 | 0.9696 | 0.9680 |
| 0.0533 | 8.0 | 392 | 0.0556 | 0.9677 | 0.9683 | 0.9680 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2