beto-ner-prostata-bs8
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: 0.0702
- Precision: 0.9608
- Recall: 0.9676
- F1: 0.9642
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: 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
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.3835 | 1.0 | 195 | 0.1729 | 0.8563 | 0.9023 | 0.8787 |
| 0.1117 | 2.0 | 390 | 0.0706 | 0.9551 | 0.9508 | 0.9530 |
| 0.0743 | 3.0 | 585 | 0.0446 | 0.9727 | 0.9696 | 0.9712 |
| 0.0569 | 4.0 | 780 | 0.0469 | 0.9760 | 0.9722 | 0.9741 |
| 0.0317 | 5.0 | 975 | 0.0478 | 0.9786 | 0.9786 | 0.9786 |
| 0.0347 | 6.0 | 1170 | 0.0491 | 0.9818 | 0.9761 | 0.9789 |
| 0.0228 | 7.0 | 1365 | 0.0491 | 0.9824 | 0.9767 | 0.9796 |
| 0.0176 | 8.0 | 1560 | 0.0491 | 0.9824 | 0.9767 | 0.9796 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2