<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
prueba1
This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1842
- Precision: 0.7072
- Recall: 0.6255
- F1: 0.6638
- Accuracy: 0.9724
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: 3.5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 32
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 29 | 0.1520 | 0.5625 | 0.6813 | 0.6162 | 0.9659 |
| No log | 2.0 | 58 | 0.1552 | 0.6293 | 0.5817 | 0.6046 | 0.9686 |
| No log | 3.0 | 87 | 0.1586 | 0.6667 | 0.5737 | 0.6167 | 0.9709 |
| No log | 4.0 | 116 | 0.1595 | 0.6981 | 0.5896 | 0.6393 | 0.9722 |
| No log | 5.0 | 145 | 0.1699 | 0.6729 | 0.5737 | 0.6194 | 0.9676 |
| No log | 6.0 | 174 | 0.1753 | 0.6577 | 0.5817 | 0.6173 | 0.9689 |
| No log | 7.0 | 203 | 0.1665 | 0.6540 | 0.6175 | 0.6352 | 0.9681 |
| No log | 8.0 | 232 | 0.1792 | 0.7157 | 0.5618 | 0.6295 | 0.9712 |
| No log | 9.0 | 261 | 0.1682 | 0.7048 | 0.5896 | 0.6421 | 0.9714 |
| No log | 10.0 | 290 | 0.1732 | 0.7366 | 0.6016 | 0.6623 | 0.9724 |
| No log | 11.0 | 319 | 0.1663 | 0.672 | 0.6693 | 0.6707 | 0.9725 |
| No log | 12.0 | 348 | 0.1882 | 0.7071 | 0.5578 | 0.6236 | 0.9692 |
| No log | 13.0 | 377 | 0.1825 | 0.7103 | 0.6056 | 0.6538 | 0.9710 |
| No log | 14.0 | 406 | 0.1755 | 0.7164 | 0.5737 | 0.6372 | 0.9709 |
| No log | 15.0 | 435 | 0.1950 | 0.6842 | 0.5697 | 0.6217 | 0.9689 |
| No log | 16.0 | 464 | 0.1660 | 0.7240 | 0.6375 | 0.6780 | 0.9727 |
| No log | 17.0 | 493 | 0.1833 | 0.7255 | 0.5896 | 0.6505 | 0.9724 |
| 0.0061 | 18.0 | 522 | 0.1832 | 0.7190 | 0.6016 | 0.6551 | 0.9702 |
| 0.0061 | 19.0 | 551 | 0.1762 | 0.6828 | 0.6175 | 0.6485 | 0.9707 |
| 0.0061 | 20.0 | 580 | 0.1785 | 0.7346 | 0.6175 | 0.6710 | 0.9734 |
| 0.0061 | 21.0 | 609 | 0.1791 | 0.7093 | 0.6414 | 0.6736 | 0.9739 |
| 0.0061 | 22.0 | 638 | 0.1843 | 0.7476 | 0.6255 | 0.6811 | 0.9737 |
| 0.0061 | 23.0 | 667 | 0.1837 | 0.7371 | 0.6255 | 0.6767 | 0.9734 |
| 0.0061 | 24.0 | 696 | 0.1867 | 0.7176 | 0.6175 | 0.6638 | 0.9715 |
| 0.0061 | 25.0 | 725 | 0.1844 | 0.7089 | 0.6016 | 0.6509 | 0.9710 |
| 0.0061 | 26.0 | 754 | 0.1815 | 0.7072 | 0.6255 | 0.6638 | 0.9725 |
| 0.0061 | 27.0 | 783 | 0.1822 | 0.7021 | 0.6574 | 0.6790 | 0.9737 |
| 0.0061 | 28.0 | 812 | 0.1853 | 0.7048 | 0.6375 | 0.6695 | 0.9732 |
| 0.0061 | 29.0 | 841 | 0.1845 | 0.7069 | 0.6534 | 0.6791 | 0.9735 |
| 0.0061 | 30.0 | 870 | 0.1827 | 0.7004 | 0.6614 | 0.6803 | 0.9735 |
| 0.0061 | 31.0 | 899 | 0.1850 | 0.7014 | 0.6175 | 0.6568 | 0.9719 |
| 0.0061 | 32.0 | 928 | 0.1842 | 0.7072 | 0.6255 | 0.6638 | 0.9724 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
