<!-- 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. -->
modelBsc
This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1830
- Precision: 0.64
- Recall: 0.6207
- F1: 0.6302
- Accuracy: 0.9685
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: 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 | 0.3033 | 0.0213 | 0.0043 | 0.0072 | 0.9174 |
No log | 2.0 | 58 | 0.2425 | 0.1522 | 0.0302 | 0.0504 | 0.9325 |
No log | 3.0 | 87 | 0.1906 | 0.3056 | 0.1422 | 0.1941 | 0.9435 |
No log | 4.0 | 116 | 0.1825 | 0.3841 | 0.2716 | 0.3182 | 0.9439 |
No log | 5.0 | 145 | 0.1594 | 0.5517 | 0.3448 | 0.4244 | 0.9554 |
No log | 6.0 | 174 | 0.1383 | 0.5408 | 0.5431 | 0.5419 | 0.9595 |
No log | 7.0 | 203 | 0.1460 | 0.5897 | 0.4957 | 0.5386 | 0.9624 |
No log | 8.0 | 232 | 0.1534 | 0.6105 | 0.5 | 0.5498 | 0.9642 |
No log | 9.0 | 261 | 0.1587 | 0.5869 | 0.5388 | 0.5618 | 0.9631 |
No log | 10.0 | 290 | 0.1684 | 0.5921 | 0.5819 | 0.5870 | 0.9637 |
No log | 11.0 | 319 | 0.1713 | 0.5270 | 0.6724 | 0.5909 | 0.9606 |
No log | 12.0 | 348 | 0.1895 | 0.4984 | 0.6897 | 0.5787 | 0.9572 |
No log | 13.0 | 377 | 0.1759 | 0.4969 | 0.6897 | 0.5776 | 0.9568 |
No log | 14.0 | 406 | 0.1798 | 0.6468 | 0.5603 | 0.6005 | 0.9664 |
No log | 15.0 | 435 | 0.1909 | 0.5118 | 0.6552 | 0.5747 | 0.9597 |
No log | 16.0 | 464 | 0.1745 | 0.6184 | 0.6078 | 0.6130 | 0.9658 |
No log | 17.0 | 493 | 0.1670 | 0.6261 | 0.6207 | 0.6234 | 0.9674 |
0.062 | 18.0 | 522 | 0.1719 | 0.5992 | 0.6509 | 0.6240 | 0.9667 |
0.062 | 19.0 | 551 | 0.1759 | 0.6224 | 0.6466 | 0.6342 | 0.9674 |
0.062 | 20.0 | 580 | 0.1780 | 0.6327 | 0.6164 | 0.6245 | 0.9669 |
0.062 | 21.0 | 609 | 0.1777 | 0.5632 | 0.6336 | 0.5963 | 0.9637 |
0.062 | 22.0 | 638 | 0.1784 | 0.6137 | 0.6164 | 0.6151 | 0.9665 |
0.062 | 23.0 | 667 | 0.1730 | 0.6276 | 0.6466 | 0.6369 | 0.9678 |
0.062 | 24.0 | 696 | 0.1822 | 0.6076 | 0.6207 | 0.6141 | 0.9660 |
0.062 | 25.0 | 725 | 0.1820 | 0.6306 | 0.6034 | 0.6167 | 0.9678 |
0.062 | 26.0 | 754 | 0.1792 | 0.6083 | 0.6293 | 0.6186 | 0.9671 |
0.062 | 27.0 | 783 | 0.1810 | 0.6416 | 0.625 | 0.6332 | 0.9691 |
0.062 | 28.0 | 812 | 0.1800 | 0.6360 | 0.625 | 0.6304 | 0.9687 |
0.062 | 29.0 | 841 | 0.1811 | 0.6025 | 0.6336 | 0.6176 | 0.9660 |
0.062 | 30.0 | 870 | 0.1821 | 0.6074 | 0.6336 | 0.6203 | 0.9664 |
0.062 | 31.0 | 899 | 0.1825 | 0.6388 | 0.625 | 0.6318 | 0.9685 |
0.062 | 32.0 | 928 | 0.1830 | 0.64 | 0.6207 | 0.6302 | 0.9685 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3