<!-- 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. -->
modelBsc5
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: 0.1546
- Precision: 0.5567
- Recall: 0.6075
- F1: 0.5810
- Accuracy: 0.9708
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 | 0.2697 | 0.0 | 0.0 | 0.0 | 0.9446 |
| No log | 2.0 | 58 | 0.2357 | 0.0 | 0.0 | 0.0 | 0.9446 |
| No log | 3.0 | 87 | 0.2176 | 0.0 | 0.0 | 0.0 | 0.9446 |
| No log | 4.0 | 116 | 0.1889 | 0.0541 | 0.0108 | 0.0179 | 0.9406 |
| No log | 5.0 | 145 | 0.1800 | 0.1613 | 0.0269 | 0.0461 | 0.9477 |
| No log | 6.0 | 174 | 0.1625 | 0.2745 | 0.0753 | 0.1181 | 0.9532 |
| No log | 7.0 | 203 | 0.1502 | 0.4306 | 0.1667 | 0.2403 | 0.9571 |
| No log | 8.0 | 232 | 0.1426 | 0.3810 | 0.2581 | 0.3077 | 0.9576 |
| No log | 9.0 | 261 | 0.1459 | 0.5586 | 0.3333 | 0.4175 | 0.9638 |
| No log | 10.0 | 290 | 0.1288 | 0.5732 | 0.5054 | 0.5371 | 0.9636 |
| No log | 11.0 | 319 | 0.1241 | 0.4769 | 0.5538 | 0.5124 | 0.9638 |
| No log | 12.0 | 348 | 0.1282 | 0.5189 | 0.5161 | 0.5175 | 0.9664 |
| No log | 13.0 | 377 | 0.1335 | 0.4232 | 0.6667 | 0.5177 | 0.9595 |
| No log | 14.0 | 406 | 0.1314 | 0.5854 | 0.5161 | 0.5486 | 0.9693 |
| No log | 15.0 | 435 | 0.1357 | 0.4772 | 0.6183 | 0.5386 | 0.9653 |
| No log | 16.0 | 464 | 0.1382 | 0.4398 | 0.6290 | 0.5177 | 0.9638 |
| No log | 17.0 | 493 | 0.1362 | 0.5634 | 0.6452 | 0.6015 | 0.9705 |
| 0.1141 | 18.0 | 522 | 0.1466 | 0.5 | 0.6505 | 0.5654 | 0.9669 |
| 0.1141 | 19.0 | 551 | 0.1497 | 0.5441 | 0.5968 | 0.5692 | 0.9703 |
| 0.1141 | 20.0 | 580 | 0.1375 | 0.5520 | 0.6559 | 0.5995 | 0.9700 |
| 0.1141 | 21.0 | 609 | 0.1373 | 0.5707 | 0.6290 | 0.5985 | 0.9722 |
| 0.1141 | 22.0 | 638 | 0.1490 | 0.5777 | 0.6398 | 0.6071 | 0.9710 |
| 0.1141 | 23.0 | 667 | 0.1550 | 0.5314 | 0.6828 | 0.5976 | 0.9679 |
| 0.1141 | 24.0 | 696 | 0.1506 | 0.5397 | 0.6935 | 0.6071 | 0.9679 |
| 0.1141 | 25.0 | 725 | 0.1528 | 0.5346 | 0.6237 | 0.5757 | 0.9703 |
| 0.1141 | 26.0 | 754 | 0.1503 | 0.5764 | 0.6290 | 0.6015 | 0.9715 |
| 0.1141 | 27.0 | 783 | 0.1446 | 0.5767 | 0.5860 | 0.5813 | 0.9722 |
| 0.1141 | 28.0 | 812 | 0.1486 | 0.5377 | 0.6129 | 0.5729 | 0.9701 |
| 0.1141 | 29.0 | 841 | 0.1538 | 0.5577 | 0.6237 | 0.5888 | 0.9703 |
| 0.1141 | 30.0 | 870 | 0.1543 | 0.5545 | 0.6022 | 0.5773 | 0.9701 |
| 0.1141 | 31.0 | 899 | 0.1551 | 0.5517 | 0.6022 | 0.5758 | 0.9708 |
| 0.1141 | 32.0 | 928 | 0.1546 | 0.5567 | 0.6075 | 0.5810 | 0.9708 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
