<!-- 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. -->
prueba
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: 0.1440
- Precision: 0.6923
- Recall: 0.6096
- F1: 0.6483
- Accuracy: 0.9719
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: 2.5e-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 | 0.3513 | 0.0 | 0.0 | 0.0 | 0.9259 |
| No log | 2.0 | 58 | 0.2696 | 0.0 | 0.0 | 0.0 | 0.9259 |
| No log | 3.0 | 87 | 0.2879 | 0.0 | 0.0 | 0.0 | 0.9259 |
| No log | 4.0 | 116 | 0.2318 | 0.0714 | 0.0080 | 0.0143 | 0.9361 |
| No log | 5.0 | 145 | 0.2055 | 0.2222 | 0.0558 | 0.0892 | 0.9376 |
| No log | 6.0 | 174 | 0.2076 | 0.3793 | 0.0876 | 0.1424 | 0.9464 |
| No log | 7.0 | 203 | 0.1630 | 0.4831 | 0.2271 | 0.3089 | 0.9525 |
| No log | 8.0 | 232 | 0.1529 | 0.5515 | 0.3625 | 0.4375 | 0.9573 |
| No log | 9.0 | 261 | 0.1519 | 0.5972 | 0.3426 | 0.4354 | 0.9603 |
| No log | 10.0 | 290 | 0.1399 | 0.6272 | 0.4223 | 0.5048 | 0.9639 |
| No log | 11.0 | 319 | 0.1412 | 0.6096 | 0.4542 | 0.5205 | 0.9641 |
| No log | 12.0 | 348 | 0.1320 | 0.5969 | 0.4661 | 0.5235 | 0.9646 |
| No log | 13.0 | 377 | 0.1311 | 0.6515 | 0.5139 | 0.5746 | 0.9671 |
| No log | 14.0 | 406 | 0.1300 | 0.6329 | 0.5219 | 0.5721 | 0.9656 |
| No log | 15.0 | 435 | 0.1346 | 0.6345 | 0.4980 | 0.5580 | 0.9672 |
| No log | 16.0 | 464 | 0.1361 | 0.6329 | 0.5219 | 0.5721 | 0.9669 |
| No log | 17.0 | 493 | 0.1312 | 0.6532 | 0.5777 | 0.6131 | 0.9689 |
| 0.1181 | 18.0 | 522 | 0.1327 | 0.6756 | 0.6056 | 0.6387 | 0.9694 |
| 0.1181 | 19.0 | 551 | 0.1495 | 0.7234 | 0.5418 | 0.6196 | 0.9704 |
| 0.1181 | 20.0 | 580 | 0.1328 | 0.6872 | 0.5777 | 0.6277 | 0.9707 |
| 0.1181 | 21.0 | 609 | 0.1363 | 0.6667 | 0.6215 | 0.6433 | 0.9710 |
| 0.1181 | 22.0 | 638 | 0.1392 | 0.6884 | 0.5896 | 0.6352 | 0.9712 |
| 0.1181 | 23.0 | 667 | 0.1377 | 0.6437 | 0.6335 | 0.6386 | 0.9704 |
| 0.1181 | 24.0 | 696 | 0.1434 | 0.6504 | 0.5857 | 0.6164 | 0.9697 |
| 0.1181 | 25.0 | 725 | 0.1418 | 0.6944 | 0.5976 | 0.6424 | 0.9710 |
| 0.1181 | 26.0 | 754 | 0.1426 | 0.6739 | 0.6175 | 0.6445 | 0.9715 |
| 0.1181 | 27.0 | 783 | 0.1447 | 0.7085 | 0.6295 | 0.6667 | 0.9734 |
| 0.1181 | 28.0 | 812 | 0.1432 | 0.6903 | 0.6215 | 0.6541 | 0.9727 |
| 0.1181 | 29.0 | 841 | 0.1421 | 0.7162 | 0.6335 | 0.6723 | 0.9729 |
| 0.1181 | 30.0 | 870 | 0.1431 | 0.6875 | 0.6135 | 0.6484 | 0.9720 |
| 0.1181 | 31.0 | 899 | 0.1431 | 0.6844 | 0.6135 | 0.6471 | 0.9717 |
| 0.1181 | 32.0 | 928 | 0.1440 | 0.6923 | 0.6096 | 0.6483 | 0.9719 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
