<!-- 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. -->
modelBsc62
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: 0.1964
- Precision: 0.6650
- Recall: 0.6422
- F1: 0.6534
- Accuracy: 0.9693
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: 6e-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 | 0.3017 | 0.0 | 0.0 | 0.0 | 0.9362 |
| No log | 2.0 | 58 | 0.2840 | 0.0 | 0.0 | 0.0 | 0.9362 |
| No log | 3.0 | 87 | 0.2159 | 0.15 | 0.0147 | 0.0268 | 0.9421 |
| No log | 4.0 | 116 | 0.1681 | 0.4189 | 0.1520 | 0.2230 | 0.9504 |
| No log | 5.0 | 145 | 0.1433 | 0.4872 | 0.2794 | 0.3551 | 0.9578 |
| No log | 6.0 | 174 | 0.1490 | 0.5532 | 0.3824 | 0.4522 | 0.9585 |
| No log | 7.0 | 203 | 0.1397 | 0.5093 | 0.5392 | 0.5238 | 0.9605 |
| No log | 8.0 | 232 | 0.1473 | 0.5289 | 0.5833 | 0.5548 | 0.9631 |
| No log | 9.0 | 261 | 0.1499 | 0.5888 | 0.5686 | 0.5786 | 0.9656 |
| No log | 10.0 | 290 | 0.1638 | 0.6728 | 0.5343 | 0.5956 | 0.9674 |
| No log | 11.0 | 319 | 0.1507 | 0.5893 | 0.6471 | 0.6168 | 0.9658 |
| No log | 12.0 | 348 | 0.1765 | 0.6550 | 0.5490 | 0.5973 | 0.9678 |
| No log | 13.0 | 377 | 0.1671 | 0.6294 | 0.6078 | 0.6185 | 0.9678 |
| No log | 14.0 | 406 | 0.1616 | 0.6154 | 0.6275 | 0.6214 | 0.9674 |
| No log | 15.0 | 435 | 0.1860 | 0.6078 | 0.6078 | 0.6078 | 0.9669 |
| No log | 16.0 | 464 | 0.1697 | 0.6906 | 0.6127 | 0.6494 | 0.9691 |
| No log | 17.0 | 493 | 0.1861 | 0.6667 | 0.6373 | 0.6516 | 0.9685 |
| 0.089 | 18.0 | 522 | 0.1790 | 0.6279 | 0.6618 | 0.6444 | 0.9674 |
| 0.089 | 19.0 | 551 | 0.1811 | 0.6685 | 0.5833 | 0.6230 | 0.9681 |
| 0.089 | 20.0 | 580 | 0.1805 | 0.6505 | 0.6569 | 0.6537 | 0.9688 |
| 0.089 | 21.0 | 609 | 0.1863 | 0.6578 | 0.6029 | 0.6292 | 0.9686 |
| 0.089 | 22.0 | 638 | 0.1881 | 0.6811 | 0.6176 | 0.6478 | 0.9691 |
| 0.089 | 23.0 | 667 | 0.1896 | 0.6502 | 0.6471 | 0.6486 | 0.9690 |
| 0.089 | 24.0 | 696 | 0.1910 | 0.6717 | 0.6520 | 0.6617 | 0.9693 |
| 0.089 | 25.0 | 725 | 0.1944 | 0.6471 | 0.6471 | 0.6471 | 0.9690 |
| 0.089 | 26.0 | 754 | 0.1946 | 0.6633 | 0.6373 | 0.6500 | 0.9693 |
| 0.089 | 27.0 | 783 | 0.1950 | 0.6599 | 0.6373 | 0.6484 | 0.9690 |
| 0.089 | 28.0 | 812 | 0.1950 | 0.6667 | 0.6373 | 0.6516 | 0.9693 |
| 0.089 | 29.0 | 841 | 0.1961 | 0.6520 | 0.6520 | 0.6520 | 0.9693 |
| 0.089 | 30.0 | 870 | 0.1968 | 0.6633 | 0.6471 | 0.6551 | 0.9693 |
| 0.089 | 31.0 | 899 | 0.1963 | 0.6650 | 0.6422 | 0.6534 | 0.9693 |
| 0.089 | 32.0 | 928 | 0.1964 | 0.6650 | 0.6422 | 0.6534 | 0.9693 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
