<!-- 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. -->
DisTEMIST_bsc_test1
This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1876
- Diso Precision: 0.7529
- Diso Recall: 0.7818
- Diso F1: 0.7671
- Diso Number: 1407
- Overall Precision: 0.7529
- Overall Recall: 0.7818
- Overall F1: 0.7671
- Overall Accuracy: 0.9744
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: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=2.6e-09
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 73
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Diso Precision | Diso Recall | Diso F1 | Diso Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.1734 | 1.0 | 997 | 0.1084 | 0.7166 | 0.6397 | 0.6759 | 1407 | 0.7166 | 0.6397 | 0.6759 | 0.9656 |
| 0.0589 | 2.0 | 1994 | 0.0896 | 0.7249 | 0.7662 | 0.7450 | 1407 | 0.7249 | 0.7662 | 0.7450 | 0.9725 |
| 0.0288 | 3.0 | 2991 | 0.1162 | 0.7199 | 0.7910 | 0.7538 | 1407 | 0.7199 | 0.7910 | 0.7538 | 0.9725 |
| 0.0163 | 4.0 | 3988 | 0.1267 | 0.7434 | 0.7783 | 0.7604 | 1407 | 0.7434 | 0.7783 | 0.7604 | 0.9731 |
| 0.0096 | 5.0 | 4985 | 0.1362 | 0.7406 | 0.7832 | 0.7613 | 1407 | 0.7406 | 0.7832 | 0.7613 | 0.9748 |
| 0.0047 | 6.0 | 5982 | 0.1573 | 0.7619 | 0.7711 | 0.7665 | 1407 | 0.7619 | 0.7711 | 0.7665 | 0.9745 |
| 0.0041 | 7.0 | 6979 | 0.1773 | 0.7083 | 0.7939 | 0.7487 | 1407 | 0.7083 | 0.7939 | 0.7487 | 0.9691 |
| 0.0019 | 8.0 | 7976 | 0.1682 | 0.7441 | 0.7811 | 0.7621 | 1407 | 0.7441 | 0.7811 | 0.7621 | 0.9741 |
| 0.0012 | 9.0 | 8973 | 0.1823 | 0.7507 | 0.7811 | 0.7656 | 1407 | 0.7507 | 0.7811 | 0.7656 | 0.9743 |
| 0.0004 | 10.0 | 9970 | 0.1876 | 0.7529 | 0.7818 | 0.7671 | 1407 | 0.7529 | 0.7818 | 0.7671 | 0.9744 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
