<!-- 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. -->
DISO_bsc_test
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: 0.0959
- Diso Precision: 0.7766
- Diso Recall: 0.7803
- Diso F1: 0.7784
- Diso Number: 4552
- Overall Precision: 0.7766
- Overall Recall: 0.7803
- Overall F1: 0.7784
- 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Diso Precision | Diso Recall | Diso F1 | Diso Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
---|---|---|---|---|---|---|---|---|---|---|---|
0.0849 | 1.0 | 2799 | 0.0734 | 0.7360 | 0.7676 | 0.7515 | 4552 | 0.7360 | 0.7676 | 0.7515 | 0.9726 |
0.0572 | 2.0 | 5598 | 0.0736 | 0.7674 | 0.7768 | 0.7721 | 4552 | 0.7674 | 0.7768 | 0.7721 | 0.9743 |
0.0462 | 3.0 | 8397 | 0.0836 | 0.7737 | 0.7707 | 0.7722 | 4552 | 0.7737 | 0.7707 | 0.7722 | 0.9736 |
0.0318 | 4.0 | 11196 | 0.0959 | 0.7766 | 0.7803 | 0.7784 | 4552 | 0.7766 | 0.7803 | 0.7784 | 0.9744 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2