spanish-disease-tagger
This model is a fine-tuned version of plncmm/roberta-clinical-wl-es on the disease dataset. It achieves the following results on the evaluation set:
- Loss: 0.1786
- Precision: 0.8385
- Recall: 0.8711
- F1: 0.8545
- Accuracy: 0.9488
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2217 | 1.0 | 502 | 0.1698 | 0.8142 | 0.8587 | 0.8359 | 0.9437 |
0.1203 | 2.0 | 1004 | 0.1735 | 0.8513 | 0.8528 | 0.8520 | 0.9473 |
0.093 | 3.0 | 1506 | 0.1786 | 0.8385 | 0.8711 | 0.8545 | 0.9488 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 114
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Space using mrojas/spanish-disease-tagger 1
Evaluation results
- Precision on diseaseself-reported0.839
- Recall on diseaseself-reported0.871
- F1 on diseaseself-reported0.855
- Accuracy on diseaseself-reported0.949