metadata
license: apache-2.0
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
tags:
- generated_from_trainer
metrics:
- precision
- f1
model-index:
- name: finetuning-0
results: []
finetuning-0
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: 0.2446
- Precision: 0.9615
- Sensitivity: 0.8065
- F1: 0.8772
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Sensitivity | F1 |
|---|---|---|---|---|---|---|
| 0.3577 | 1.27 | 150 | 0.2695 | 0.9615 | 0.5376 | 0.6897 |
| 0.1836 | 2.54 | 300 | 0.2239 | 0.9545 | 0.6774 | 0.7925 |
| 0.1518 | 3.81 | 450 | 0.1970 | 0.9481 | 0.7849 | 0.8588 |
| 0.1129 | 5.08 | 600 | 0.2098 | 0.9620 | 0.8172 | 0.8837 |
| 0.0688 | 6.36 | 750 | 0.2758 | 0.9853 | 0.7204 | 0.8323 |
| 0.0592 | 7.63 | 900 | 0.2446 | 0.9615 | 0.8065 | 0.8772 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2