|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: testlink-class-2 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# testlink-class-2 |
|
|
|
This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1903 |
|
- Precision: 0.6705 |
|
- Recall: 0.6901 |
|
- F1: 0.6801 |
|
- Accuracy: 0.9752 |
|
|
|
## 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: 7e-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: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 29 | 0.1665 | 0.5894 | 0.7135 | 0.6455 | 0.9717 | |
|
| No log | 2.0 | 58 | 0.1726 | 0.6864 | 0.6784 | 0.6824 | 0.9745 | |
|
| No log | 3.0 | 87 | 0.1412 | 0.6398 | 0.6959 | 0.6667 | 0.9748 | |
|
| No log | 4.0 | 116 | 0.1735 | 0.6646 | 0.6374 | 0.6507 | 0.9737 | |
|
| No log | 5.0 | 145 | 0.2060 | 0.4448 | 0.7544 | 0.5597 | 0.9592 | |
|
| No log | 6.0 | 174 | 0.1974 | 0.6529 | 0.6491 | 0.6510 | 0.9710 | |
|
| No log | 7.0 | 203 | 0.1564 | 0.6062 | 0.6842 | 0.6429 | 0.9726 | |
|
| No log | 8.0 | 232 | 0.1690 | 0.5580 | 0.7310 | 0.6329 | 0.9693 | |
|
| No log | 9.0 | 261 | 0.1869 | 0.6805 | 0.6725 | 0.6765 | 0.9736 | |
|
| No log | 10.0 | 290 | 0.1729 | 0.6894 | 0.6491 | 0.6687 | 0.9754 | |
|
| No log | 11.0 | 319 | 0.1793 | 0.7114 | 0.6199 | 0.6625 | 0.9754 | |
|
| No log | 12.0 | 348 | 0.1703 | 0.5805 | 0.6959 | 0.6330 | 0.9723 | |
|
| No log | 13.0 | 377 | 0.1649 | 0.6429 | 0.6842 | 0.6629 | 0.9739 | |
|
| No log | 14.0 | 406 | 0.1832 | 0.7081 | 0.6667 | 0.6867 | 0.9758 | |
|
| No log | 15.0 | 435 | 0.1877 | 0.7063 | 0.6608 | 0.6828 | 0.9763 | |
|
| No log | 16.0 | 464 | 0.1828 | 0.6981 | 0.6491 | 0.6727 | 0.9763 | |
|
| No log | 17.0 | 493 | 0.1666 | 0.6842 | 0.6842 | 0.6842 | 0.9767 | |
|
| 0.0032 | 18.0 | 522 | 0.1795 | 0.5982 | 0.7661 | 0.6718 | 0.9732 | |
|
| 0.0032 | 19.0 | 551 | 0.1728 | 0.6543 | 0.7193 | 0.6852 | 0.9765 | |
|
| 0.0032 | 20.0 | 580 | 0.1781 | 0.6425 | 0.7251 | 0.6813 | 0.9754 | |
|
| 0.0032 | 21.0 | 609 | 0.1747 | 0.6743 | 0.6901 | 0.6821 | 0.9765 | |
|
| 0.0032 | 22.0 | 638 | 0.1815 | 0.6173 | 0.7076 | 0.6594 | 0.9743 | |
|
| 0.0032 | 23.0 | 667 | 0.1863 | 0.6842 | 0.6842 | 0.6842 | 0.9761 | |
|
| 0.0032 | 24.0 | 696 | 0.1871 | 0.6742 | 0.7018 | 0.6877 | 0.9758 | |
|
| 0.0032 | 25.0 | 725 | 0.1912 | 0.6517 | 0.6784 | 0.6648 | 0.9745 | |
|
| 0.0032 | 26.0 | 754 | 0.1907 | 0.6839 | 0.6959 | 0.6899 | 0.9758 | |
|
| 0.0032 | 27.0 | 783 | 0.1904 | 0.6630 | 0.7018 | 0.6818 | 0.9747 | |
|
| 0.0032 | 28.0 | 812 | 0.1895 | 0.6630 | 0.7018 | 0.6818 | 0.9748 | |
|
| 0.0032 | 29.0 | 841 | 0.1903 | 0.6648 | 0.6959 | 0.68 | 0.9750 | |
|
| 0.0032 | 30.0 | 870 | 0.1903 | 0.6705 | 0.6901 | 0.6801 | 0.9752 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
