|
--- |
|
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: 0.2116 |
|
- Precision: 0.7516 |
|
- Recall: 0.6901 |
|
- F1: 0.7195 |
|
- Accuracy: 0.9758 |
|
|
|
## 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: 7.5e-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 | 0.2388 | 0.7315 | 0.6374 | 0.6813 | 0.9739 | |
|
| No log | 2.0 | 58 | 0.1956 | 0.6169 | 0.7251 | 0.6667 | 0.9723 | |
|
| No log | 3.0 | 87 | 0.1637 | 0.6302 | 0.7076 | 0.6667 | 0.9730 | |
|
| No log | 4.0 | 116 | 0.2107 | 0.6810 | 0.6491 | 0.6647 | 0.9741 | |
|
| No log | 5.0 | 145 | 0.1987 | 0.6981 | 0.6491 | 0.6727 | 0.9745 | |
|
| No log | 6.0 | 174 | 0.1524 | 0.7355 | 0.6667 | 0.6994 | 0.9756 | |
|
| No log | 7.0 | 203 | 0.1933 | 0.7664 | 0.6140 | 0.6818 | 0.9750 | |
|
| No log | 8.0 | 232 | 0.2150 | 0.7836 | 0.6140 | 0.6885 | 0.9747 | |
|
| No log | 9.0 | 261 | 0.1700 | 0.7405 | 0.6842 | 0.7112 | 0.9761 | |
|
| No log | 10.0 | 290 | 0.1626 | 0.6142 | 0.7076 | 0.6576 | 0.9730 | |
|
| No log | 11.0 | 319 | 0.1826 | 0.7035 | 0.7076 | 0.7055 | 0.9761 | |
|
| No log | 12.0 | 348 | 0.1724 | 0.6802 | 0.6842 | 0.6822 | 0.9758 | |
|
| No log | 13.0 | 377 | 0.1823 | 0.7852 | 0.6199 | 0.6928 | 0.9741 | |
|
| No log | 14.0 | 406 | 0.1833 | 0.7284 | 0.6901 | 0.7087 | 0.9761 | |
|
| No log | 15.0 | 435 | 0.1816 | 0.5853 | 0.7427 | 0.6546 | 0.9701 | |
|
| No log | 16.0 | 464 | 0.2084 | 0.7770 | 0.6725 | 0.7210 | 0.9761 | |
|
| No log | 17.0 | 493 | 0.2043 | 0.7069 | 0.7193 | 0.7130 | 0.9748 | |
|
| 0.0022 | 18.0 | 522 | 0.1996 | 0.6541 | 0.7076 | 0.6798 | 0.9741 | |
|
| 0.0022 | 19.0 | 551 | 0.2013 | 0.7484 | 0.6959 | 0.7212 | 0.9763 | |
|
| 0.0022 | 20.0 | 580 | 0.1933 | 0.7159 | 0.7368 | 0.7262 | 0.9770 | |
|
| 0.0022 | 21.0 | 609 | 0.1931 | 0.7101 | 0.7018 | 0.7059 | 0.9759 | |
|
| 0.0022 | 22.0 | 638 | 0.1946 | 0.7052 | 0.7135 | 0.7093 | 0.9759 | |
|
| 0.0022 | 23.0 | 667 | 0.1968 | 0.6936 | 0.7018 | 0.6977 | 0.9752 | |
|
| 0.0022 | 24.0 | 696 | 0.2076 | 0.7296 | 0.6784 | 0.7030 | 0.9754 | |
|
| 0.0022 | 25.0 | 725 | 0.2076 | 0.7296 | 0.6784 | 0.7030 | 0.9756 | |
|
| 0.0022 | 26.0 | 754 | 0.2051 | 0.6941 | 0.6901 | 0.6921 | 0.9747 | |
|
| 0.0022 | 27.0 | 783 | 0.2106 | 0.7342 | 0.6784 | 0.7052 | 0.9752 | |
|
| 0.0022 | 28.0 | 812 | 0.2093 | 0.7312 | 0.6842 | 0.7069 | 0.9752 | |
|
| 0.0022 | 29.0 | 841 | 0.2112 | 0.7516 | 0.6901 | 0.7195 | 0.9758 | |
|
| 0.0022 | 30.0 | 870 | 0.2116 | 0.7516 | 0.6901 | 0.7195 | 0.9758 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
