|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: prueba3 |
|
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. --> |
|
|
|
# prueba3 |
|
|
|
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: 0.2158 |
|
- Precision: 0.7162 |
|
- Recall: 0.6335 |
|
- F1: 0.6723 |
|
- Accuracy: 0.9737 |
|
|
|
## 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: 2.75e-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 | 0.2562 | 0.7732 | 0.5976 | 0.6742 | 0.9719 | |
|
| No log | 2.0 | 58 | 0.2526 | 0.705 | 0.5618 | 0.6253 | 0.9704 | |
|
| No log | 3.0 | 87 | 0.2187 | 0.6833 | 0.6534 | 0.6680 | 0.9705 | |
|
| No log | 4.0 | 116 | 0.2205 | 0.6583 | 0.6295 | 0.6436 | 0.9715 | |
|
| No log | 5.0 | 145 | 0.2161 | 0.7162 | 0.6534 | 0.6833 | 0.9712 | |
|
| No log | 6.0 | 174 | 0.2293 | 0.6977 | 0.5976 | 0.6438 | 0.9722 | |
|
| No log | 7.0 | 203 | 0.2207 | 0.6972 | 0.6056 | 0.6482 | 0.9724 | |
|
| No log | 8.0 | 232 | 0.2343 | 0.6781 | 0.6295 | 0.6529 | 0.9707 | |
|
| No log | 9.0 | 261 | 0.2212 | 0.7115 | 0.5896 | 0.6449 | 0.9730 | |
|
| No log | 10.0 | 290 | 0.2171 | 0.7260 | 0.6016 | 0.6580 | 0.9734 | |
|
| No log | 11.0 | 319 | 0.2191 | 0.6851 | 0.6414 | 0.6626 | 0.9725 | |
|
| No log | 12.0 | 348 | 0.2101 | 0.7056 | 0.6494 | 0.6763 | 0.9740 | |
|
| No log | 13.0 | 377 | 0.2227 | 0.7240 | 0.6375 | 0.6780 | 0.9732 | |
|
| No log | 14.0 | 406 | 0.2226 | 0.7442 | 0.6375 | 0.6867 | 0.9739 | |
|
| No log | 15.0 | 435 | 0.2247 | 0.7339 | 0.6375 | 0.6823 | 0.9739 | |
|
| No log | 16.0 | 464 | 0.2167 | 0.6983 | 0.6454 | 0.6708 | 0.9729 | |
|
| No log | 17.0 | 493 | 0.2220 | 0.7281 | 0.6295 | 0.6752 | 0.9732 | |
|
| 0.0005 | 18.0 | 522 | 0.2294 | 0.7299 | 0.6135 | 0.6667 | 0.9725 | |
|
| 0.0005 | 19.0 | 551 | 0.2104 | 0.6949 | 0.6534 | 0.6735 | 0.9722 | |
|
| 0.0005 | 20.0 | 580 | 0.2103 | 0.7240 | 0.6375 | 0.6780 | 0.9730 | |
|
| 0.0005 | 21.0 | 609 | 0.2092 | 0.7137 | 0.6454 | 0.6778 | 0.9735 | |
|
| 0.0005 | 22.0 | 638 | 0.2091 | 0.7181 | 0.6494 | 0.6820 | 0.9737 | |
|
| 0.0005 | 23.0 | 667 | 0.2081 | 0.7162 | 0.6534 | 0.6833 | 0.9735 | |
|
| 0.0005 | 24.0 | 696 | 0.2198 | 0.7264 | 0.6135 | 0.6652 | 0.9722 | |
|
| 0.0005 | 25.0 | 725 | 0.2206 | 0.7290 | 0.6215 | 0.6710 | 0.9725 | |
|
| 0.0005 | 26.0 | 754 | 0.2194 | 0.7256 | 0.6215 | 0.6695 | 0.9735 | |
|
| 0.0005 | 27.0 | 783 | 0.2220 | 0.7290 | 0.6215 | 0.6710 | 0.9739 | |
|
| 0.0005 | 28.0 | 812 | 0.2230 | 0.7290 | 0.6215 | 0.6710 | 0.9735 | |
|
| 0.0005 | 29.0 | 841 | 0.2163 | 0.7182 | 0.6295 | 0.6709 | 0.9737 | |
|
| 0.0005 | 30.0 | 870 | 0.2158 | 0.7162 | 0.6335 | 0.6723 | 0.9737 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.3 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
