|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: roberta-finetuned-CPV_Spanish |
|
results: [] |
|
--- |
|
|
|
# roberta-finetuned-CPV_Spanish |
|
|
|
This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on the a dataset derived from Spanish Public Procurement documents from 2019. The whole fine-tuning process is available in the following [Kaggle notebook](https://www.kaggle.com/code/marianavasloro/fine-tuned-roberta-for-spanish-cpv-codes). |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0417 |
|
- F1: 0.7757 |
|
- Roc Auc: 0.8684 |
|
- Accuracy: 0.7223 |
|
- Coverage Error: 11.7873 |
|
- Label Ranking Average Precision Score: 0.7728 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | Coverage Error | Label Ranking Average Precision Score | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|:--------:|:--------------:|:-------------------------------------:| |
|
| 0.0582 | 1.0 | 2039 | 0.0554 | 0.6291 | 0.7463 | 0.5235 | 21.9642 | 0.5547 | |
|
| 0.0413 | 2.0 | 4078 | 0.0437 | 0.7054 | 0.7959 | 0.6239 | 17.5374 | 0.6589 | |
|
| 0.0295 | 3.0 | 6117 | 0.0403 | 0.7391 | 0.8285 | 0.6788 | 14.7700 | 0.7197 | |
|
| 0.022 | 4.0 | 8156 | 0.0390 | 0.7562 | 0.8414 | 0.6987 | 13.8217 | 0.7425 | |
|
| 0.0168 | 5.0 | 10195 | 0.0393 | 0.7600 | 0.8547 | 0.7007 | 12.8532 | 0.7542 | |
|
| 0.0127 | 6.0 | 12234 | 0.0396 | 0.7645 | 0.8606 | 0.7099 | 12.3890 | 0.7622 | |
|
| 0.0094 | 7.0 | 14273 | 0.0406 | 0.7642 | 0.8675 | 0.7027 | 11.8679 | 0.7628 | |
|
| 0.0066 | 8.0 | 16312 | 0.0404 | 0.7706 | 0.8641 | 0.7173 | 12.0876 | 0.7681 | |
|
| 0.0052 | 9.0 | 18351 | 0.0411 | 0.7748 | 0.8679 | 0.7182 | 11.8149 | 0.7705 | |
|
| 0.0042 | 10.0 | 20390 | 0.0417 | 0.7757 | 0.8684 | 0.7223 | 11.7873 | 0.7728 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.16.2 |
|
- Pytorch 1.9.1 |
|
- Datasets 1.18.4 |
|
- Tokenizers 0.11.6 |
|
|
