|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: xlm-roberta-base-ptbr-finetuned |
|
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. --> |
|
|
|
# xlm-roberta-base-ptbr-finetuned |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3305 |
|
- F1: 0.2957 |
|
- Roc Auc: 0.6147 |
|
- Accuracy: 0.48 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
|
| 0.3954 | 1.0 | 109 | 0.3836 | 0.0 | 0.5 | 0.23 | |
|
| 0.3868 | 2.0 | 218 | 0.3428 | 0.1905 | 0.5658 | 0.415 | |
|
| 0.3374 | 3.0 | 327 | 0.3169 | 0.2236 | 0.5866 | 0.48 | |
|
| 0.2931 | 4.0 | 436 | 0.3217 | 0.2091 | 0.5789 | 0.425 | |
|
| 0.2601 | 5.0 | 545 | 0.3166 | 0.2752 | 0.6008 | 0.485 | |
|
| 0.2381 | 6.0 | 654 | 0.3305 | 0.2957 | 0.6147 | 0.48 | |
|
| 0.1987 | 7.0 | 763 | 0.3561 | 0.2761 | 0.6045 | 0.455 | |
|
| 0.1863 | 8.0 | 872 | 0.3538 | 0.2905 | 0.6121 | 0.465 | |
|
| 0.1335 | 9.0 | 981 | 0.3741 | 0.2710 | 0.6029 | 0.445 | |
|
| 0.1343 | 10.0 | 1090 | 0.3873 | 0.2850 | 0.6096 | 0.46 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.0 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
