|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: neuralmind/bert-base-portuguese-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
model-index: |
|
- name: neuralmind/bert-base-portuguese-cased |
|
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. --> |
|
|
|
# neuralmind/bert-base-portuguese-cased |
|
|
|
This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0505 |
|
- Accuracy: 0.7211 |
|
- F1: 0.6737 |
|
- Recall: 0.7341 |
|
- Precision: 0.6706 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 5151 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 120 |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:| |
|
| 0.0685 | 1.0 | 18 | 0.0667 | 0.3571 | 0.3563 | 0.4877 | 0.4864 | |
|
| 0.0642 | 2.0 | 36 | 0.0655 | 0.5268 | 0.5020 | 0.5461 | 0.5354 | |
|
| 0.0629 | 3.0 | 54 | 0.0641 | 0.6607 | 0.6052 | 0.6253 | 0.6036 | |
|
| 0.0614 | 4.0 | 72 | 0.0618 | 0.6964 | 0.6569 | 0.6942 | 0.6551 | |
|
| 0.0583 | 5.0 | 90 | 0.0584 | 0.7054 | 0.6773 | 0.7339 | 0.6816 | |
|
| 0.0549 | 6.0 | 108 | 0.0548 | 0.7321 | 0.6930 | 0.7295 | 0.6862 | |
|
| 0.048 | 7.0 | 126 | 0.0553 | 0.7768 | 0.7124 | 0.7148 | 0.7102 | |
|
| 0.0391 | 8.0 | 144 | 0.0521 | 0.7768 | 0.7460 | 0.7933 | 0.7360 | |
|
| 0.032 | 9.0 | 162 | 0.0523 | 0.7679 | 0.7208 | 0.7424 | 0.7103 | |
|
| 0.0222 | 10.0 | 180 | 0.0585 | 0.7946 | 0.7354 | 0.7381 | 0.7329 | |
|
| 0.0181 | 11.0 | 198 | 0.0809 | 0.8036 | 0.7083 | 0.6880 | 0.7561 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.0 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
