metadata
library_name: transformers
license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
- generated_from_trainer
model-index:
- name: epochs_3_fold_3
results: []
epochs_3_fold_3
This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4448
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- 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: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.738 | 0.2020 | 300 | 0.5920 |
| 0.5744 | 0.4040 | 600 | 0.5276 |
| 0.5463 | 0.6061 | 900 | 0.5022 |
| 0.5206 | 0.8081 | 1200 | 0.4901 |
| 0.4908 | 1.0101 | 1500 | 0.4721 |
| 0.4024 | 1.2121 | 1800 | 0.4696 |
| 0.3901 | 1.4141 | 2100 | 0.4606 |
| 0.394 | 1.6162 | 2400 | 0.4515 |
| 0.3715 | 1.8182 | 2700 | 0.4389 |
| 0.3594 | 2.0202 | 3000 | 0.4496 |
| 0.2809 | 2.2222 | 3300 | 0.4604 |
| 0.2589 | 2.4242 | 3600 | 0.4525 |
| 0.273 | 2.6263 | 3900 | 0.4554 |
| 0.2642 | 2.8283 | 4200 | 0.4448 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0