metadata
library_name: transformers
license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: BingoGuard-bert-base-pt
results: []
BingoGuard-bert-base-pt
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: 0.1359
- Accuracy: 0.9438
- F1: 0.6724
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: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4101 | 1.0 | 456 | 0.1396 | 0.9428 | 0.6398 |
| 0.3366 | 2.0 | 912 | 0.1291 | 0.9393 | 0.6516 |
| 0.2788 | 3.0 | 1368 | 0.1209 | 0.9462 | 0.6766 |
| 0.2695 | 4.0 | 1824 | 0.1321 | 0.9413 | 0.6648 |
| 0.236 | 5.0 | 2280 | 0.1359 | 0.9438 | 0.6724 |
Framework versions
- Transformers 4.55.2
- Pytorch 2.8.0+cu128
- Datasets 3.6.0
- Tokenizers 0.21.4