metadata
library_name: transformers
license: mit
base_model: neuralmind/bert-large-portuguese-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test_trainer
results: []
test_trainer
This model is a fine-tuned version of neuralmind/bert-large-portuguese-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2830
- Accuracy: 0.4335
- F1-macro: 0.4110
- F1-micro: 0.4335
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: Use OptimizerNames.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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-macro | F1-micro |
|---|---|---|---|---|---|---|
| 1.3757 | 1.0 | 191 | 1.3268 | 0.3716 | 0.3142 | 0.3716 |
| 1.1447 | 2.0 | 382 | 1.2496 | 0.4197 | 0.4421 | 0.4197 |
| 0.8885 | 3.0 | 573 | 1.4038 | 0.4174 | 0.3850 | 0.4174 |
| 0.4716 | 4.0 | 764 | 1.7668 | 0.4243 | 0.4081 | 0.4243 |
| 0.2784 | 5.0 | 955 | 2.0514 | 0.4404 | 0.4047 | 0.4404 |
| 0.1178 | 6.0 | 1146 | 2.2830 | 0.4335 | 0.4110 | 0.4335 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0