bertimbau-base-finetuned-lener-br-finetuned-peticoes-assuntos
This model is a fine-tuned version of Luciano/bertimbau-base-finetuned-lener-br on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9930
- Accuracy: 0.3575
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.7305 | 1.0 | 898 | 3.6586 | 0.2533 |
| 3.4793 | 2.0 | 1796 | 3.2827 | 0.3029 |
| 3.0791 | 3.0 | 2694 | 3.0938 | 0.3427 |
| 2.83 | 4.0 | 3592 | 3.0101 | 0.3477 |
| 2.7427 | 5.0 | 4490 | 2.9930 | 0.3575 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1