my_model_
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: 0.0661
- Precision: 0.9465
- Recall: 0.9687
- F1: 0.9574
- Accuracy: 0.9847
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 233 | 0.0729 | 0.9346 | 0.9642 | 0.9492 | 0.9826 |
| No log | 2.0 | 466 | 0.0669 | 0.9442 | 0.9696 | 0.9567 | 0.9844 |
| 0.1286 | 3.0 | 699 | 0.0661 | 0.9465 | 0.9687 | 0.9574 | 0.9847 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1