metadata
license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
- generated_from_keras_callback
model-index:
- name: gustavokpc/bert-base-portuguese-cased_LRATE_2e-05_EPOCHS_5
results: []
gustavokpc/bert-base-portuguese-cased_LRATE_2e-05_EPOCHS_5
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:
- Train Loss: 0.0733
- Train Accuracy: 0.9750
- Train F1 M: 0.5536
- Train Precision M: 0.4010
- Train Recall M: 0.9577
- Validation Loss: 0.1758
- Validation Accuracy: 0.9426
- Validation F1 M: 0.5568
- Validation Precision M: 0.4015
- Validation Recall M: 0.9529
- Epoch: 2
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:
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3790, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Train F1 M | Train Precision M | Train Recall M | Validation Loss | Validation Accuracy | Validation F1 M | Validation Precision M | Validation Recall M | Epoch |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.2270 | 0.9119 | 0.5181 | 0.3865 | 0.8561 | 0.1618 | 0.9367 | 0.5592 | 0.4050 | 0.9478 | 0 |
| 0.1186 | 0.9551 | 0.5516 | 0.4007 | 0.9397 | 0.1621 | 0.9347 | 0.5628 | 0.4068 | 0.9580 | 1 |
| 0.0733 | 0.9750 | 0.5536 | 0.4010 | 0.9577 | 0.1758 | 0.9426 | 0.5568 | 0.4015 | 0.9529 | 2 |
Framework versions
- Transformers 4.34.1
- TensorFlow 2.10.0
- Datasets 2.14.5
- Tokenizers 0.14.1