gustavokpc/bert-base-portuguese-cased_LRATE_8e-06_EPOCHS_6

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: 0.0760
• Train Accuracy: 0.9736
• Train F1 M: 0.5546
• Train Precision M: 0.4022
• Train Recall M: 0.9573
• Validation Loss: 0.1946
• Validation Accuracy: 0.9373
• Validation F1 M: 0.5597
• Validation Precision M: 0.4031
• Validation Recall M: 0.9604
• Epoch: 3

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': 8e-06, 'decay_steps': 4548, '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
0.2551	0.8979	0.4816	0.3610	0.7830	0.1728	0.9321	0.5389	0.3930	0.9010	0
0.1422	0.9482	0.5464	0.3984	0.9255	0.1703	0.9334	0.5630	0.4084	0.9522	1
0.1011	0.9626	0.5514	0.4011	0.9448	0.1802	0.9400	0.5506	0.3983	0.9366	2
0.0760	0.9736	0.5546	0.4022	0.9573	0.1946	0.9373	0.5597	0.4031	0.9604	3

Framework versions

• Transformers 4.34.1
• TensorFlow 2.10.0
• Datasets 2.14.5
• Tokenizers 0.14.1