gustavokpc/bert-base-portuguese-cased_LRATE_1e-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: 0.0570
• Train Accuracy: 0.9806
• Train F1 M: 0.5606
• Train Precision M: 0.4043
• Train Recall M: 0.9769
• Validation Loss: 0.1851
• Validation Accuracy: 0.9446
• Validation F1 M: 0.5629
• Validation Precision M: 0.4035
• Validation Recall M: 0.9763
• Epoch: 4

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': 1e-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
0.2400	0.9057	0.5084	0.3774	0.8407	0.1924	0.9294	0.5681	0.4101	0.9715	0
0.1325	0.9529	0.5557	0.4036	0.9509	0.1685	0.9367	0.5519	0.3998	0.9380	1
0.0929	0.9681	0.5582	0.4031	0.9644	0.1650	0.9426	0.5583	0.4027	0.9554	2
0.0703	0.9764	0.5599	0.4042	0.9720	0.1808	0.9426	0.5670	0.4068	0.9794	3
0.0570	0.9806	0.5606	0.4043	0.9769	0.1851	0.9446	0.5629	0.4035	0.9763	4

Framework versions

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