gustavokpc/bert-base-portuguese-cased_LRATE_1e-05_EPOCHS_7

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: 0.0650
• Train Accuracy: 0.9758
• Train F1 M: 0.5601
• Train Precision M: 0.4039
• Train Recall M: 0.9754
• Validation Loss: 0.1751
• Validation Accuracy: 0.9466
• Validation F1 M: 0.5620
• Validation Precision M: 0.4036
• Validation Recall M: 0.9696
• 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': 1e-05, 'decay_steps': 5306, '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
0.2473	0.9048	0.5004	0.3720	0.8254	0.1669	0.9340	0.5489	0.3976	0.9281	0
0.1350	0.9505	0.5530	0.4016	0.9485	0.1610	0.9420	0.5661	0.4073	0.9706	1
0.0890	0.9685	0.5595	0.4035	0.9677	0.1719	0.9446	0.5691	0.4082	0.9825	2
0.0650	0.9758	0.5601	0.4039	0.9754	0.1751	0.9466	0.5620	0.4036	0.9696	3

Framework versions

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