metadata

license: mit
base_model: neuralmind/bert-base-portuguese-cased
tags:
  - generated_from_keras_callback
model-index:
  - name: gustavokpc/bert-base-portuguese-cased_LRATE_5e-06_EPOCHS_6
    results: []

gustavokpc/bert-base-portuguese-cased_LRATE_5e-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: 0.0811
Train Accuracy: 0.9728
Train F1 M: 0.5572
Train Precision M: 0.4036
Train Recall M: 0.9646
Validation Loss: 0.1804
Validation Accuracy: 0.9387
Validation F1 M: 0.5549
Validation Precision M: 0.3999
Validation Recall M: 0.9504
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': 5e-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
0.2887	0.8821	0.4544	0.3418	0.7393	0.1871	0.9321	0.5574	0.4039	0.9455	0
0.1571	0.9439	0.5463	0.3992	0.9299	0.1740	0.9321	0.5596	0.4040	0.9542	1
0.1185	0.9587	0.5529	0.4020	0.9480	0.1714	0.9367	0.5588	0.4030	0.9555	2
0.0950	0.9662	0.5572	0.4033	0.9621	0.1775	0.9373	0.5604	0.4033	0.9607	3
0.0811	0.9728	0.5572	0.4036	0.9646	0.1804	0.9387	0.5549	0.3999	0.9504	4

Framework versions

Transformers 4.34.1
TensorFlow 2.10.0
Datasets 2.14.5
Tokenizers 0.14.1