gustavokpc/bert-base-portuguese-cased_LRATE_1e-06_EPOCHS_10

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: 0.1478
• Train Accuracy: 0.9481
• Train F1 M: 0.5518
• Train Precision M: 0.4013
• Train Recall M: 0.9436
• Validation Loss: 0.1862
• Validation Accuracy: 0.9307
• Validation F1 M: 0.5600
• Validation Precision M: 0.4033
• Validation Recall M: 0.9613
• Epoch: 9

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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-06, 'decay_steps': 7580, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, '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
0.4813	0.7972	0.2411	0.2093	0.3344	0.2665	0.9090	0.5217	0.3877	0.8393	0
0.2432	0.9126	0.5317	0.3942	0.8764	0.2185	0.9169	0.5490	0.3979	0.9239	1
0.2054	0.9262	0.5438	0.3981	0.9151	0.2059	0.9222	0.5441	0.3948	0.9188	2
0.1883	0.9300	0.5471	0.3992	0.9253	0.1970	0.9294	0.5504	0.3977	0.9356	3
0.1771	0.9359	0.5494	0.4011	0.9339	0.1918	0.9268	0.5550	0.4005	0.9486	4
0.1632	0.9418	0.5507	0.4016	0.9369	0.1889	0.9294	0.5578	0.4023	0.9538	5
0.1591	0.9436	0.5507	0.4023	0.9416	0.1878	0.9307	0.5547	0.4005	0.9464	6
0.1536	0.9452	0.5529	0.4028	0.9419	0.1871	0.9301	0.5561	0.4010	0.9521	7
0.1512	0.9471	0.5514	0.4012	0.9396	0.1864	0.9307	0.5599	0.4032	0.9613	8
0.1478	0.9481	0.5518	0.4013	0.9436	0.1862	0.9307	0.5600	0.4033	0.9613	9

Framework versions

• Transformers 4.37.2
• TensorFlow 2.15.0
• Datasets 2.16.1
• Tokenizers 0.15.1