Modelpublic

gustavokpc/IC_primeiro

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes6downloads

Model Card

gustavokpc/IC_primeiro

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

—Train Loss: 0.0532
—Train Accuracy: 0.9812
—Train F1 M: 0.5544
—Train Precision M: 0.4027
—Train Recall M: 0.9558
—Validation Loss: 0.2580
—Validation Accuracy: 0.9175
—Validation F1 M: 0.5588
—Validation Precision M: 0.4059
—Validation Recall M: 0.9423
—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', 'weightdecay': None, 'clipnorm': None, 'globalclipnorm': None, 'clipvalue': None, 'useema': False, 'emamomentum': 0.99, 'emaoverwritefrequency': None, 'jitcompile': False, 'islegacyoptimizer': False, 'learningrate': {'module': 'keras.optimizers.schedules', 'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 2e-05, 'decaysteps': 3790, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registeredname': None}, 'beta1': 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
0.3533	0.8498	0.4723	0.4085	0.6530	0.2424	0.9037	0.5060	0.3909	0.7591	0
0.1974	0.9259	0.5184	0.3930	0.8161	0.1978	0.9202	0.5425	0.4014	0.8778	1
0.1242	0.9551	0.5382	0.3974	0.8918	0.1970	0.9248	0.5583	0.4106	0.9195	2
0.0823	0.9705	0.5511	0.4024	0.9370	0.2550	0.9116	0.5567	0.4057	0.9330	3
0.0532	0.9812	0.5544	0.4027	0.9558	0.2580	0.9175	0.5588	0.4059	0.9423	4

Framework versions

—Transformers 4.34.1
—TensorFlow 2.14.0
—Datasets 2.14.5
—Tokenizers 0.14.1