Modelpublic

gabriel-hf/bert-hate-speech-ptbr

sourceHugging Faceapache-2.0updated 10mo agoView on Hugging Face

0likes11downloads

Model Card

gabriel-hf/bert-hate-speech-ptbr

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

—Loss: 0.0646
—Accuracy: 0.9896

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:

—learning_rate: 5e-05
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0894	0.2312	200	0.0639	0.9890
0.0665	0.4624	400	0.0747	0.9890
0.034	0.6936	600	0.0763	0.9890
0.1097	0.9249	800	0.0671	0.9890
0.0478	1.1561	1000	0.0716	0.9890
0.1024	1.3873	1200	0.0604	0.9890
0.0702	1.6185	1400	0.0669	0.9890
0.0614	1.8497	1600	0.0708	0.9890
0.0526	2.0809	1800	0.0720	0.9890
0.0628	2.3121	2000	0.0696	0.9890
0.0702	2.5434	2200	0.0660	0.9890
0.0633	2.7746	2400	0.0696	0.9890
0.104	3.0058	2600	0.0624	0.9890
0.0543	3.2370	2800	0.0684	0.9890
0.0763	3.4682	3000	0.0671	0.9890
0.0911	3.6994	3200	0.0638	0.9890
0.0805	3.9306	3400	0.0677	0.9890
0.0875	4.1618	3600	0.0751	0.9861
0.0392	4.3931	3800	0.0752	0.9890
0.0516	4.6243	4000	0.0607	0.9890
0.0609	4.8555	4200	0.0646	0.9896

Framework versions

—Transformers 4.57.1
—Pytorch 2.9.0+cu126
—Datasets 4.0.0
—Tokenizers 0.22.1