bert-base-indonesian-1.5G-multilabel-indonesian-hate-speech-modified-v3 – AI Model by PaceKW | AlphaNeural AI

You can deploy this model and start earning money today!

PaceKW/
bert-base-indonesian-1.5G-multilabel-indonesian-hate-speech-modified-v3

like

0

generated_from_trainer

cahya/bert-base-indonesian-1.5G

endpoints_compatible

Views

No views yet

bert-base-indonesian-1.5G-multilabel-indonesian-hate-speech-modified-v3

This model is a fine-tuned version of cahya/bert-base-indonesian-1.5G on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2123
F1: 0.7965
Roc Auc: 0.8744
Accuracy: 0.7115

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: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.2695	1.0	1317	0.2122	0.7390	0.8253	0.6234
0.1976	2.0	2634	0.2010	0.7734	0.8606	0.6446
0.1602	3.0	3951	0.1976	0.7902	0.8779	0.6864
0.1263	4.0	5268	0.2062	0.7930	0.8660	0.7175
0.1022	5.0	6585	0.2123	0.7965	0.8744	0.7115

Framework versions

Transformers 4.51.3
Pytorch 2.7.0+cu128
Datasets 3.6.0
Tokenizers 0.21.1