You can deploy this model and start earning money today!

PaceKW/
bert-base-multilingual-uncased-multilabel-indonesian-hate-speech-modified

Name: bert-base-multilingual-uncased-multilabel-indonesian-hate-speech-modified
Availability: InStock

Views

No views yet

bert-base-multilingual-uncased-multilabel-indonesian-hate-speech-modified

This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

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
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.2629	1.0	1317	0.2287	0.7077	0.7990	0.6135
0.1953	2.0	2634	0.2081	0.7501	0.8357	0.6393
0.1604	3.0	3951	0.2065	0.7741	0.8509	0.6955
0.1237	4.0	5268	0.2283	0.7645	0.8503	0.6978
0.0942	5.0	6585	0.2499	0.7813	0.8631	0.7206
0.0687	6.0	7902	0.2639	0.7741	0.8629	0.7008
0.0506	7.0	9219	0.2991	0.7812	0.8678	0.7267
0.0402	8.0	10536	0.3122	0.7796	0.8585	0.7289
0.0261	9.0	11853	0.3437	0.7744	0.8671	0.7092
0.0223	10.0	13170	0.3687	0.7755	0.8651	0.7153
0.0176	11.0	14487	0.3868	0.7674	0.8561	0.7130
0.0132	12.0	15804	0.3760	0.7780	0.8600	0.7282
0.0111	13.0	17121	0.3927	0.7797	0.8690	0.7175
0.0078	14.0	18438	0.3943	0.7755	0.8635	0.7168
0.0065	15.0	19755	0.4001	0.7772	0.8628	0.7175