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
0.3501	1.0	659	0.2838	0.6629	0.8057	0.5313
0.2605	2.0	1318	0.2387	0.7122	0.8282	0.5687
0.2164	3.0	1977	0.2381	0.7231	0.8249	0.6355
0.1468	4.0	2636	0.2437	0.7455	0.8429	0.6524
0.1172	5.0	3295	0.2534	0.7517	0.8422	0.6553
0.1019	6.0	3954	0.2661	0.7545	0.8481	0.6557
0.0695	7.0	4613	0.2833	0.7597	0.8512	0.6735
0.0568	8.0	5272	0.2976	0.7615	0.8553	0.6824
0.0508	9.0	5931	0.3146	0.7649	0.8602	0.6809
0.0366	10.0	6590	0.3294	0.7583	0.8454	0.6929
0.0299	11.0	7249	0.3407	0.7667	0.8626	0.6875
0.0262	12.0	7908	0.3437	0.7706	0.8622	0.6940
0.0195	13.0	8567	0.3481	0.7707	0.8603	0.7010
0.0176	14.0	9226	0.3543	0.7722	0.8657	0.7010
0.0151	15.0	9885	0.3566	0.7711	0.8642	0.6978

PaceKW/indobert-base-uncased-multilabel-indonesian-hate-speech-new

indobert-base-uncased-multilabel-indonesian-hate-speech-new