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: 100

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.2334	1.0	1148	0.2260	0.7302	0.8204	0.6179
0.1693	2.0	2296	0.2107	0.7656	0.8493	0.6581
0.1171	3.0	3444	0.2374	0.7767	0.8543	0.6893
0.0819	4.0	4592	0.2665	0.7746	0.8498	0.6983
0.0531	5.0	5740	0.2861	0.7810	0.8574	0.6928
0.0362	6.0	6888	0.3174	0.7840	0.8695	0.6948
0.0303	7.0	8036	0.3597	0.7731	0.8447	0.7097
0.0249	8.0	9184	0.3791	0.7763	0.8542	0.7127
0.0202	9.0	10332	0.3736	0.7904	0.8724	0.7082
0.0172	10.0	11480	0.4195	0.7683	0.8505	0.6973
0.0148	11.0	12628	0.4318	0.7789	0.8598	0.7097
0.0164	12.0	13776	0.4472	0.7843	0.8698	0.7211

PaceKW/bert-base-indonesian-1.5G-multilabel-indonesian-hate-speech-100

bert-base-indonesian-1.5G-multilabel-indonesian-hate-speech-100