learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.6354	1.0	61	0.6015	0.0208	0.5056	0.1463
0.4919	2.0	122	0.4256	0.4526	0.6896	0.3008
0.4178	3.0	183	0.3842	0.5266	0.7193	0.3577
0.3592	4.0	244	0.3720	0.6510	0.7751	0.4065
0.3122	5.0	305	0.3901	0.6165	0.7589	0.4390
0.2941	6.0	366	0.3834	0.6817	0.7886	0.3984
0.2558	7.0	427	0.3634	0.6841	0.7945	0.4553
0.2337	8.0	488	0.4079	0.6820	0.7824	0.3902
0.2208	9.0	549	0.4187	0.6656	0.7800	0.3740
0.198	10.0	610	0.4166	0.6858	0.7838	0.3902
0.1813	11.0	671	0.4107	0.6886	0.7895	0.3984
0.1689	12.0	732	0.4313	0.6907	0.7912	0.4065
0.1431	13.0	793	0.4393	0.7035	0.7953	0.3821
0.131	14.0	854	0.4399	0.6805	0.7787	0.3740
0.1227	15.0	915	0.4599	0.6952	0.7923	0.3984
0.1009	16.0	976	0.4618	0.6712	0.7723	0.3659
0.1025	17.0	1037	0.4569	0.6844	0.7842	0.3902

Kuongan/xlm-roberta-base-ron-finetuned

xlm-roberta-base-ron-finetuned