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
0.3522	1.0	170	0.3363	0.0	0.5	0.4009
0.3151	2.0	340	0.2986	0.0046	0.5010	0.4024
0.275	3.0	510	0.2839	0.1828	0.5760	0.4480
0.2398	4.0	680	0.2658	0.2440	0.6088	0.4775
0.2262	5.0	850	0.2434	0.3808	0.6624	0.5468
0.1922	6.0	1020	0.2215	0.4540	0.7054	0.5932
0.167	7.0	1190	0.2103	0.4839	0.7109	0.6021
0.1668	8.0	1360	0.2017	0.6163	0.7905	0.6139
0.1357	9.0	1530	0.1938	0.6076	0.7741	0.6529
0.118	10.0	1700	0.2072	0.5860	0.7642	0.6220
0.1076	11.0	1870	0.1881	0.6222	0.7799	0.6728
0.1118	12.0	2040	0.1785	0.6688	0.8074	0.6912
0.0932	13.0	2210	0.1691	0.7133	0.8296	0.7038
0.079	14.0	2380	0.1799	0.6766	0.8135	0.7067
0.083	15.0	2550	0.1621	0.7358	0.8429	0.7332
0.0613	16.0	2720	0.1663	0.7316	0.8373	0.7406
0.0737	17.0	2890	0.1637	0.7400	0.8425	0.7458
0.064	18.0	3060	0.1631	0.7352	0.8376	0.7465
0.0593	19.0	3230	0.1617	0.7425	0.8416	0.7524
0.0628	20.0	3400	0.1613	0.7399	0.8399	0.7502

Kuongan/xlm-roberta-base-som-finetuned-RC

xlm-roberta-base-som-finetuned-RC