learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
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: linear
num_epochs: 150

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	8	5.8256	0.0203	5.8256	2.4136
No log	2.0	16	2.5991	0.0046	2.5991	1.6122
No log	3.0	24	1.6691	0.0212	1.6691	1.2919
No log	4.0	32	1.5520	0.0212	1.5520	1.2458
No log	5.0	40	1.0416	0.0564	1.0416	1.0206
No log	6.0	48	0.9078	0.1563	0.9078	0.9528
No log	7.0	56	1.1098	0.0401	1.1098	1.0535
No log	8.0	64	1.2687	0.0373	1.2687	1.1264
No log	9.0	72	2.1799	0.0074	2.1799	1.4764
No log	10.0	80	1.1075	0.0283	1.1075	1.0524
No log	11.0	88	1.0643	0.0527	1.0643	1.0316
No log	12.0	96	1.5839	-0.0254	1.5839	1.2585
No log	13.0	104	1.3669	0.0440	1.3669	1.1691
No log	14.0	112	1.6440	0.0297	1.6440	1.2822
No log	15.0	120	1.3880	0.0416	1.3880	1.1781
No log	16.0	128	1.8376	-0.0281	1.8376	1.3556
No log	17.0	136	1.4309	0.0108	1.4309	1.1962
No log	18.0	144	1.2547	0.0826	1.2547	1.1201
No log	19.0	152	2.1650	-0.0405	2.1650	1.4714
No log	20.0	160	1.6114	-0.0359	1.6114	1.2694
No log	21.0	168	1.2137	0.1288	1.2137	1.1017

genki10/BERT_AugV8_k10_task1_organization_sp060_lw030_fold0

BERT_AugV8_k10_task1_organization_sp060_lw030_fold0