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	5.8859	0.0115	5.8836	2.4256
No log	2.0	16	1.7898	0.0607	1.7881	1.3372
No log	3.0	24	1.6931	0.0379	1.6914	1.3005
No log	4.0	32	1.9593	-0.0017	1.9573	1.3990
No log	5.0	40	1.0529	0.1007	1.0514	1.0254
No log	6.0	48	0.9047	0.1428	0.9034	0.9505
No log	7.0	56	1.0940	0.1584	1.0928	1.0454
No log	8.0	64	1.1180	0.2082	1.1167	1.0567
No log	9.0	72	1.5089	0.2113	1.5071	1.2276
No log	10.0	80	0.9696	0.2955	0.9679	0.9838
No log	11.0	88	1.0905	0.2171	1.0888	1.0435
No log	12.0	96	2.4519	0.0721	2.4495	1.5651
No log	13.0	104	1.7314	0.1533	1.7293	1.3150
No log	14.0	112	1.1619	0.2463	1.1599	1.0770
No log	15.0	120	1.6895	0.1927	1.6874	1.2990
No log	16.0	128	1.4350	0.2088	1.4332	1.1972
No log	17.0	136	2.1320	0.0631	2.1295	1.4593
No log	18.0	144	1.3319	0.1593	1.3299	1.1532
No log	19.0	152	1.7050	0.1106	1.7031	1.3050
No log	20.0	160	1.4992	0.1386	1.4972	1.2236
No log	21.0	168	1.6193	0.1405	1.6174	1.2718
No log	22.0	176	1.2609	0.1948	1.2590	1.1221
No log	23.0	184	1.2556	0.1836	1.2538	1.1197
No log	24.0	192	1.0443	0.1975	1.0428	1.0212
No log	25.0	200	1.1367	0.1883	1.1352	1.0655

genki10/BERT_AugV8_k10_task1_organization_sp020_lw060_fold1

BERT_AugV8_k10_task1_organization_sp020_lw060_fold1