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	5	11.6213	-0.0119	11.6213	3.4090
No log	2.0	10	6.8480	0.0	6.8483	2.6169
No log	3.0	15	3.6255	0.0039	3.6259	1.9042
No log	4.0	20	1.5792	0.0422	1.5797	1.2569
No log	5.0	25	1.0475	0.0107	1.0480	1.0237
No log	6.0	30	0.8982	0.1117	0.8987	0.9480
No log	7.0	35	1.0904	0.1028	1.0905	1.0443
No log	8.0	40	0.9098	0.1585	0.9101	0.9540
No log	9.0	45	0.7474	0.2186	0.7474	0.8645
No log	10.0	50	0.8154	0.2003	0.8155	0.9030
No log	11.0	55	0.6567	0.3969	0.6564	0.8102
No log	12.0	60	0.8070	0.3846	0.8066	0.8981
No log	13.0	65	1.2853	0.0449	1.2857	1.1339
No log	14.0	70	1.3446	0.0626	1.3444	1.1595
No log	15.0	75	1.2436	0.1338	1.2435	1.1151
No log	16.0	80	1.3581	0.0846	1.3580	1.1654
No log	17.0	85	1.5030	0.0063	1.5030	1.2260
No log	18.0	90	1.1629	0.0949	1.1628	1.0783
No log	19.0	95	1.4977	0.0312	1.4977	1.2238
No log	20.0	100	1.2065	0.0965	1.2064	1.0984
No log	21.0	105	1.2364	0.0232	1.2367	1.1120
No log	22.0	110	1.2001	0.0632	1.2001	1.0955
No log	23.0	115	0.9863	0.1598	0.9862	0.9931
No log	24.0	120	1.3749	0.0314	1.3751	1.1727
No log	25.0	125	1.3610	0.0150	1.3613	1.1667
No log	26.0	130	1.3016	0.0458	1.3018	1.1410

genki10/BERT_AugV8_k7_task1_organization_sp040_lw010_fold2

BERT_AugV8_k7_task1_organization_sp040_lw010_fold2