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	6	7.3587	0.0	7.3570	2.7124
No log	2.0	12	3.1456	0.0	3.1448	1.7734
No log	3.0	18	1.5370	0.0166	1.5363	1.2395
No log	4.0	24	2.6475	0.0042	2.6463	1.6267
No log	5.0	30	1.1431	0.0	1.1425	1.0689
No log	6.0	36	1.1775	0.0273	1.1770	1.0849
No log	7.0	42	0.9845	0.2849	0.9845	0.9922
No log	8.0	48	1.3357	0.1348	1.3344	1.1552
No log	9.0	54	2.4608	0.0733	2.4585	1.5680
No log	10.0	60	1.8559	0.1214	1.8539	1.3616
No log	11.0	66	1.7564	0.0766	1.7545	1.3246
No log	12.0	72	2.0160	0.0790	2.0141	1.4192
No log	13.0	78	1.5440	0.1598	1.5424	1.2419
No log	14.0	84	1.2638	0.1983	1.2626	1.1236
No log	15.0	90	2.2688	-0.0353	2.2665	1.5055
No log	16.0	96	2.3330	-0.0164	2.3307	1.5267
No log	17.0	102	2.1900	0.0108	2.1878	1.4791
No log	18.0	108	2.1733	0.0310	2.1713	1.4735
No log	19.0	114	2.1091	0.0565	2.1072	1.4516
No log	20.0	120	2.1922	0.0417	2.1902	1.4799
No log	21.0	126	2.3693	-0.0103	2.3670	1.5385
No log	22.0	132	2.6396	0.0185	2.6375	1.6240

genki10/BERT_AugV8_k7_task1_organization_sp060_lw030_fold3

BERT_AugV8_k7_task1_organization_sp060_lw030_fold3