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	4	9.1901	0.0018	9.1901	3.0315
No log	2.0	8	5.4205	0.0386	5.4205	2.3282
No log	3.0	12	2.9717	0.0118	2.9717	1.7238
No log	4.0	16	1.5918	0.0420	1.5918	1.2617
No log	5.0	20	1.2733	0.0420	1.2733	1.1284
No log	6.0	24	1.5406	0.1027	1.5406	1.2412
No log	7.0	28	1.1345	0.1445	1.1345	1.0651
No log	8.0	32	1.3971	0.1725	1.3971	1.1820
No log	9.0	36	0.8656	0.3243	0.8656	0.9304
No log	10.0	40	0.7114	0.4776	0.7114	0.8434
No log	11.0	44	0.7003	0.4744	0.7003	0.8368
No log	12.0	48	0.6584	0.4467	0.6584	0.8114
No log	13.0	52	0.8664	0.4395	0.8664	0.9308
No log	14.0	56	0.6137	0.4699	0.6137	0.7834
No log	15.0	60	0.7594	0.4605	0.7594	0.8714
No log	16.0	64	0.8403	0.4929	0.8403	0.9167
No log	17.0	68	0.7063	0.5488	0.7063	0.8404
No log	18.0	72	0.7131	0.4775	0.7131	0.8445
No log	19.0	76	0.8500	0.4406	0.8500	0.9219
No log	20.0	80	0.7284	0.4959	0.7284	0.8535
No log	21.0	84	0.9963	0.4314	0.9963	0.9982
No log	22.0	88	0.7166	0.5221	0.7166	0.8465
No log	23.0	92	0.7397	0.5095	0.7397	0.8601
No log	24.0	96	0.7315	0.4999	0.7315	0.8553
No log	25.0	100	0.7295	0.4840	0.7295	0.8541
No log	26.0	104	0.7584	0.4399	0.7584	0.8709
No log	27.0	108	1.1138	0.4110	1.1138	1.0554
No log	28.0	112	0.6870	0.5474	0.6870	0.8289
No log	29.0	116	0.9406	0.3941	0.9406	0.9698
No log	30.0	120	0.7302	0.4801	0.7302	0.8545
No log	31.0	124	1.0419	0.3748	1.0419	1.0207
No log	32.0	128	0.7185	0.4467	0.7185	0.8477

genki10/BERT_AugV8_k5_task1_organization_sp060_lw030_fold4

BERT_AugV8_k5_task1_organization_sp060_lw030_fold4