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	7	6.3601	0.0	6.3579	2.5215
No log	2.0	14	2.2720	0.1856	2.2702	1.5067
No log	3.0	21	0.9932	0.0	0.9919	0.9959
No log	4.0	28	1.3763	0.0276	1.3748	1.1725
No log	5.0	35	0.9447	0.0983	0.9434	0.9713
No log	6.0	42	0.8239	0.2764	0.8227	0.9071
No log	7.0	49	0.7475	0.2919	0.7464	0.8639
No log	8.0	56	1.1985	0.1826	1.1975	1.0943
No log	9.0	63	1.7932	0.1227	1.7928	1.3389
No log	10.0	70	0.8362	0.3862	0.8358	0.9142
No log	11.0	77	0.9780	0.2599	0.9773	0.9886
No log	12.0	84	1.4851	0.2019	1.4846	1.2184
No log	13.0	91	1.4098	0.2250	1.4093	1.1872
No log	14.0	98	1.0539	0.2783	1.0535	1.0264
No log	15.0	105	1.1363	0.2416	1.1358	1.0657
No log	16.0	112	1.3285	0.2137	1.3280	1.1524
No log	17.0	119	1.8759	0.1420	1.8753	1.3694
No log	18.0	126	1.2443	0.2450	1.2436	1.1152
No log	19.0	133	1.3491	0.2318	1.3485	1.1612
No log	20.0	140	1.4626	0.1973	1.4618	1.2091
No log	21.0	147	1.0108	0.2388	1.0100	1.0050
No log	22.0	154	1.0993	0.2709	1.0986	1.0482
No log	23.0	161	1.1308	0.2524	1.1301	1.0631
No log	24.0	168	0.9679	0.2722	0.9671	0.9834
No log	25.0	175	0.9176	0.2795	0.9169	0.9576

genki10/BERT_AugV8_k10_task1_organization_sp020_lw030_fold1

BERT_AugV8_k10_task1_organization_sp020_lw030_fold1