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	11.2772	-0.0187	11.2772	3.3581
No log	2.0	10	6.9059	0.0	6.9059	2.6279
No log	3.0	15	4.0796	0.0079	4.0796	2.0198
No log	4.0	20	2.0109	0.0558	2.0109	1.4181
No log	5.0	25	1.0397	0.0316	1.0397	1.0197
No log	6.0	30	0.8689	0.2524	0.8689	0.9321
No log	7.0	35	0.9583	0.0509	0.9583	0.9789
No log	8.0	40	0.8547	0.2488	0.8547	0.9245
No log	9.0	45	1.2091	0.1800	1.2091	1.0996
No log	10.0	50	1.4497	0.1922	1.4497	1.2040
No log	11.0	55	0.7388	0.4234	0.7388	0.8595
No log	12.0	60	1.1427	0.2837	1.1427	1.0690
No log	13.0	65	0.8399	0.3835	0.8399	0.9165
No log	14.0	70	0.8955	0.3642	0.8955	0.9463
No log	15.0	75	1.0395	0.3279	1.0395	1.0196
No log	16.0	80	1.8717	0.1828	1.8717	1.3681
No log	17.0	85	0.9201	0.3949	0.9201	0.9592
No log	18.0	90	1.4613	0.2195	1.4613	1.2088
No log	19.0	95	1.2626	0.2351	1.2626	1.1236
No log	20.0	100	1.0077	0.3077	1.0077	1.0039
No log	21.0	105	1.4793	0.2021	1.4793	1.2163
No log	22.0	110	1.4508	0.1936	1.4508	1.2045
No log	23.0	115	1.1021	0.2324	1.1021	1.0498
No log	24.0	120	1.1756	0.2146	1.1756	1.0842
No log	25.0	125	1.2388	0.2485	1.2388	1.1130
No log	26.0	130	1.1374	0.2599	1.1374	1.0665

genki10/BERT_AugV8_k7_task1_organization_sp020_lw030_fold4

BERT_AugV8_k7_task1_organization_sp020_lw030_fold4