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	2	8.6230	0.0037	8.6230	2.9365
No log	2.0	4	5.5221	0.0274	5.5221	2.3499
No log	3.0	6	4.3453	0.0118	4.3453	2.0845
No log	4.0	8	3.3370	0.0079	3.3370	1.8267
No log	5.0	10	2.7258	0.0040	2.7258	1.6510
No log	6.0	12	2.1882	0.0851	2.1882	1.4793
No log	7.0	14	1.8458	0.0420	1.8458	1.3586
No log	8.0	16	1.5229	0.0420	1.5229	1.2341
No log	9.0	18	1.3691	0.0847	1.3691	1.1701
No log	10.0	20	1.3172	0.1173	1.3172	1.1477
No log	11.0	22	0.9325	0.0722	0.9325	0.9657
No log	12.0	24	0.8395	0.0962	0.8395	0.9163
No log	13.0	26	0.8276	0.2522	0.8276	0.9097
No log	14.0	28	1.5588	0.2600	1.5588	1.2485
No log	15.0	30	1.7647	0.2704	1.7647	1.3284
No log	16.0	32	1.8464	0.2684	1.8464	1.3588
No log	17.0	34	1.8261	0.2684	1.8261	1.3513
No log	18.0	36	1.3561	0.2654	1.3561	1.1645
No log	19.0	38	0.6765	0.5488	0.6765	0.8225
No log	20.0	40	0.6503	0.5735	0.6503	0.8064
No log	21.0	42	1.1416	0.2703	1.1416	1.0685
No log	22.0	44	1.4302	0.2525	1.4302	1.1959
No log	23.0	46	0.8579	0.4101	0.8579	0.9262
No log	24.0	48	0.6094	0.5249	0.6094	0.7806
No log	25.0	50	0.6447	0.5286	0.6447	0.8029
No log	26.0	52	1.1798	0.3061	1.1798	1.0862
No log	27.0	54	0.9188	0.4133	0.9188	0.9586
No log	28.0	56	0.5912	0.5285	0.5912	0.7689
No log	29.0	58	0.5946	0.5434	0.5946	0.7711
No log	30.0	60	0.9485	0.4339	0.9485	0.9739
No log	31.0	62	1.4224	0.3135	1.4224	1.1926
No log	32.0	64	0.8403	0.4742	0.8403	0.9167
No log	33.0	66	0.6577	0.4866	0.6577	0.8110
No log	34.0	68	0.7240	0.4798	0.7240	0.8509
No log	35.0	70	0.9880	0.3511	0.9880	0.9940

genki10/BERT_AugV8_k1_task1_organization_sp060_lw030_fold4

BERT_AugV8_k1_task1_organization_sp060_lw030_fold4