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	8	7.6390	0.0018	7.6390	2.7639
No log	2.0	16	3.3769	0.0079	3.3769	1.8376
No log	3.0	24	1.3111	0.0316	1.3111	1.1450
No log	4.0	32	1.1527	0.0316	1.1527	1.0737
No log	5.0	40	1.5605	0.1138	1.5605	1.2492
No log	6.0	48	1.4408	0.2178	1.4408	1.2003
No log	7.0	56	2.2113	0.0708	2.2113	1.4871
No log	8.0	64	2.1095	0.0967	2.1095	1.4524
No log	9.0	72	1.3612	0.1418	1.3612	1.1667
No log	10.0	80	0.9467	0.3490	0.9467	0.9730
No log	11.0	88	1.2184	0.2545	1.2184	1.1038
No log	12.0	96	1.0905	0.2771	1.0905	1.0443
No log	13.0	104	1.8609	0.1651	1.8609	1.3641
No log	14.0	112	2.2461	0.0961	2.2461	1.4987
No log	15.0	120	2.5907	0.1065	2.5907	1.6096
No log	16.0	128	1.6534	0.1867	1.6534	1.2859
No log	17.0	136	1.8642	0.1607	1.8642	1.3653
No log	18.0	144	2.0013	0.1252	2.0013	1.4147
No log	19.0	152	1.9328	0.1268	1.9328	1.3903
No log	20.0	160	2.3867	0.1018	2.3867	1.5449
No log	21.0	168	2.4350	0.0719	2.4350	1.5604
No log	22.0	176	1.9662	0.1218	1.9662	1.4022
No log	23.0	184	1.8695	0.1263	1.8695	1.3673
No log	24.0	192	2.2528	0.0980	2.2528	1.5009
No log	25.0	200	1.5814	0.1898	1.5814	1.2575

genki10/BERT_AugV8_k10_task1_organization_sp060_lw040_fold4

BERT_AugV8_k10_task1_organization_sp060_lw040_fold4