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	5.8742	0.0201	5.8742	2.4237
No log	2.0	16	2.5397	0.0486	2.5397	1.5936
No log	3.0	24	1.3876	0.0316	1.3876	1.1780
No log	4.0	32	1.0636	0.0463	1.0636	1.0313
No log	5.0	40	0.9513	0.0558	0.9513	0.9753
No log	6.0	48	0.7673	0.1990	0.7673	0.8760
No log	7.0	56	0.9039	0.1047	0.9039	0.9508
No log	8.0	64	1.6779	-0.1319	1.6779	1.2954
No log	9.0	72	1.3567	0.0026	1.3567	1.1648
No log	10.0	80	1.6884	-0.0511	1.6884	1.2994
No log	11.0	88	1.2450	0.0406	1.2450	1.1158
No log	12.0	96	1.1428	0.0662	1.1428	1.0690
No log	13.0	104	2.2909	-0.0939	2.2909	1.5136
No log	14.0	112	1.6484	0.0440	1.6484	1.2839
No log	15.0	120	1.6149	-0.0049	1.6149	1.2708
No log	16.0	128	1.9296	-0.0342	1.9296	1.3891
No log	17.0	136	2.5331	-0.0910	2.5331	1.5916
No log	18.0	144	1.4974	-0.0305	1.4974	1.2237
No log	19.0	152	2.7080	-0.0586	2.7080	1.6456
No log	20.0	160	1.3682	0.0586	1.3682	1.1697
No log	21.0	168	1.5050	0.0392	1.5050	1.2268

genki10/BERT_AugV8_k10_task1_organization_sp020_lw070_fold0

BERT_AugV8_k10_task1_organization_sp020_lw070_fold0