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	6	8.3077	0.0018	8.3076	2.8823
No log	2.0	12	4.3036	0.0123	4.3041	2.0746
No log	3.0	18	2.4889	0.0176	2.4895	1.5778
No log	4.0	24	1.2478	0.0213	1.2483	1.1173
No log	5.0	30	2.1535	-0.0789	2.1533	1.4674
No log	6.0	36	1.0332	0.0136	1.0336	1.0166
No log	7.0	42	0.8575	0.2716	0.8578	0.9262
No log	8.0	48	0.7698	0.3625	0.7700	0.8775
No log	9.0	54	0.6827	0.3542	0.6829	0.8264
No log	10.0	60	0.9624	0.0970	0.9628	0.9812
No log	11.0	66	0.9881	0.1315	0.9884	0.9942
No log	12.0	72	0.7948	0.2406	0.7949	0.8916
No log	13.0	78	0.9394	0.1650	0.9395	0.9693
No log	14.0	84	1.2968	0.0134	1.2968	1.1388
No log	15.0	90	1.3846	-0.0625	1.3846	1.1767
No log	16.0	96	1.6841	-0.2372	1.6841	1.2977
No log	17.0	102	1.3739	-0.0591	1.3742	1.1723
No log	18.0	108	1.5307	-0.1004	1.5310	1.2373
No log	19.0	114	1.7846	-0.2123	1.7846	1.3359
No log	20.0	120	1.9862	-0.2473	1.9861	1.4093
No log	21.0	126	1.6753	-0.0947	1.6754	1.2944
No log	22.0	132	1.6899	-0.1917	1.6900	1.3000
No log	23.0	138	1.8074	-0.2632	1.8076	1.3445

genki10/BERT_AugV8_k7_task1_organization_sp040_lw040_fold2

BERT_AugV8_k7_task1_organization_sp040_lw040_fold2