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	8.5323	0.0	8.5309	2.9208
No log	2.0	12	3.5660	0.0076	3.5652	1.8882
No log	3.0	18	1.5180	0.0365	1.5174	1.2318
No log	4.0	24	2.2270	0.1059	2.2263	1.4921
No log	5.0	30	1.0896	0.0202	1.0893	1.0437
No log	6.0	36	1.7108	0.0328	1.7104	1.3078
No log	7.0	42	1.1429	0.1044	1.1429	1.0691
No log	8.0	48	0.9151	0.2874	0.9156	0.9569
No log	9.0	54	0.9018	0.2895	0.9024	0.9499
No log	10.0	60	0.9988	0.2602	0.9995	0.9998
No log	11.0	66	0.8511	0.2626	0.8517	0.9229
No log	12.0	72	2.0838	0.0921	2.0841	1.4436
No log	13.0	78	3.2108	0.0097	3.2103	1.7917
No log	14.0	84	1.3319	0.1879	1.3324	1.1543
No log	15.0	90	0.8512	0.3453	0.8518	0.9229
No log	16.0	96	1.7537	0.1051	1.7537	1.3243
No log	17.0	102	2.5601	0.0482	2.5598	1.5999
No log	18.0	108	1.5055	0.1614	1.5060	1.2272
No log	19.0	114	1.4346	0.1422	1.4351	1.1980
No log	20.0	120	2.0682	0.0805	2.0681	1.4381
No log	21.0	126	2.0858	0.0610	2.0854	1.4441
No log	22.0	132	1.7805	0.0712	1.7804	1.3343
No log	23.0	138	1.8365	0.0800	1.8364	1.3552
No log	24.0	144	2.5830	0.0524	2.5826	1.6071
No log	25.0	150	1.1549	0.2436	1.1556	1.0750
No log	26.0	156	1.0064	0.2864	1.0072	1.0036
No log	27.0	162	2.0123	0.0858	2.0124	1.4186
No log	28.0	168	2.6962	0.0604	2.6958	1.6419
No log	29.0	174	1.6363	0.1189	1.6365	1.2792
No log	30.0	180	1.4734	0.1526	1.4736	1.2139

genki10/BERT_AugV8_k7_task1_organization_sp010_lw070_fold3

BERT_AugV8_k7_task1_organization_sp010_lw070_fold3