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	5	7.0416	0.0	7.0416	2.6536
No log	2.0	10	4.9090	0.0115	4.9090	2.2156
No log	3.0	15	2.7793	0.0	2.7793	1.6671
No log	4.0	20	1.4306	0.0316	1.4306	1.1961
No log	5.0	25	0.9499	0.0316	0.9499	0.9746
No log	6.0	30	0.9291	0.0538	0.9291	0.9639
No log	7.0	35	0.8726	0.2520	0.8726	0.9341
No log	8.0	40	0.8869	0.3606	0.8869	0.9418
No log	9.0	45	0.7057	0.4085	0.7057	0.8401
No log	10.0	50	0.6208	0.3891	0.6208	0.7879
No log	11.0	55	0.9168	0.3714	0.9168	0.9575
No log	12.0	60	0.9299	0.3598	0.9299	0.9643
No log	13.0	65	0.9479	0.3470	0.9479	0.9736
No log	14.0	70	0.9355	0.3557	0.9355	0.9672
No log	15.0	75	1.4375	0.2436	1.4375	1.1990
No log	16.0	80	0.8071	0.4365	0.8071	0.8984
No log	17.0	85	0.8142	0.4247	0.8142	0.9023
No log	18.0	90	0.8702	0.3871	0.8702	0.9328
No log	19.0	95	0.8993	0.4109	0.8993	0.9483
No log	20.0	100	1.0391	0.2957	1.0391	1.0194
No log	21.0	105	1.0083	0.3089	1.0083	1.0041
No log	22.0	110	0.8635	0.3759	0.8635	0.9292
No log	23.0	115	0.8527	0.4008	0.8527	0.9234
No log	24.0	120	0.8371	0.4014	0.8371	0.9150
No log	25.0	125	0.9850	0.3267	0.9850	0.9925
No log	26.0	130	1.0402	0.3202	1.0402	1.0199
No log	27.0	135	1.0939	0.3010	1.0939	1.0459
No log	28.0	140	0.8335	0.3455	0.8335	0.9130
No log	29.0	145	1.1059	0.2706	1.1059	1.0516
No log	30.0	150	0.8931	0.3587	0.8931	0.9450
No log	31.0	155	0.9007	0.3688	0.9007	0.9490

genki10/Trial3BERT_AugV8_k7_task1_organization_sp050_lw010_fold0

Trial3BERT_AugV8_k7_task1_organization_sp050_lw010_fold0