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	8.3757	0.0	8.3743	2.8938
No log	2.0	10	5.7119	0.0334	5.7106	2.3897
No log	3.0	15	2.6744	0.0215	2.6736	1.6351
No log	4.0	20	1.7985	0.0229	1.7977	1.3408
No log	5.0	25	1.4612	0.0329	1.4608	1.2086
No log	6.0	30	1.0788	0.0302	1.0784	1.0385
No log	7.0	35	0.8569	0.3313	0.8569	0.9257
No log	8.0	40	0.7827	0.3717	0.7830	0.8849
No log	9.0	45	0.7437	0.3317	0.7440	0.8625
No log	10.0	50	0.6574	0.4018	0.6580	0.8112
No log	11.0	55	0.6859	0.3798	0.6867	0.8287
No log	12.0	60	0.6695	0.4812	0.6701	0.8186
No log	13.0	65	0.6066	0.5203	0.6073	0.7793
No log	14.0	70	0.7629	0.4669	0.7637	0.8739
No log	15.0	75	0.7819	0.4595	0.7828	0.8848
No log	16.0	80	0.6895	0.4888	0.6905	0.8309
No log	17.0	85	1.3060	0.3464	1.3068	1.1432
No log	18.0	90	1.4259	0.2947	1.4265	1.1943
No log	19.0	95	0.7908	0.4535	0.7916	0.8897
No log	20.0	100	0.8277	0.4073	0.8286	0.9103
No log	21.0	105	1.0048	0.3366	1.0052	1.0026
No log	22.0	110	1.0383	0.3630	1.0386	1.0191
No log	23.0	115	1.0751	0.3432	1.0756	1.0371
No log	24.0	120	0.8621	0.3886	0.8626	0.9288
No log	25.0	125	0.8630	0.4045	0.8636	0.9293
No log	26.0	130	1.2530	0.2827	1.2536	1.1196
No log	27.0	135	1.3878	0.2441	1.3883	1.1783
No log	28.0	140	1.2346	0.3042	1.2351	1.1114

genki10/Trial3BERT_AugV8_k7_task1_organization_sp010_lw040_fold3

Trial3BERT_AugV8_k7_task1_organization_sp010_lw040_fold3