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	7.8210	0.0	7.8185	2.7962
No log	2.0	10	4.9116	0.0147	4.9095	2.2157
No log	3.0	15	2.2818	0.1264	2.2800	1.5100
No log	4.0	20	1.4920	0.0106	1.4904	1.2208
No log	5.0	25	1.0799	0.0315	1.0786	1.0385
No log	6.0	30	1.0754	0.0443	1.0741	1.0364
No log	7.0	35	0.9223	0.1023	0.9210	0.9597
No log	8.0	40	1.3895	0.1344	1.3879	1.1781
No log	9.0	45	0.6763	0.3797	0.6754	0.8218
No log	10.0	50	0.7011	0.3942	0.7001	0.8367
No log	11.0	55	0.6613	0.3974	0.6604	0.8126
No log	12.0	60	0.8168	0.4042	0.8156	0.9031
No log	13.0	65	1.0960	0.2897	1.0944	1.0462
No log	14.0	70	1.4424	0.2208	1.4406	1.2003
No log	15.0	75	1.7884	0.1933	1.7866	1.3366
No log	16.0	80	0.8433	0.3908	0.8419	0.9175
No log	17.0	85	1.0530	0.2933	1.0513	1.0253
No log	18.0	90	1.1334	0.2635	1.1317	1.0638
No log	19.0	95	1.5468	0.2229	1.5449	1.2430
No log	20.0	100	1.1800	0.2921	1.1784	1.0856
No log	21.0	105	0.8770	0.3475	0.8757	0.9358
No log	22.0	110	1.3291	0.2029	1.3275	1.1522
No log	23.0	115	1.3335	0.2197	1.3319	1.1541
No log	24.0	120	1.3252	0.2159	1.3236	1.1505
No log	25.0	125	1.6739	0.1848	1.6721	1.2931
No log	26.0	130	1.4931	0.1966	1.4913	1.2212
No log	27.0	135	1.2344	0.2396	1.2327	1.1103

genki10/Trial3BERT_AugV8_k7_task1_organization_sp020_lw030_fold1

Trial3BERT_AugV8_k7_task1_organization_sp020_lw030_fold1