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	7.1067	0.0	7.1067	2.6658
No log	2.0	10	5.0401	0.0115	5.0401	2.2450
No log	3.0	15	3.0053	0.0	3.0053	1.7336
No log	4.0	20	1.5109	0.0316	1.5109	1.2292
No log	5.0	25	0.9743	0.0316	0.9743	0.9871
No log	6.0	30	0.9542	0.0316	0.9542	0.9768
No log	7.0	35	1.9966	0.1548	1.9966	1.4130
No log	8.0	40	0.7826	0.4347	0.7826	0.8846
No log	9.0	45	1.3875	0.1267	1.3875	1.1779
No log	10.0	50	0.6880	0.4262	0.6880	0.8294
No log	11.0	55	0.9716	0.2431	0.9716	0.9857
No log	12.0	60	0.9459	0.2383	0.9459	0.9726
No log	13.0	65	0.7292	0.3368	0.7292	0.8539
No log	14.0	70	0.9379	0.2880	0.9379	0.9685
No log	15.0	75	1.0797	0.2524	1.0797	1.0391
No log	16.0	80	1.1857	0.2820	1.1857	1.0889
No log	17.0	85	1.2707	0.1932	1.2707	1.1273
No log	18.0	90	1.2126	0.1905	1.2126	1.1012
No log	19.0	95	1.3088	0.2360	1.3088	1.1440
No log	20.0	100	1.1322	0.2670	1.1322	1.0641
No log	21.0	105	1.3775	0.1993	1.3775	1.1737
No log	22.0	110	1.3328	0.2071	1.3328	1.1545
No log	23.0	115	1.0881	0.2745	1.0881	1.0431

genki10/Trial3BERT_AugV8_k7_task1_organization_sp020_lw030_fold0

Trial3BERT_AugV8_k7_task1_organization_sp020_lw030_fold0