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	10.7161	-0.0145	10.7132	3.2731
No log	2.0	10	6.5112	0.0	6.5089	2.5513
No log	3.0	15	3.8617	0.0	3.8596	1.9646
No log	4.0	20	1.9415	0.0834	1.9398	1.3928
No log	5.0	25	1.1160	0.0	1.1145	1.0557
No log	6.0	30	1.0856	0.0185	1.0841	1.0412
No log	7.0	35	1.2935	0.1045	1.2918	1.1366
No log	8.0	40	1.0438	0.2125	1.0422	1.0209
No log	9.0	45	1.6321	0.1523	1.6304	1.2769
No log	10.0	50	1.3508	0.1067	1.3497	1.1618
No log	11.0	55	1.5943	0.0752	1.5930	1.2622
No log	12.0	60	2.4596	0.0080	2.4578	1.5677
No log	13.0	65	2.8391	0.0054	2.8370	1.6844
No log	14.0	70	2.6356	0.0046	2.6336	1.6228
No log	15.0	75	1.3544	0.0742	1.3533	1.1633
No log	16.0	80	1.4520	0.0875	1.4510	1.2046
No log	17.0	85	1.9070	0.0717	1.9056	1.3804
No log	18.0	90	1.8300	0.1044	1.8285	1.3522
No log	19.0	95	1.9070	0.0819	1.9053	1.3803
No log	20.0	100	1.7839	0.0902	1.7822	1.3350
No log	21.0	105	1.0672	0.2051	1.0664	1.0327
No log	22.0	110	2.4026	0.0609	2.4007	1.5494
No log	23.0	115	1.4963	0.1198	1.4951	1.2228

genki10/BERT_AugV8_k7_task1_organization_sp010_lw040_fold1

BERT_AugV8_k7_task1_organization_sp010_lw040_fold1