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	11.2719	-0.0168	11.2719	3.3574
No log	2.0	10	7.0538	0.0	7.0538	2.6559
No log	3.0	15	4.0216	0.0079	4.0216	2.0054
No log	4.0	20	2.0054	0.1031	2.0054	1.4161
No log	5.0	25	1.1134	0.0316	1.1134	1.0552
No log	6.0	30	1.0967	0.0743	1.0967	1.0472
No log	7.0	35	1.7452	0.1865	1.7452	1.3211
No log	8.0	40	2.2177	0.0814	2.2177	1.4892
No log	9.0	45	1.6950	0.1457	1.6950	1.3019
No log	10.0	50	1.6081	0.1628	1.6081	1.2681
No log	11.0	55	1.4319	0.1862	1.4319	1.1966
No log	12.0	60	1.1164	0.3291	1.1164	1.0566
No log	13.0	65	1.8443	0.1920	1.8443	1.3581
No log	14.0	70	2.3835	0.1305	2.3835	1.5439
No log	15.0	75	1.8103	0.1853	1.8103	1.3455
No log	16.0	80	1.7441	0.1724	1.7441	1.3207
No log	17.0	85	1.3779	0.2627	1.3779	1.1738
No log	18.0	90	2.6902	0.0942	2.6902	1.6402
No log	19.0	95	1.2087	0.3005	1.2087	1.0994
No log	20.0	100	1.9064	0.1526	1.9064	1.3807
No log	21.0	105	2.4655	0.1016	2.4655	1.5702
No log	22.0	110	1.4275	0.2246	1.4275	1.1948
No log	23.0	115	1.6463	0.1961	1.6463	1.2831
No log	24.0	120	2.0362	0.1617	2.0362	1.4270
No log	25.0	125	2.4549	0.1251	2.4549	1.5668
No log	26.0	130	2.0720	0.1445	2.0720	1.4394
No log	27.0	135	1.6132	0.2268	1.6132	1.2701

genki10/BERT_AugV8_k7_task1_organization_sp010_lw060_fold4

BERT_AugV8_k7_task1_organization_sp010_lw060_fold4