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	5.8248	0.0486	5.8248	2.4135
No log	2.0	10	3.1404	0.0040	3.1404	1.7721
No log	3.0	15	1.6726	0.0420	1.6726	1.2933
No log	4.0	20	1.1492	0.0212	1.1492	1.0720
No log	5.0	25	1.1498	0.0107	1.1498	1.0723
No log	6.0	30	1.3305	0.0421	1.3305	1.1535
No log	7.0	35	1.7316	0.1312	1.7316	1.3159
No log	8.0	40	0.9102	0.3493	0.9102	0.9540
No log	9.0	45	2.2341	0.1018	2.2341	1.4947
No log	10.0	50	1.5169	0.1835	1.5169	1.2316
No log	11.0	55	1.4348	0.2190	1.4348	1.1978
No log	12.0	60	2.0798	0.1122	2.0799	1.4422
No log	13.0	65	1.7556	0.2142	1.7556	1.3250
No log	14.0	70	1.9447	0.1733	1.9447	1.3945
No log	15.0	75	1.9438	0.1912	1.9438	1.3942
No log	16.0	80	2.0210	0.1899	2.0210	1.4216
No log	17.0	85	1.5878	0.2379	1.5878	1.2601
No log	18.0	90	2.6091	0.1222	2.6091	1.6153
No log	19.0	95	2.6103	0.1142	2.6103	1.6156
No log	20.0	100	1.3562	0.2638	1.3562	1.1646
No log	21.0	105	1.9607	0.1529	1.9607	1.4003
No log	22.0	110	2.1816	0.1560	2.1816	1.4770
No log	23.0	115	2.0946	0.1958	2.0946	1.4473

genki10/BERT_AugV8_k7_task1_organization_sp040_lw030_fold4

BERT_AugV8_k7_task1_organization_sp040_lw030_fold4