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	6	7.5318	0.0	7.5320	2.7444
No log	2.0	12	2.9205	0.0	2.9209	1.7091
No log	3.0	18	1.2842	0.0280	1.2846	1.1334
No log	4.0	24	1.9080	0.1342	1.9084	1.3814
No log	5.0	30	1.3619	0.0703	1.3622	1.1671
No log	6.0	36	0.9717	0.2754	0.9717	0.9858
No log	7.0	42	1.3353	0.2488	1.3352	1.1555
No log	8.0	48	0.6179	0.4612	0.6179	0.7861
No log	9.0	54	0.6013	0.4586	0.6011	0.7753
No log	10.0	60	1.5891	0.2192	1.5883	1.2603
No log	11.0	66	1.4938	0.2351	1.4930	1.2219
No log	12.0	72	1.6939	0.2059	1.6929	1.3011
No log	13.0	78	1.6875	0.2323	1.6866	1.2987
No log	14.0	84	2.2660	0.1573	2.2647	1.5049
No log	15.0	90	2.2872	0.1255	2.2863	1.5120
No log	16.0	96	1.8858	0.1520	1.8851	1.3730
No log	17.0	102	3.2186	0.0538	3.2179	1.7938
No log	18.0	108	0.9249	0.4095	0.9244	0.9614
No log	19.0	114	1.5612	0.2165	1.5604	1.2492
No log	20.0	120	1.9796	0.1751	1.9787	1.4067
No log	21.0	126	1.5420	0.2011	1.5411	1.2414
No log	22.0	132	0.9206	0.2997	0.9198	0.9591
No log	23.0	138	1.9456	0.1084	1.9449	1.3946

genki10/BERT_AugV8_k7_task1_organization_sp060_lw030_fold2

BERT_AugV8_k7_task1_organization_sp060_lw030_fold2