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	9.0927	0.0	9.0909	3.0151
No log	2.0	12	6.4958	0.0	6.4945	2.5484
No log	3.0	18	4.0758	0.0	4.0746	2.0186
No log	4.0	24	2.2461	0.1083	2.2453	1.4984
No log	5.0	30	1.3169	0.0401	1.3164	1.1473
No log	6.0	36	1.3792	0.0202	1.3787	1.1742
No log	7.0	42	0.9921	0.0768	0.9923	0.9961
No log	8.0	48	0.8049	0.2997	0.8051	0.8973
No log	9.0	54	0.8379	0.1584	0.8381	0.9155
No log	10.0	60	0.9386	0.1355	0.9389	0.9690
No log	11.0	66	1.6103	-0.0711	1.6100	1.2688
No log	12.0	72	0.9227	0.1190	0.9229	0.9607
No log	13.0	78	0.9566	0.1484	0.9565	0.9780
No log	14.0	84	1.4205	0.0317	1.4192	1.1913
No log	15.0	90	2.0386	-0.0338	2.0367	1.4271
No log	16.0	96	1.6174	-0.0057	1.6160	1.2712
No log	17.0	102	1.9031	-0.0200	1.9018	1.3791
No log	18.0	108	1.8633	-0.0076	1.8620	1.3645
No log	19.0	114	1.8419	-0.0095	1.8406	1.3567
No log	20.0	120	1.9460	-0.0429	1.9446	1.3945
No log	21.0	126	1.8740	0.0493	1.8728	1.3685
No log	22.0	132	1.9506	0.0340	1.9496	1.3963
No log	23.0	138	1.8783	0.0281	1.8773	1.3701

genki10/BERT_AugV8_k7_task1_organization_sp030_lw050_fold3

BERT_AugV8_k7_task1_organization_sp030_lw050_fold3