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	8	5.7572	0.0180	5.7572	2.3994
No log	2.0	16	2.5152	0.0364	2.5152	1.5860
No log	3.0	24	1.6276	0.0106	1.6276	1.2758
No log	4.0	32	1.7246	0.0175	1.7246	1.3132
No log	5.0	40	2.4938	0.0229	2.4938	1.5792
No log	6.0	48	0.8696	0.1625	0.8696	0.9325
No log	7.0	56	0.8778	0.0835	0.8778	0.9369
No log	8.0	64	0.8457	0.1477	0.8457	0.9196
No log	9.0	72	0.9868	0.1823	0.9868	0.9934
No log	10.0	80	1.0868	0.1514	1.0868	1.0425
No log	11.0	88	1.0320	0.1281	1.0320	1.0159
No log	12.0	96	1.2693	0.0442	1.2693	1.1266
No log	13.0	104	0.9994	0.1711	0.9994	0.9997
No log	14.0	112	1.5577	0.0545	1.5577	1.2481
No log	15.0	120	1.4542	0.0386	1.4542	1.2059
No log	16.0	128	1.1078	0.0972	1.1078	1.0525
No log	17.0	136	1.1996	0.0765	1.1996	1.0953
No log	18.0	144	1.3538	0.0352	1.3538	1.1635
No log	19.0	152	1.2951	0.0528	1.2951	1.1380
No log	20.0	160	1.1532	0.0745	1.1532	1.0739
No log	21.0	168	1.2049	0.0876	1.2049	1.0977
No log	22.0	176	1.4740	0.0284	1.4740	1.2141
No log	23.0	184	1.4078	0.0539	1.4078	1.1865
No log	24.0	192	1.3784	0.0649	1.3784	1.1740

genki10/BERT_AugV8_k10_task1_organization_sp010_lw070_fold0

BERT_AugV8_k10_task1_organization_sp010_lw070_fold0