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	3	8.6070	0.0018	8.6070	2.9338
No log	2.0	6	5.2867	0.0165	5.2867	2.2993
No log	3.0	9	3.7699	0.0040	3.7699	1.9416
No log	4.0	12	2.5867	0.0349	2.5868	1.6083
No log	5.0	15	1.6852	0.0420	1.6852	1.2982
No log	6.0	18	1.2050	0.0316	1.2050	1.0977
No log	7.0	21	1.0224	0.0420	1.0224	1.0111
No log	8.0	24	1.2437	0.0923	1.2437	1.1152
No log	9.0	27	0.9067	0.1677	0.9067	0.9522
No log	10.0	30	1.1652	0.1685	1.1652	1.0795
No log	11.0	33	0.9281	0.2713	0.9281	0.9634
No log	12.0	36	1.0069	0.3178	1.0069	1.0034
No log	13.0	39	0.9250	0.4043	0.9250	0.9618
No log	14.0	42	1.2880	0.3159	1.2880	1.1349
No log	15.0	45	0.6638	0.5122	0.6638	0.8147
No log	16.0	48	0.9108	0.4416	0.9108	0.9544
No log	17.0	51	1.6139	0.2612	1.6139	1.2704
No log	18.0	54	1.0314	0.3775	1.0314	1.0156
No log	19.0	57	1.2185	0.3185	1.2185	1.1039
No log	20.0	60	0.9667	0.3542	0.9667	0.9832
No log	21.0	63	1.0849	0.3571	1.0849	1.0416
No log	22.0	66	1.5618	0.2791	1.5618	1.2497
No log	23.0	69	1.6299	0.2618	1.6299	1.2767
No log	24.0	72	1.7522	0.2202	1.7522	1.3237
No log	25.0	75	1.7932	0.2143	1.7932	1.3391
No log	26.0	78	0.9525	0.3769	0.9525	0.9760
No log	27.0	81	1.6875	0.2285	1.6875	1.2990
No log	28.0	84	1.6164	0.2512	1.6164	1.2714
No log	29.0	87	1.4039	0.2634	1.4039	1.1848
No log	30.0	90	1.8760	0.1711	1.8760	1.3697

genki10/BERT_AugV8_k3_task1_organization_sp030_lw040_fold4

BERT_AugV8_k3_task1_organization_sp030_lw040_fold4