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	8.2839	0.0	8.2839	2.8782
No log	2.0	16	3.9662	0.0040	3.9662	1.9915
No log	3.0	24	1.6408	0.0344	1.6408	1.2810
No log	4.0	32	1.1617	0.0134	1.1617	1.0778
No log	5.0	40	1.1065	0.0408	1.1065	1.0519
No log	6.0	48	0.9278	0.2471	0.9278	0.9632
No log	7.0	56	0.9622	0.2168	0.9622	0.9809
No log	8.0	64	0.9549	0.2640	0.9549	0.9772
No log	9.0	72	1.5729	0.2680	1.5729	1.2542
No log	10.0	80	1.2585	0.2659	1.2585	1.1218
No log	11.0	88	1.5839	0.2044	1.5839	1.2585
No log	12.0	96	1.9491	0.1880	1.9491	1.3961
No log	13.0	104	1.9431	0.1699	1.9431	1.3940
No log	14.0	112	1.8226	0.1978	1.8226	1.3500
No log	15.0	120	1.2092	0.3029	1.2092	1.0996
No log	16.0	128	1.5083	0.2387	1.5083	1.2281
No log	17.0	136	1.2528	0.2107	1.2528	1.1193
No log	18.0	144	1.4050	0.2185	1.4050	1.1853
No log	19.0	152	1.9604	0.1596	1.9604	1.4001
No log	20.0	160	1.6917	0.1868	1.6917	1.3006
No log	21.0	168	1.6496	0.1921	1.6496	1.2843
No log	22.0	176	1.5783	0.2089	1.5783	1.2563
No log	23.0	184	1.2175	0.2549	1.2175	1.1034
No log	24.0	192	1.7589	0.2267	1.7590	1.3263
No log	25.0	200	1.4088	0.2505	1.4088	1.1869
No log	26.0	208	1.5148	0.2401	1.5148	1.2308
No log	27.0	216	1.8818	0.1749	1.8818	1.3718
No log	28.0	224	1.4656	0.2110	1.4656	1.2106
No log	29.0	232	1.9949	0.1537	1.9949	1.4124
No log	30.0	240	1.4895	0.1981	1.4895	1.2205

genki10/BERT_AugV8_k10_task1_organization_sp020_lw060_fold4

BERT_AugV8_k10_task1_organization_sp020_lw060_fold4