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	4	8.3905	0.0	8.3908	2.8967
No log	2.0	8	5.2014	0.0370	5.2019	2.2808
No log	3.0	12	3.1558	0.0039	3.1564	1.7766
No log	4.0	16	1.5538	0.0463	1.5543	1.2467
No log	5.0	20	1.5460	0.0451	1.5466	1.2436
No log	6.0	24	1.4170	0.0763	1.4176	1.1906
No log	7.0	28	1.1365	0.0979	1.1370	1.0663
No log	8.0	32	1.1126	0.1101	1.1131	1.0550
No log	9.0	36	0.8616	0.3243	0.8618	0.9283
No log	10.0	40	0.9088	0.3166	0.9088	0.9533
No log	11.0	44	1.0943	0.2890	1.0940	1.0459
No log	12.0	48	1.0957	0.3577	1.0951	1.0464
No log	13.0	52	1.1661	0.3545	1.1651	1.0794
No log	14.0	56	1.5240	0.2443	1.5227	1.2340
No log	15.0	60	1.8273	0.2176	1.8261	1.3513
No log	16.0	64	1.6351	0.2270	1.6341	1.2783
No log	17.0	68	1.5399	0.2304	1.5394	1.2407
No log	18.0	72	1.6582	0.2100	1.6579	1.2876
No log	19.0	76	1.7378	0.2186	1.7371	1.3180
No log	20.0	80	1.6267	0.2016	1.6256	1.2750
No log	21.0	84	1.1821	0.3156	1.1809	1.0867
No log	22.0	88	2.0659	0.1402	2.0647	1.4369
No log	23.0	92	1.8663	0.1744	1.8652	1.3657
No log	24.0	96	1.8387	0.1892	1.8376	1.3556
No log	25.0	100	1.7810	0.1970	1.7802	1.3342
No log	26.0	104	1.9937	0.1781	1.9927	1.4116
No log	27.0	108	1.7497	0.2068	1.7483	1.3222

genki10/BERT_AugV8_k5_task1_organization_sp060_lw030_fold2

BERT_AugV8_k5_task1_organization_sp060_lw030_fold2