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	12.4313	0.0	12.4292	3.5255
No log	2.0	8	7.9099	0.0	7.9084	2.8122
No log	3.0	12	5.3009	0.0076	5.2995	2.3021
No log	4.0	16	3.1716	0.0	3.1706	1.7806
No log	5.0	20	1.6623	0.0463	1.6617	1.2891
No log	6.0	24	1.4710	0.0102	1.4704	1.2126
No log	7.0	28	1.0807	0.0634	1.0803	1.0394
No log	8.0	32	1.1735	0.0735	1.1731	1.0831
No log	9.0	36	0.9654	0.1180	0.9651	0.9824
No log	10.0	40	1.4178	0.1390	1.4174	1.1905
No log	11.0	44	0.8717	0.2586	0.8715	0.9335
No log	12.0	48	1.3725	0.1941	1.3724	1.1715
No log	13.0	52	0.8975	0.4041	0.8976	0.9474
No log	14.0	56	2.5485	0.1720	2.5484	1.5964
No log	15.0	60	0.7610	0.4660	0.7614	0.8726
No log	16.0	64	1.5123	0.2731	1.5130	1.2300
No log	17.0	68	0.6479	0.5101	0.6484	0.8053
No log	18.0	72	1.2243	0.3638	1.2251	1.1068
No log	19.0	76	1.4018	0.3028	1.4026	1.1843
No log	20.0	80	0.8149	0.4527	0.8155	0.9030
No log	21.0	84	1.7857	0.2400	1.7863	1.3365
No log	22.0	88	1.2946	0.3355	1.2954	1.1382
No log	23.0	92	1.1836	0.3470	1.1844	1.0883
No log	24.0	96	1.9384	0.2125	1.9390	1.3925
No log	25.0	100	1.1497	0.3633	1.1504	1.0726
No log	26.0	104	1.2586	0.3239	1.2593	1.1222
No log	27.0	108	1.4905	0.2703	1.4912	1.2211
No log	28.0	112	1.2549	0.2927	1.2556	1.1205
No log	29.0	116	1.8651	0.2161	1.8657	1.3659
No log	30.0	120	1.9011	0.2215	1.9018	1.3790
No log	31.0	124	1.2171	0.2986	1.2178	1.1036
No log	32.0	128	1.6294	0.2262	1.6301	1.2768

genki10/Trial3BERT_AugV8_k5_task1_organization_sp030_lw010_fold3

Trial3BERT_AugV8_k5_task1_organization_sp030_lw010_fold3