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	5	5.5904	0.0579	5.5883	2.3639
No log	2.0	10	3.0575	0.0	3.0557	1.7480
No log	3.0	15	1.5987	0.0	1.5971	1.2638
No log	4.0	20	1.0135	0.0	1.0122	1.0061
No log	5.0	25	0.9114	0.2273	0.9101	0.9540
No log	6.0	30	1.1637	0.0347	1.1620	1.0779
No log	7.0	35	0.8747	0.2115	0.8732	0.9345
No log	8.0	40	2.3182	0.0624	2.3159	1.5218
No log	9.0	45	1.0797	0.1422	1.0780	1.0383
No log	10.0	50	1.0416	0.1148	1.0403	1.0199
No log	11.0	55	1.0550	0.1922	1.0537	1.0265
No log	12.0	60	1.0787	0.2810	1.0775	1.0380
No log	13.0	65	1.0839	0.3394	1.0831	1.0407
No log	14.0	70	1.2325	0.3241	1.2317	1.1098
No log	15.0	75	1.7087	0.2137	1.7074	1.3067
No log	16.0	80	1.0401	0.3637	1.0397	1.0197
No log	17.0	85	1.5249	0.2007	1.5234	1.2343
No log	18.0	90	1.0661	0.3284	1.0655	1.0322
No log	19.0	95	0.9432	0.4094	0.9426	0.9709
No log	20.0	100	1.6278	0.1941	1.6263	1.2753
No log	21.0	105	1.0356	0.3553	1.0349	1.0173
No log	22.0	110	1.1194	0.2602	1.1187	1.0577
No log	23.0	115	1.2010	0.2537	1.1999	1.0954
No log	24.0	120	1.2549	0.2203	1.2537	1.1197
No log	25.0	125	1.2529	0.2203	1.2517	1.1188
No log	26.0	130	1.1958	0.2209	1.1947	1.0930
No log	27.0	135	1.2239	0.2262	1.2227	1.1058
No log	28.0	140	1.2033	0.2147	1.2020	1.0963
No log	29.0	145	1.3785	0.1513	1.3770	1.1734
No log	30.0	150	1.1732	0.1987	1.1720	1.0826
No log	31.0	155	1.2129	0.2180	1.2115	1.1007
No log	32.0	160	1.1747	0.2353	1.1734	1.0832
No log	33.0	165	1.2722	0.2186	1.2707	1.1273
No log	34.0	170	1.2919	0.1789	1.2906	1.1360

genki10/Trial3BERT_AugV8_k7_task1_organization_sp010_lw020_fold1

Trial3BERT_AugV8_k7_task1_organization_sp010_lw020_fold1