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	7.8664	0.0	7.8638	2.8043
No log	2.0	10	3.9012	0.0040	3.8993	1.9747
No log	3.0	15	1.9890	0.0669	1.9873	1.4097
No log	4.0	20	1.2295	0.0	1.2280	1.1081
No log	5.0	25	1.1510	0.0	1.1496	1.0722
No log	6.0	30	1.3151	0.0	1.3137	1.1461
No log	7.0	35	1.4387	0.0	1.4370	1.1988
No log	8.0	40	1.1735	-0.0139	1.1719	1.0826
No log	9.0	45	1.0060	0.0921	1.0046	1.0023
No log	10.0	50	0.9087	0.1811	0.9076	0.9527
No log	11.0	55	1.1250	0.0531	1.1241	1.0602
No log	12.0	60	1.1929	0.1008	1.1919	1.0917
No log	13.0	65	1.0374	0.1830	1.0364	1.0181
No log	14.0	70	1.1603	0.1156	1.1590	1.0766
No log	15.0	75	3.5096	-0.0451	3.5073	1.8728
No log	16.0	80	0.8109	0.3222	0.8101	0.9001
No log	17.0	85	1.1514	0.1851	1.1502	1.0725
No log	18.0	90	1.1935	0.1969	1.1925	1.0920
No log	19.0	95	1.1370	0.2334	1.1359	1.0658
No log	20.0	100	1.3605	0.1502	1.3596	1.1660
No log	21.0	105	0.9909	0.2306	0.9898	0.9949
No log	22.0	110	1.2143	0.1569	1.2131	1.1014
No log	23.0	115	1.6959	0.0984	1.6944	1.3017
No log	24.0	120	1.7303	0.1540	1.7287	1.3148
No log	25.0	125	0.9566	0.2365	0.9555	0.9775
No log	26.0	130	0.8617	0.3166	0.8608	0.9278
No log	27.0	135	1.1329	0.2021	1.1318	1.0639
No log	28.0	140	1.6282	0.1853	1.6267	1.2754
No log	29.0	145	2.3909	0.0664	2.3890	1.5456
No log	30.0	150	1.0677	0.2061	1.0663	1.0326
No log	31.0	155	1.8458	0.1320	1.8440	1.3579

genki10/BERT_AugV8_k7_task1_organization_sp020_lw040_fold1

BERT_AugV8_k7_task1_organization_sp020_lw040_fold1