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	7	6.0014	0.0002	5.9993	2.4494
No log	2.0	14	2.6098	0.0	2.6079	1.6149
No log	3.0	21	1.2092	0.0106	1.2078	1.0990
No log	4.0	28	0.9023	0.2291	0.9011	0.9492
No log	5.0	35	1.2748	0.0013	1.2733	1.1284
No log	6.0	42	1.0366	0.0194	1.0353	1.0175
No log	7.0	49	0.8388	0.2156	0.8378	0.9153
No log	8.0	56	0.9187	0.1691	0.9179	0.9581
No log	9.0	63	1.6843	0.0820	1.6832	1.2974
No log	10.0	70	0.8451	0.2998	0.8447	0.9190
No log	11.0	77	0.9758	0.2084	0.9751	0.9875
No log	12.0	84	0.8196	0.3244	0.8190	0.9050
No log	13.0	91	0.8824	0.3078	0.8815	0.9389
No log	14.0	98	1.1504	0.1914	1.1495	1.0721
No log	15.0	105	1.5689	0.1647	1.5677	1.2521
No log	16.0	112	1.3964	0.1264	1.3954	1.1813
No log	17.0	119	1.1039	0.2477	1.1031	1.0503
No log	18.0	126	0.9670	0.2236	0.9662	0.9830
No log	19.0	133	0.9034	0.3983	0.9025	0.9500
No log	20.0	140	1.1053	0.2093	1.1045	1.0510
No log	21.0	147	1.1257	0.1327	1.1248	1.0606
No log	22.0	154	1.0596	0.1953	1.0587	1.0289
No log	23.0	161	0.8428	0.2860	0.8420	0.9176
No log	24.0	168	0.9105	0.2096	0.9096	0.9537
No log	25.0	175	1.0818	0.1230	1.0806	1.0395
No log	26.0	182	1.0011	0.2219	1.0001	1.0001
No log	27.0	189	1.1218	0.1919	1.1208	1.0587
No log	28.0	196	0.9402	0.2302	0.9392	0.9691
No log	29.0	203	0.9825	0.2674	0.9814	0.9907
No log	30.0	210	1.1660	0.1393	1.1649	1.0793
No log	31.0	217	0.9461	0.2852	0.9451	0.9722
No log	32.0	224	1.0568	0.2207	1.0556	1.0274
No log	33.0	231	0.9813	0.2488	0.9801	0.9900
No log	34.0	238	0.9745	0.2479	0.9733	0.9866

genki10/Trial3BERT_AugV8_k10_task1_organization_sp010_lw020_fold1

Trial3BERT_AugV8_k10_task1_organization_sp010_lw020_fold1