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	6.6285	0.0	6.6285	2.5746
No log	2.0	8	4.6674	0.0016	4.6674	2.1604
No log	3.0	12	2.6380	0.0040	2.6380	1.6242
No log	4.0	16	1.5543	0.0212	1.5543	1.2467
No log	5.0	20	1.2685	0.0212	1.2685	1.1263
No log	6.0	24	0.8649	0.2385	0.8649	0.9300
No log	7.0	28	1.0686	0.0316	1.0686	1.0337
No log	8.0	32	0.8996	0.1438	0.8996	0.9484
No log	9.0	36	1.1454	0.1187	1.1454	1.0702
No log	10.0	40	0.7038	0.4140	0.7038	0.8389
No log	11.0	44	1.1480	0.2873	1.1480	1.0714
No log	12.0	48	1.5211	0.2361	1.5211	1.2333
No log	13.0	52	0.9304	0.3550	0.9304	0.9646
No log	14.0	56	1.4282	0.2510	1.4282	1.1951
No log	15.0	60	0.8071	0.4307	0.8071	0.8984
No log	16.0	64	2.0963	0.1655	2.0963	1.4479
No log	17.0	68	0.8056	0.4079	0.8056	0.8975
No log	18.0	72	1.0796	0.2796	1.0796	1.0390
No log	19.0	76	1.9390	0.1777	1.9390	1.3925
No log	20.0	80	0.8374	0.3923	0.8374	0.9151
No log	21.0	84	2.3617	0.0986	2.3617	1.5368
No log	22.0	88	1.2043	0.3066	1.2043	1.0974
No log	23.0	92	1.1280	0.2987	1.1280	1.0621
No log	24.0	96	1.3330	0.2646	1.3330	1.1546
No log	25.0	100	0.9613	0.4131	0.9613	0.9805
No log	26.0	104	1.7648	0.2242	1.7648	1.3285
No log	27.0	108	1.1857	0.3002	1.1857	1.0889
No log	28.0	112	1.1555	0.2721	1.1555	1.0749
No log	29.0	116	1.2923	0.2589	1.2923	1.1368
No log	30.0	120	1.0838	0.3036	1.0838	1.0410

genki10/Trial3BERT_AugV8_k5_task1_organization_sp010_lw010_fold4

Trial3BERT_AugV8_k5_task1_organization_sp010_lw010_fold4