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	8	8.0373	0.0	8.0358	2.8347
No log	2.0	16	4.4010	0.0	4.4000	2.0976
No log	3.0	24	1.7767	0.0266	1.7760	1.3327
No log	4.0	32	1.4469	0.0102	1.4462	1.2026
No log	5.0	40	1.1573	0.0479	1.1577	1.0760
No log	6.0	48	0.8661	0.2470	0.8665	0.9309
No log	7.0	56	0.8794	0.1262	0.8799	0.9380
No log	8.0	64	1.1441	0.0943	1.1443	1.0697
No log	9.0	72	1.4346	0.0741	1.4342	1.1976
No log	10.0	80	1.6393	0.1034	1.6387	1.2801
No log	11.0	88	2.0622	-0.0328	2.0614	1.4358
No log	12.0	96	1.3774	0.0686	1.3770	1.1735
No log	13.0	104	1.6308	0.0084	1.6300	1.2767
No log	14.0	112	2.5347	0.0062	2.5338	1.5918
No log	15.0	120	1.5933	0.0227	1.5926	1.2620
No log	16.0	128	1.4296	0.0887	1.4292	1.1955
No log	17.0	136	1.7643	-0.0089	1.7632	1.3278
No log	18.0	144	1.9136	0.0495	1.9124	1.3829
No log	19.0	152	1.5868	0.0604	1.5860	1.2594
No log	20.0	160	2.1597	0.0226	2.1590	1.4694
No log	21.0	168	1.4617	0.0741	1.4611	1.2088

genki10/BERT_AugV8_k10_task1_organization_sp060_lw030_fold3

BERT_AugV8_k10_task1_organization_sp060_lw030_fold3