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	10.0331	0.0018	10.0331	3.1675
No log	2.0	8	8.1321	0.0	8.1321	2.8517
No log	3.0	12	5.2953	0.0142	5.2953	2.3012
No log	4.0	16	3.3297	0.0040	3.3297	1.8248
No log	5.0	20	1.9826	0.0470	1.9826	1.4080
No log	6.0	24	1.3609	0.0317	1.3609	1.1666
No log	7.0	28	1.0389	0.0107	1.0389	1.0193
No log	8.0	32	0.8288	0.2618	0.8288	0.9104
No log	9.0	36	0.9604	0.0698	0.9604	0.9800
No log	10.0	40	1.2907	0.1834	1.2907	1.1361
No log	11.0	44	0.7337	0.4555	0.7337	0.8566
No log	12.0	48	1.5144	0.2294	1.5144	1.2306
No log	13.0	52	0.5822	0.5039	0.5822	0.7630
No log	14.0	56	1.4580	0.2667	1.4580	1.2075
No log	15.0	60	0.6198	0.5030	0.6198	0.7873
No log	16.0	64	0.8190	0.4414	0.8190	0.9050
No log	17.0	68	0.8699	0.4206	0.8699	0.9327
No log	18.0	72	0.9703	0.4035	0.9703	0.9850
No log	19.0	76	0.6770	0.5154	0.6770	0.8228
No log	20.0	80	1.4235	0.2960	1.4235	1.1931
No log	21.0	84	0.6828	0.5271	0.6828	0.8263
No log	22.0	88	1.0047	0.3678	1.0047	1.0023
No log	23.0	92	0.9327	0.4006	0.9327	0.9658
No log	24.0	96	0.8041	0.4860	0.8041	0.8967
No log	25.0	100	0.8621	0.4394	0.8621	0.9285
No log	26.0	104	0.7773	0.4748	0.7773	0.8816
No log	27.0	108	0.8825	0.4204	0.8825	0.9394
No log	28.0	112	1.0279	0.3357	1.0279	1.0139
No log	29.0	116	0.8620	0.4345	0.8620	0.9284
No log	30.0	120	0.8859	0.4066	0.8859	0.9412
No log	31.0	124	0.8972	0.4290	0.8972	0.9472
No log	32.0	128	0.9125	0.3960	0.9125	0.9553
No log	33.0	132	0.9423	0.3704	0.9423	0.9707
No log	34.0	136	0.8016	0.4249	0.8016	0.8953
No log	35.0	140	0.8891	0.3996	0.8891	0.9429
No log	36.0	144	0.9794	0.3390	0.9794	0.9896

genki10/BERT_AugV8_k5_task1_organization_sp020_lw010_fold4

BERT_AugV8_k5_task1_organization_sp020_lw010_fold4