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	2	9.0494	0.0	9.0494	3.0082
No log	2.0	4	7.6640	0.0	7.6640	2.7684
No log	3.0	6	6.8838	0.0	6.8838	2.6237
No log	4.0	8	6.2097	-0.0103	6.2097	2.4919
No log	5.0	10	5.4356	0.0112	5.4356	2.3314
No log	6.0	12	4.6922	0.0077	4.6922	2.1661
No log	7.0	14	3.9405	0.0039	3.9405	1.9851
No log	8.0	16	3.2107	0.0	3.2107	1.7919
No log	9.0	18	2.4951	0.1188	2.4951	1.5796
No log	10.0	20	1.9928	0.0714	1.9928	1.4117
No log	11.0	22	1.6141	0.0409	1.6141	1.2705
No log	12.0	24	1.5118	0.0409	1.5118	1.2296
No log	13.0	26	1.2128	0.0382	1.2128	1.1013
No log	14.0	28	0.9916	0.0382	0.9916	0.9958
No log	15.0	30	0.9392	0.0666	0.9392	0.9691
No log	16.0	32	0.7471	0.4133	0.7471	0.8643
No log	17.0	34	0.7616	0.3810	0.7616	0.8727
No log	18.0	36	1.1577	0.1665	1.1577	1.0760
No log	19.0	38	1.5795	0.1740	1.5795	1.2568
No log	20.0	40	0.9943	0.2852	0.9943	0.9971
No log	21.0	42	0.6071	0.3998	0.6071	0.7792
No log	22.0	44	0.5825	0.4628	0.5825	0.7632
No log	23.0	46	2.0499	0.1835	2.0499	1.4317
No log	24.0	48	2.7344	0.1089	2.7344	1.6536
No log	25.0	50	1.8894	0.1713	1.8894	1.3746
No log	26.0	52	0.7121	0.3559	0.7121	0.8439
No log	27.0	54	0.6627	0.3528	0.6627	0.8141
No log	28.0	56	0.7408	0.2865	0.7408	0.8607
No log	29.0	58	0.9837	0.2070	0.9837	0.9918
No log	30.0	60	0.7318	0.2827	0.7318	0.8555
No log	31.0	62	0.7439	0.2981	0.7439	0.8625
No log	32.0	64	1.0777	0.2824	1.0777	1.0381
No log	33.0	66	1.1621	0.2710	1.1621	1.0780
No log	34.0	68	0.8109	0.2865	0.8109	0.9005
No log	35.0	70	0.7931	0.3048	0.7931	0.8906
No log	36.0	72	0.9215	0.2808	0.9215	0.9599
No log	37.0	74	0.8065	0.3078	0.8065	0.8980

genki10/Trial3BERT_AugV8_k1_task1_organization_sp020_lw030_fold0

Trial3BERT_AugV8_k1_task1_organization_sp020_lw030_fold0