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	8.8249	0.0	8.8249	2.9707
No log	2.0	4	7.6677	0.0	7.6677	2.7691
No log	3.0	6	6.8690	0.0	6.8690	2.6209
No log	4.0	8	5.9510	0.0184	5.9510	2.4395
No log	5.0	10	5.1717	0.0077	5.1717	2.2741
No log	6.0	12	4.2801	0.0039	4.2801	2.0688
No log	7.0	14	3.5441	0.0	3.5441	1.8826
No log	8.0	16	2.7057	0.0	2.7057	1.6449
No log	9.0	18	2.1066	0.0447	2.1066	1.4514
No log	10.0	20	1.6764	0.0316	1.6764	1.2947
No log	11.0	22	1.6233	0.0316	1.6233	1.2741
No log	12.0	24	1.4127	0.0484	1.4127	1.1886
No log	13.0	26	1.0133	0.0316	1.0133	1.0066
No log	14.0	28	0.9342	0.0484	0.9342	0.9665
No log	15.0	30	0.9900	0.0649	0.9900	0.9950
No log	16.0	32	0.9552	0.1206	0.9552	0.9774
No log	17.0	34	0.7865	0.3633	0.7865	0.8868
No log	18.0	36	1.3063	0.1428	1.3063	1.1429
No log	19.0	38	0.9872	0.2401	0.9872	0.9936
No log	20.0	40	0.7104	0.3835	0.7104	0.8429
No log	21.0	42	0.9631	0.3316	0.9631	0.9814
No log	22.0	44	1.3192	0.2421	1.3192	1.1486
No log	23.0	46	0.8889	0.3388	0.8889	0.9428
No log	24.0	48	1.1337	0.2643	1.1337	1.0648
No log	25.0	50	0.9848	0.3008	0.9848	0.9924
No log	26.0	52	0.7615	0.3500	0.7615	0.8727
No log	27.0	54	1.1737	0.2418	1.1737	1.0834
No log	28.0	56	1.5316	0.1945	1.5316	1.2376
No log	29.0	58	0.9711	0.3456	0.9711	0.9854
No log	30.0	60	1.0234	0.2739	1.0234	1.0116
No log	31.0	62	1.4554	0.1909	1.4554	1.2064
No log	32.0	64	1.3836	0.2159	1.3836	1.1763
No log	33.0	66	1.0424	0.3218	1.0424	1.0210
No log	34.0	68	1.0987	0.2820	1.0987	1.0482
No log	35.0	70	1.6632	0.1839	1.6632	1.2897

genki10/Trial2BERT_AugV8_k1_task1_organization_sp010_lw060_fold0

Trial2BERT_AugV8_k1_task1_organization_sp010_lw060_fold0