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	10.9248	0.0057	10.9248	3.3053
No log	2.0	4	9.0715	0.0	9.0715	3.0119
No log	3.0	6	8.1690	0.0	8.1690	2.8581
No log	4.0	8	7.1554	0.0	7.1554	2.6750
No log	5.0	10	5.9682	0.0041	5.9682	2.4430
No log	6.0	12	4.6963	0.0079	4.6963	2.1671
No log	7.0	14	3.7874	0.0040	3.7874	1.9461
No log	8.0	16	2.8762	0.0040	2.8762	1.6959
No log	9.0	18	2.2337	0.1150	2.2337	1.4946
No log	10.0	20	1.9181	0.0630	1.9181	1.3849
No log	11.0	22	1.3541	0.0316	1.3541	1.1637
No log	12.0	24	1.0803	0.0316	1.0803	1.0394
No log	13.0	26	0.9440	0.0316	0.9440	0.9716
No log	14.0	28	0.8863	0.0980	0.8863	0.9414
No log	15.0	30	1.0274	0.1060	1.0274	1.0136
No log	16.0	32	0.7815	0.3756	0.7815	0.8840
No log	17.0	34	1.1395	0.2025	1.1395	1.0675
No log	18.0	36	1.3757	0.2167	1.3757	1.1729
No log	19.0	38	0.9669	0.3673	0.9669	0.9833
No log	20.0	40	0.7807	0.4899	0.7807	0.8836
No log	21.0	42	1.2953	0.2741	1.2953	1.1381
No log	22.0	44	1.8289	0.2168	1.8289	1.3524
No log	23.0	46	1.6420	0.2369	1.6420	1.2814
No log	24.0	48	1.1453	0.3521	1.1453	1.0702
No log	25.0	50	1.7320	0.1943	1.7320	1.3161
No log	26.0	52	1.0121	0.3856	1.0121	1.0061
No log	27.0	54	0.9228	0.4140	0.9228	0.9606
No log	28.0	56	1.7851	0.2254	1.7851	1.3361
No log	29.0	58	1.5688	0.2608	1.5688	1.2525
No log	30.0	60	0.8707	0.4306	0.8707	0.9331
No log	31.0	62	1.1260	0.3533	1.1260	1.0611
No log	32.0	64	1.2226	0.3336	1.2226	1.1057
No log	33.0	66	1.2557	0.3303	1.2557	1.1206
No log	34.0	68	1.4778	0.2631	1.4778	1.2157
No log	35.0	70	1.1110	0.3485	1.1110	1.0540

genki10/BERT_AugV8_k1_task1_organization_sp060_lw010_fold4

BERT_AugV8_k1_task1_organization_sp060_lw010_fold4