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	9.0804	0.0	9.0804	3.0134
No log	2.0	4	7.8850	0.0	7.8850	2.8080
No log	3.0	6	7.0738	0.0	7.0738	2.6597
No log	4.0	8	6.3963	-0.0022	6.3963	2.5291
No log	5.0	10	5.5802	0.0112	5.5802	2.3622
No log	6.0	12	4.8321	0.0039	4.8321	2.1982
No log	7.0	14	4.0981	0.0	4.0981	2.0244
No log	8.0	16	3.9131	0.0	3.9131	1.9781
No log	9.0	18	3.1418	0.0	3.1418	1.7725
No log	10.0	20	2.7452	0.0	2.7452	1.6569
No log	11.0	22	2.1476	0.0527	2.1476	1.4655
No log	12.0	24	1.8400	0.0436	1.8400	1.3564
No log	13.0	26	1.5061	0.0316	1.5061	1.2272
No log	14.0	28	1.1404	0.0316	1.1404	1.0679
No log	15.0	30	0.9653	0.0316	0.9653	0.9825
No log	16.0	32	0.8463	0.2845	0.8463	0.9200
No log	17.0	34	0.7687	0.4107	0.7687	0.8768
No log	18.0	36	0.7088	0.4389	0.7088	0.8419
No log	19.0	38	1.1779	0.1450	1.1779	1.0853
No log	20.0	40	1.1827	0.2031	1.1827	1.0875
No log	21.0	42	0.7018	0.4572	0.7018	0.8377
No log	22.0	44	0.6104	0.4853	0.6104	0.7813
No log	23.0	46	0.6200	0.4876	0.6200	0.7874
No log	24.0	48	1.2505	0.1921	1.2505	1.1182
No log	25.0	50	1.3523	0.1702	1.3523	1.1629
No log	26.0	52	0.9033	0.3345	0.9033	0.9504
No log	27.0	54	0.6861	0.4265	0.6861	0.8283
No log	28.0	56	0.8548	0.3457	0.8548	0.9246
No log	29.0	58	0.7266	0.3664	0.7266	0.8524
No log	30.0	60	0.6943	0.3150	0.6943	0.8333
No log	31.0	62	0.7379	0.3171	0.7379	0.8590
No log	32.0	64	0.8300	0.3049	0.8300	0.9111
No log	33.0	66	0.7592	0.3377	0.7592	0.8713
No log	34.0	68	0.7047	0.3541	0.7047	0.8395
No log	35.0	70	0.7376	0.3499	0.7376	0.8588
No log	36.0	72	0.7403	0.3755	0.7403	0.8604
No log	37.0	74	0.7866	0.3742	0.7866	0.8869
No log	38.0	76	0.9373	0.3091	0.9373	0.9681

genki10/Trial3BERT_AugV8_k1_task1_organization_sp010_lw030_fold0

Trial3BERT_AugV8_k1_task1_organization_sp010_lw030_fold0