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	3	8.7000	0.0	8.6985	2.9493
No log	2.0	6	5.5009	0.0197	5.4996	2.3451
No log	3.0	9	3.8148	0.0038	3.8137	1.9529
No log	4.0	12	2.8421	-0.0043	2.8412	1.6856
No log	5.0	15	1.8961	0.0556	1.8953	1.3767
No log	6.0	18	1.4910	0.0292	1.4904	1.2208
No log	7.0	21	1.3369	0.0329	1.3363	1.1560
No log	8.0	24	1.3158	0.0586	1.3154	1.1469
No log	9.0	27	1.9974	0.0894	1.9971	1.4132
No log	10.0	30	1.5337	0.0958	1.5336	1.2384
No log	11.0	33	1.8511	0.1102	1.8512	1.3606
No log	12.0	36	1.0511	0.1042	1.0511	1.0252
No log	13.0	39	1.6241	0.1536	1.6243	1.2745
No log	14.0	42	0.8070	0.3418	0.8072	0.8984
No log	15.0	45	1.0744	0.2832	1.0746	1.0366
No log	16.0	48	0.9437	0.2547	0.9436	0.9714
No log	17.0	51	1.2791	0.1691	1.2786	1.1307
No log	18.0	54	1.2570	0.1839	1.2566	1.1210
No log	19.0	57	1.7015	0.1279	1.7013	1.3043
No log	20.0	60	1.9256	0.1274	1.9254	1.3876
No log	21.0	63	1.7982	0.1331	1.7981	1.3409
No log	22.0	66	1.9056	0.0953	1.9053	1.3803
No log	23.0	69	1.5224	0.1529	1.5224	1.2338
No log	24.0	72	1.7196	0.1440	1.7196	1.3113
No log	25.0	75	2.1853	0.0901	2.1849	1.4782
No log	26.0	78	1.3399	0.1913	1.3401	1.1576
No log	27.0	81	2.6550	0.0405	2.6544	1.6292
No log	28.0	84	1.7961	0.1103	1.7959	1.3401
No log	29.0	87	1.0354	0.2470	1.0356	1.0176

genki10/BERT_AugV8_k3_task1_organization_sp030_lw050_fold3

BERT_AugV8_k3_task1_organization_sp030_lw050_fold3