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	10.0940	0.0018	10.0940	3.1771
No log	2.0	6	8.3891	0.0	8.3891	2.8964
No log	3.0	9	6.7291	0.0	6.7291	2.5941
No log	4.0	12	4.6527	0.0079	4.6527	2.1570
No log	5.0	15	2.9300	0.0040	2.9300	1.7117
No log	6.0	18	2.1573	0.0771	2.1573	1.4688
No log	7.0	21	1.3492	0.0342	1.3492	1.1615
No log	8.0	24	1.1626	0.0238	1.1626	1.0782
No log	9.0	27	2.3531	-0.0358	2.3531	1.5340
No log	10.0	30	1.1481	0.0368	1.1481	1.0715
No log	11.0	33	1.3377	0.0771	1.3377	1.1566
No log	12.0	36	1.2323	0.0902	1.2323	1.1101
No log	13.0	39	1.5344	0.0913	1.5344	1.2387
No log	14.0	42	1.0769	0.1704	1.0769	1.0377
No log	15.0	45	1.7253	0.0712	1.7253	1.3135
No log	16.0	48	1.8679	0.1151	1.8679	1.3667
No log	17.0	51	2.0050	0.1134	2.0050	1.4160
No log	18.0	54	1.8482	0.1370	1.8482	1.3595
No log	19.0	57	1.8430	0.1177	1.8430	1.3576
No log	20.0	60	2.7173	0.0455	2.7173	1.6484
No log	21.0	63	1.7443	0.1041	1.7443	1.3207
No log	22.0	66	2.5184	0.0407	2.5184	1.5870
No log	23.0	69	2.3525	0.0623	2.3525	1.5338
No log	24.0	72	2.5638	0.0542	2.5638	1.6012
No log	25.0	75	2.3903	0.0723	2.3903	1.5461
No log	26.0	78	2.2414	0.0770	2.2414	1.4971
No log	27.0	81	3.2704	0.0263	3.2704	1.8084
No log	28.0	84	1.8451	0.0735	1.8451	1.3584
No log	29.0	87	2.2618	0.0322	2.2618	1.5039

genki10/BERT_AugV8_k3_task1_organization_sp060_lw030_fold4

BERT_AugV8_k3_task1_organization_sp060_lw030_fold4