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	4	6.6687	0.0	6.6676	2.5822
No log	2.0	8	3.8392	0.0	3.8381	1.9591
No log	3.0	12	2.4263	0.0718	2.4255	1.5574
No log	4.0	16	1.5477	0.0202	1.5469	1.2437
No log	5.0	20	1.1800	0.0202	1.1795	1.0860
No log	6.0	24	1.6141	0.1659	1.6134	1.2702
No log	7.0	28	1.4587	0.1796	1.4579	1.2074
No log	8.0	32	2.0213	0.2120	2.0205	1.4215
No log	9.0	36	1.4758	0.2482	1.4755	1.2147
No log	10.0	40	2.0912	0.2423	2.0904	1.4458
No log	11.0	44	3.3726	0.1212	3.3710	1.8360
No log	12.0	48	0.8570	0.4924	0.8571	0.9258
No log	13.0	52	2.2396	0.1872	2.2387	1.4962
No log	14.0	56	0.8129	0.4633	0.8129	0.9016
No log	15.0	60	2.4617	0.1829	2.4604	1.5686
No log	16.0	64	1.4240	0.3663	1.4232	1.1930
No log	17.0	68	2.3460	0.2104	2.3445	1.5312
No log	18.0	72	0.8309	0.4622	0.8308	0.9115
No log	19.0	76	1.7763	0.2442	1.7749	1.3323
No log	20.0	80	1.0851	0.4189	1.0845	1.0414
No log	21.0	84	1.2232	0.3441	1.2221	1.1055
No log	22.0	88	1.3982	0.2602	1.3967	1.1818
No log	23.0	92	1.4174	0.2501	1.4160	1.1900
No log	24.0	96	2.0950	0.1583	2.0931	1.4468
No log	25.0	100	1.4736	0.2509	1.4725	1.2135
No log	26.0	104	0.9537	0.3446	0.9535	0.9765
No log	27.0	108	1.6909	0.2008	1.6897	1.2999

genki10/BERT_AugV8_k5_task1_organization_sp030_lw050_fold3

BERT_AugV8_k5_task1_organization_sp030_lw050_fold3