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	9.8797	0.0	9.8771	3.1428
No log	2.0	6	8.4662	0.0	8.4638	2.9093
No log	3.0	9	6.2450	0.0	6.2428	2.4986
No log	4.0	12	4.4505	0.0040	4.4484	2.1091
No log	5.0	15	2.9261	0.0	2.9243	1.7101
No log	6.0	18	2.0081	0.0145	2.0064	1.4165
No log	7.0	21	1.2676	0.0	1.2661	1.1252
No log	8.0	24	1.0088	0.0	1.0074	1.0037
No log	9.0	27	1.0700	0.0132	1.0686	1.0337
No log	10.0	30	1.2333	0.0441	1.2318	1.1098
No log	11.0	33	1.0609	0.0777	1.0594	1.0293
No log	12.0	36	1.1056	0.1649	1.1038	1.0506
No log	13.0	39	1.3877	0.1795	1.3855	1.1771
No log	14.0	42	1.4993	0.1769	1.4970	1.2235
No log	15.0	45	0.9074	0.3927	0.9058	0.9517
No log	16.0	48	1.4685	0.2098	1.4664	1.2109
No log	17.0	51	0.8042	0.3691	0.8032	0.8962
No log	18.0	54	2.0315	0.1278	2.0291	1.4245
No log	19.0	57	0.8366	0.3598	0.8356	0.9141
No log	20.0	60	0.9248	0.3093	0.9235	0.9610
No log	21.0	63	1.3941	0.1733	1.3922	1.1799
No log	22.0	66	1.3281	0.1999	1.3261	1.1516
No log	23.0	69	1.3000	0.2033	1.2980	1.1393
No log	24.0	72	0.9112	0.3416	0.9097	0.9538
No log	25.0	75	1.1136	0.2997	1.1118	1.0544
No log	26.0	78	0.9168	0.3760	0.9153	0.9567
No log	27.0	81	1.2113	0.2690	1.2094	1.0997
No log	28.0	84	1.0232	0.3228	1.0216	1.0108
No log	29.0	87	1.6204	0.2162	1.6182	1.2721
No log	30.0	90	0.8378	0.3728	0.8367	0.9147

genki10/Trial3BERT_AugV8_k3_task1_organization_sp010_lw030_fold1

Trial3BERT_AugV8_k3_task1_organization_sp010_lw030_fold1