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	7	9.0116	0.0	9.0115	3.0019
No log	2.0	14	4.2556	0.0039	4.2560	2.0630
No log	3.0	21	1.3624	0.0136	1.3629	1.1674
No log	4.0	28	1.6130	0.0342	1.6132	1.2701
No log	5.0	35	2.5156	0.0817	2.5143	1.5857
No log	6.0	42	1.7691	0.1695	1.7676	1.3295
No log	7.0	49	1.3934	0.2455	1.3918	1.1798
No log	8.0	56	0.8783	0.3421	0.8773	0.9366
No log	9.0	63	1.4890	0.2296	1.4872	1.2195
No log	10.0	70	2.3372	0.1374	2.3351	1.5281
No log	11.0	77	2.2482	0.1260	2.2466	1.4989
No log	12.0	84	1.7827	0.1971	1.7809	1.3345
No log	13.0	91	2.1816	0.1275	2.1797	1.4764
No log	14.0	98	1.7701	0.1545	1.7684	1.3298
No log	15.0	105	1.0876	0.3067	1.0863	1.0423
No log	16.0	112	1.1322	0.2933	1.1308	1.0634
No log	17.0	119	2.4626	0.0924	2.4609	1.5687
No log	18.0	126	2.4995	0.0617	2.4977	1.5804
No log	19.0	133	2.2529	0.0876	2.2510	1.5003
No log	20.0	140	1.5219	0.1814	1.5202	1.2330
No log	21.0	147	2.0240	0.1036	2.0220	1.4220
No log	22.0	154	2.4271	0.0908	2.4248	1.5572
No log	23.0	161	2.2803	0.1052	2.2781	1.5093

genki10/BERT_AugV8_k10_task1_organization_sp060_lw010_fold2

BERT_AugV8_k10_task1_organization_sp060_lw010_fold2