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	2	8.9564	0.0033	8.9564	2.9927
No log	2.0	4	6.5768	0.0	6.5768	2.5645
No log	3.0	6	5.7097	0.0059	5.7097	2.3895
No log	4.0	8	4.2743	0.0079	4.2743	2.0674
No log	5.0	10	3.4084	0.0040	3.4084	1.8462
No log	6.0	12	2.8448	0.0040	2.8448	1.6866
No log	7.0	14	2.2448	0.1750	2.2448	1.4982
No log	8.0	16	1.7794	0.0952	1.7794	1.3339
No log	9.0	18	1.4418	0.0407	1.4418	1.2008
No log	10.0	20	1.1961	0.0407	1.1961	1.0937
No log	11.0	22	1.0388	0.0809	1.0388	1.0192
No log	12.0	24	0.8563	0.1815	0.8563	0.9253
No log	13.0	26	0.7879	0.4047	0.7879	0.8877
No log	14.0	28	0.6969	0.5154	0.6969	0.8348
No log	15.0	30	0.7444	0.5263	0.7444	0.8628
No log	16.0	32	0.7751	0.5140	0.7751	0.8804
No log	17.0	34	0.8271	0.4943	0.8271	0.9094
No log	18.0	36	0.5875	0.5366	0.5875	0.7665
No log	19.0	38	0.6052	0.5124	0.6052	0.7779
No log	20.0	40	0.8818	0.4687	0.8818	0.9390
No log	21.0	42	1.1078	0.3865	1.1078	1.0525
No log	22.0	44	0.7878	0.4565	0.7878	0.8876
No log	23.0	46	0.9697	0.3689	0.9697	0.9847
No log	24.0	48	1.1149	0.2869	1.1149	1.0559
No log	25.0	50	0.7781	0.4282	0.7781	0.8821
No log	26.0	52	0.8394	0.4067	0.8394	0.9162
No log	27.0	54	1.6670	0.1536	1.6670	1.2911
No log	28.0	56	1.6111	0.1851	1.6111	1.2693
No log	29.0	58	0.7618	0.4597	0.7618	0.8728
No log	30.0	60	0.7791	0.5366	0.7791	0.8827
No log	31.0	62	0.8333	0.4484	0.8333	0.9128
No log	32.0	64	1.9667	0.1812	1.9667	1.4024
No log	33.0	66	1.5905	0.2684	1.5905	1.2612

genki10/Trial3BERT_AugV8_k1_task1_organization_sp010_lw030_fold4

Trial3BERT_AugV8_k1_task1_organization_sp010_lw030_fold4