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	5	5.5910	0.0800	5.5887	2.3641
No log	2.0	10	2.6632	0.0	2.6612	1.6313
No log	3.0	15	1.2551	0.0	1.2536	1.1196
No log	4.0	20	0.9458	0.0990	0.9445	0.9719
No log	5.0	25	1.3200	0.0	1.3187	1.1483
No log	6.0	30	0.9236	0.2426	0.9223	0.9604
No log	7.0	35	0.9423	0.0461	0.9411	0.9701
No log	8.0	40	0.7656	0.3886	0.7646	0.8744
No log	9.0	45	0.6777	0.4195	0.6766	0.8226
No log	10.0	50	0.5890	0.4467	0.5883	0.7670
No log	11.0	55	0.6271	0.3995	0.6266	0.7916
No log	12.0	60	0.5350	0.5639	0.5345	0.7311
No log	13.0	65	0.5791	0.5927	0.5787	0.7608
No log	14.0	70	0.6134	0.5886	0.6131	0.7830
No log	15.0	75	0.5643	0.6313	0.5639	0.7509
No log	16.0	80	0.5879	0.5920	0.5874	0.7664
No log	17.0	85	0.7716	0.5085	0.7712	0.8782
No log	18.0	90	0.6715	0.5635	0.6711	0.8192
No log	19.0	95	0.6509	0.5353	0.6502	0.8063
No log	20.0	100	0.9961	0.4186	0.9956	0.9978
No log	21.0	105	0.8980	0.4647	0.8975	0.9473
No log	22.0	110	0.6519	0.5333	0.6507	0.8067
No log	23.0	115	0.6963	0.5478	0.6956	0.8340
No log	24.0	120	0.6169	0.5694	0.6161	0.7849
No log	25.0	125	0.5973	0.5668	0.5966	0.7724
No log	26.0	130	0.6998	0.5631	0.6992	0.8362
No log	27.0	135	0.6620	0.4870	0.6608	0.8129
No log	28.0	140	0.6916	0.4758	0.6904	0.8309
No log	29.0	145	0.6267	0.5294	0.6257	0.7910
No log	30.0	150	0.6019	0.5679	0.6012	0.7754

genki10/Trial3BERT_AugV8_k7_task1_organization_sp010_lw030_fold1

Trial3BERT_AugV8_k7_task1_organization_sp010_lw030_fold1