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	8	5.4696	0.0559	5.4675	2.3383
No log	2.0	16	2.1012	0.0407	2.0995	1.4490
No log	3.0	24	1.4357	0.0	1.4341	1.1975
No log	4.0	32	1.1399	0.0041	1.1384	1.0670
No log	5.0	40	0.9116	0.1926	0.9104	0.9542
No log	6.0	48	1.0076	0.0761	1.0066	1.0033
No log	7.0	56	1.3515	-0.0763	1.3505	1.1621
No log	8.0	64	1.8956	-0.1466	1.8938	1.3762
No log	9.0	72	1.7261	-0.1167	1.7248	1.3133
No log	10.0	80	2.4810	-0.1300	2.4793	1.5746
No log	11.0	88	2.6000	-0.1114	2.5983	1.6119
No log	12.0	96	1.8386	0.0106	1.8374	1.3555
No log	13.0	104	1.3502	0.1069	1.3488	1.1614
No log	14.0	112	1.5225	0.0486	1.5209	1.2332
No log	15.0	120	1.8895	-0.0525	1.8879	1.3740
No log	16.0	128	1.5407	0.0133	1.5392	1.2407
No log	17.0	136	1.5206	0.0575	1.5193	1.2326
No log	18.0	144	2.0429	-0.1277	2.0412	1.4287
No log	19.0	152	1.1850	0.1436	1.1838	1.0880
No log	20.0	160	2.1952	-0.0842	2.1936	1.4811

genki10/Trial3BERT_AugV8_k10_task1_organization_sp020_lw070_fold1

Trial3BERT_AugV8_k10_task1_organization_sp020_lw070_fold1