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	8.5832	0.0	8.5832	2.9297
No log	2.0	6	6.0094	0.0244	6.0094	2.4514
No log	3.0	9	4.2850	0.0066	4.2850	2.0700
No log	4.0	12	2.7536	0.0181	2.7536	1.6594
No log	5.0	15	1.8062	0.1094	1.8062	1.3440
No log	6.0	18	1.2838	0.0344	1.2838	1.1331
No log	7.0	21	1.0610	0.0239	1.0610	1.0300
No log	8.0	24	1.4696	0.0666	1.4696	1.2123
No log	9.0	27	1.1316	0.0702	1.1316	1.0637
No log	10.0	30	0.9352	0.2121	0.9352	0.9670
No log	11.0	33	0.9565	0.1801	0.9565	0.9780
No log	12.0	36	0.7548	0.4153	0.7548	0.8688
No log	13.0	39	0.6832	0.4304	0.6832	0.8265
No log	14.0	42	0.7312	0.3787	0.7312	0.8551
No log	15.0	45	0.8258	0.4081	0.8258	0.9087
No log	16.0	48	0.6317	0.4720	0.6317	0.7948
No log	17.0	51	0.9968	0.3541	0.9968	0.9984
No log	18.0	54	0.7260	0.4962	0.7260	0.8521
No log	19.0	57	0.7954	0.3939	0.7954	0.8918
No log	20.0	60	0.9748	0.3498	0.9748	0.9873
No log	21.0	63	0.8075	0.4286	0.8075	0.8986
No log	22.0	66	1.0259	0.3673	1.0259	1.0128
No log	23.0	69	0.9078	0.3967	0.9078	0.9528
No log	24.0	72	0.9754	0.3417	0.9754	0.9876
No log	25.0	75	0.9475	0.3688	0.9475	0.9734
No log	26.0	78	0.9423	0.3795	0.9423	0.9707
No log	27.0	81	1.1040	0.3605	1.1040	1.0507
No log	28.0	84	1.0798	0.3968	1.0798	1.0391
No log	29.0	87	0.8197	0.4409	0.8197	0.9054
No log	30.0	90	1.0577	0.3710	1.0577	1.0284
No log	31.0	93	0.8198	0.4435	0.8198	0.9054
No log	32.0	96	1.3014	0.2440	1.3014	1.1408
No log	33.0	99	0.8372	0.4320	0.8372	0.9150

genki10/BERT_AugV8_k3_task1_organization_sp020_lw060_fold4

BERT_AugV8_k3_task1_organization_sp020_lw060_fold4