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	6	6.1640	0.0	6.1640	2.4827
No log	2.0	12	3.4450	0.0040	3.4450	1.8561
No log	3.0	18	1.5496	0.0317	1.5496	1.2448
No log	4.0	24	0.9400	0.0107	0.9400	0.9695
No log	5.0	30	1.0959	-0.0430	1.0959	1.0468
No log	6.0	36	0.7810	0.3572	0.7810	0.8838
No log	7.0	42	0.7803	0.2701	0.7803	0.8834
No log	8.0	48	0.6089	0.4426	0.6089	0.7803
No log	9.0	54	0.5995	0.4186	0.5995	0.7743
No log	10.0	60	0.6127	0.4468	0.6127	0.7827
No log	11.0	66	0.5917	0.5279	0.5917	0.7692
No log	12.0	72	0.6402	0.5195	0.6402	0.8001
No log	13.0	78	0.6841	0.4996	0.6841	0.8271
No log	14.0	84	0.7546	0.4368	0.7546	0.8687
No log	15.0	90	0.6790	0.5165	0.6790	0.8240
No log	16.0	96	0.8216	0.3984	0.8216	0.9064
No log	17.0	102	0.7939	0.3306	0.7939	0.8910
No log	18.0	108	0.6779	0.4939	0.6779	0.8233
No log	19.0	114	0.8158	0.3952	0.8158	0.9032
No log	20.0	120	0.7321	0.4420	0.7321	0.8556
No log	21.0	126	0.9264	0.3345	0.9264	0.9625
No log	22.0	132	0.7709	0.3949	0.7709	0.8780
No log	23.0	138	0.7858	0.3842	0.7858	0.8865
No log	24.0	144	0.7728	0.3896	0.7728	0.8791
No log	25.0	150	0.7008	0.4241	0.7008	0.8371
No log	26.0	156	0.7631	0.3893	0.7631	0.8736

genki10/Trial3BERT_AugV8_k10_task1_organization_sp010_lw020_fold4

Trial3BERT_AugV8_k10_task1_organization_sp010_lw020_fold4