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	7	6.8320	0.0027	6.8322	2.6138
No log	2.0	14	2.3190	0.1859	2.3194	1.5229
No log	3.0	21	0.9753	0.0213	0.9757	0.9878
No log	4.0	28	0.8781	0.0543	0.8784	0.9373
No log	5.0	35	0.7115	0.4401	0.7117	0.8436
No log	6.0	42	0.5963	0.4621	0.5964	0.7723
No log	7.0	49	0.7205	0.3714	0.7205	0.8488
No log	8.0	56	0.9459	0.3377	0.9458	0.9725
No log	9.0	63	1.0141	0.2931	1.0138	1.0069
No log	10.0	70	0.5529	0.4689	0.5527	0.7435
No log	11.0	77	0.6923	0.3793	0.6921	0.8319
No log	12.0	84	0.6608	0.4515	0.6604	0.8127
No log	13.0	91	1.0864	0.2958	1.0860	1.0421
No log	14.0	98	1.6875	0.1537	1.6869	1.2988
No log	15.0	105	0.7122	0.3942	0.7117	0.8436
No log	16.0	112	0.9470	0.2999	0.9464	0.9729
No log	17.0	119	1.1360	0.2674	1.1357	1.0657
No log	18.0	126	0.9654	0.3037	0.9651	0.9824
No log	19.0	133	1.0618	0.2388	1.0615	1.0303
No log	20.0	140	0.8940	0.2922	0.8936	0.9453
No log	21.0	147	0.8947	0.3232	0.8943	0.9457
No log	22.0	154	0.7011	0.3964	0.7007	0.8371
No log	23.0	161	0.6597	0.4339	0.6593	0.8119
No log	24.0	168	1.3825	0.1604	1.3820	1.1756
No log	25.0	175	1.3881	0.2000	1.3879	1.1781

genki10/Trial3BERT_AugV8_k10_task1_organization_sp010_lw040_fold2

Trial3BERT_AugV8_k10_task1_organization_sp010_lw040_fold2