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	8.8062	0.0	8.8044	2.9672
No log	2.0	14	5.7808	0.0427	5.7797	2.4041
No log	3.0	21	2.9139	0.0	2.9130	1.7068
No log	4.0	28	1.3639	0.0102	1.3633	1.1676
No log	5.0	35	1.0031	0.0401	1.0028	1.0014
No log	6.0	42	0.9330	0.1411	0.9326	0.9657
No log	7.0	49	0.8578	0.3971	0.8581	0.9263
No log	8.0	56	0.7495	0.4520	0.7497	0.8659
No log	9.0	63	0.6702	0.5358	0.6706	0.8189
No log	10.0	70	1.4417	0.3028	1.4414	1.2006
No log	11.0	77	0.9634	0.4570	0.9635	0.9816
No log	12.0	84	1.1148	0.3700	1.1149	1.0559
No log	13.0	91	1.3740	0.3096	1.3740	1.1722
No log	14.0	98	1.9757	0.2094	1.9756	1.4055
No log	15.0	105	1.0713	0.3860	1.0715	1.0351
No log	16.0	112	1.5898	0.2466	1.5897	1.2608
No log	17.0	119	1.2780	0.2977	1.2779	1.1304
No log	18.0	126	0.8515	0.4331	0.8516	0.9228
No log	19.0	133	0.8945	0.4163	0.8945	0.9458
No log	20.0	140	0.7489	0.4424	0.7491	0.8655
No log	21.0	147	0.6407	0.4819	0.6409	0.8006
No log	22.0	154	1.7412	0.1969	1.7409	1.3194
No log	23.0	161	1.3913	0.2676	1.3913	1.1795
No log	24.0	168	1.3922	0.2711	1.3923	1.1800

genki10/Trial3BERT_AugV8_k10_task1_organization_sp010_lw020_fold3

Trial3BERT_AugV8_k10_task1_organization_sp010_lw020_fold3