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	4.9882	0.0	4.9862	2.2330
No log	2.0	16	2.5647	0.0	2.5630	1.6009
No log	3.0	24	1.6014	0.0	1.5998	1.2648
No log	4.0	32	1.4304	0.0	1.4286	1.1953
No log	5.0	40	1.2652	0.0272	1.2634	1.1240
No log	6.0	48	1.0896	0.0798	1.0882	1.0432
No log	7.0	56	1.0128	0.0998	1.0117	1.0058
No log	8.0	64	1.1727	0.0580	1.1713	1.0823
No log	9.0	72	1.2117	0.1937	1.2107	1.1003
No log	10.0	80	1.7042	0.0560	1.7030	1.3050
No log	11.0	88	2.1033	-0.0158	2.1024	1.4499
No log	12.0	96	1.7476	0.0485	1.7462	1.3215
No log	13.0	104	2.4602	0.0504	2.4583	1.5679
No log	14.0	112	1.4663	0.0540	1.4650	1.2104
No log	15.0	120	1.4542	0.0322	1.4528	1.2053
No log	16.0	128	2.8767	0.0372	2.8748	1.6955
No log	17.0	136	1.9232	0.0248	1.9215	1.3862
No log	18.0	144	1.2981	0.0815	1.2969	1.1388
No log	19.0	152	1.9024	-0.0002	1.9007	1.3786
No log	20.0	160	1.6743	0.0512	1.6725	1.2933
No log	21.0	168	1.7680	0.0817	1.7664	1.3291
No log	22.0	176	1.8524	0.0392	1.8509	1.3605
No log	23.0	184	1.9541	0.0576	1.9525	1.3973
No log	24.0	192	1.3377	0.1631	1.3363	1.1560

genki10/BERT_AugV8_k10_task1_organization_sp060_lw030_fold1

BERT_AugV8_k10_task1_organization_sp060_lw030_fold1