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	8.7620	0.0018	8.7620	2.9601
No log	2.0	12	4.5333	0.0079	4.5333	2.1292
No log	3.0	18	2.2359	0.1086	2.2359	1.4953
No log	4.0	24	1.7794	0.0445	1.7794	1.3340
No log	5.0	30	1.0673	0.0107	1.0673	1.0331
No log	6.0	36	1.8988	0.0509	1.8988	1.3780
No log	7.0	42	1.0576	0.0445	1.0576	1.0284
No log	8.0	48	1.0176	0.2023	1.0176	1.0087
No log	9.0	54	0.7653	0.3502	0.7653	0.8748
No log	10.0	60	0.8353	0.3162	0.8353	0.9140
No log	11.0	66	1.5007	0.1554	1.5007	1.2250
No log	12.0	72	1.2947	0.2293	1.2947	1.1379
No log	13.0	78	0.7646	0.4648	0.7646	0.8744
No log	14.0	84	0.9575	0.3391	0.9575	0.9785
No log	15.0	90	1.9641	0.1445	1.9641	1.4015
No log	16.0	96	0.8034	0.4336	0.8034	0.8963
No log	17.0	102	1.5013	0.2109	1.5013	1.2253
No log	18.0	108	1.0866	0.3239	1.0866	1.0424
No log	19.0	114	0.8198	0.3976	0.8198	0.9054
No log	20.0	120	0.9675	0.3735	0.9675	0.9836
No log	21.0	126	1.4262	0.2505	1.4262	1.1942
No log	22.0	132	1.2871	0.2607	1.2871	1.1345
No log	23.0	138	1.1062	0.3211	1.1062	1.0518
No log	24.0	144	1.0810	0.3567	1.0810	1.0397
No log	25.0	150	1.0992	0.3368	1.0992	1.0484
No log	26.0	156	0.9159	0.3871	0.9159	0.9570
No log	27.0	162	0.9068	0.3780	0.9068	0.9523
No log	28.0	168	0.9319	0.3348	0.9319	0.9653

genki10/BERT_AugV8_k7_task1_organization_sp010_lw070_fold4

BERT_AugV8_k7_task1_organization_sp010_lw070_fold4