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	3	8.1512	0.0	8.1512	2.8550
No log	2.0	6	6.8227	0.0	6.8227	2.6120
No log	3.0	9	5.5115	0.0112	5.5115	2.3477
No log	4.0	12	4.2832	0.0039	4.2832	2.0696
No log	5.0	15	3.0948	0.0	3.0948	1.7592
No log	6.0	18	2.0609	0.0575	2.0609	1.4356
No log	7.0	21	1.4131	0.0316	1.4131	1.1888
No log	8.0	24	1.0426	0.0316	1.0426	1.0211
No log	9.0	27	0.9641	0.0669	0.9641	0.9819
No log	10.0	30	0.7929	0.3687	0.7929	0.8904
No log	11.0	33	1.8751	0.1999	1.8751	1.3693
No log	12.0	36	0.6830	0.5037	0.6830	0.8264
No log	13.0	39	0.7343	0.4282	0.7343	0.8569
No log	14.0	42	1.4083	0.1822	1.4083	1.1867
No log	15.0	45	0.5855	0.4291	0.5855	0.7652
No log	16.0	48	0.6374	0.4744	0.6374	0.7984
No log	17.0	51	1.3843	0.2018	1.3843	1.1766
No log	18.0	54	0.6272	0.4138	0.6272	0.7920
No log	19.0	57	0.6768	0.3436	0.6768	0.8227
No log	20.0	60	1.0887	0.2785	1.0887	1.0434
No log	21.0	63	0.7359	0.3307	0.7359	0.8578
No log	22.0	66	0.9372	0.3166	0.9372	0.9681
No log	23.0	69	0.8969	0.2621	0.8969	0.9471
No log	24.0	72	1.2500	0.1855	1.2500	1.1181
No log	25.0	75	0.9291	0.2500	0.9291	0.9639
No log	26.0	78	1.1446	0.1519	1.1446	1.0699
No log	27.0	81	0.9477	0.2619	0.9477	0.9735

genki10/BERT_AugV8_k3_task1_organization_sp010_lw040_fold0

BERT_AugV8_k3_task1_organization_sp010_lw040_fold0