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	7.0215	0.0018	7.0215	2.6498
No log	2.0	12	3.4372	0.0040	3.4372	1.8540
No log	3.0	18	1.3984	0.0445	1.3984	1.1825
No log	4.0	24	2.2095	0.1452	2.2095	1.4864
No log	5.0	30	1.0417	0.0213	1.0417	1.0207
No log	6.0	36	2.0590	0.1973	2.0590	1.4349
No log	7.0	42	0.7883	0.3983	0.7883	0.8879
No log	8.0	48	1.3804	0.1264	1.3804	1.1749
No log	9.0	54	0.7325	0.4106	0.7325	0.8558
No log	10.0	60	1.0812	0.3566	1.0812	1.0398
No log	11.0	66	0.6495	0.4014	0.6495	0.8059
No log	12.0	72	0.7509	0.4090	0.7509	0.8666
No log	13.0	78	1.5518	0.2477	1.5518	1.2457
No log	14.0	84	0.7278	0.4971	0.7278	0.8531
No log	15.0	90	0.9346	0.4329	0.9346	0.9668
No log	16.0	96	0.8036	0.4496	0.8036	0.8964
No log	17.0	102	0.8480	0.4480	0.8480	0.9209
No log	18.0	108	0.7758	0.4124	0.7758	0.8808
No log	19.0	114	0.8511	0.3597	0.8511	0.9225
No log	20.0	120	0.8080	0.4198	0.8080	0.8989
No log	21.0	126	0.7027	0.4318	0.7027	0.8383
No log	22.0	132	0.7951	0.4154	0.7951	0.8917
No log	23.0	138	1.1914	0.2862	1.1914	1.0915
No log	24.0	144	0.9115	0.3570	0.9115	0.9547
No log	25.0	150	0.7551	0.4217	0.7551	0.8690
No log	26.0	156	0.9857	0.3617	0.9857	0.9928
No log	27.0	162	1.1134	0.2988	1.1134	1.0552
No log	28.0	168	1.3158	0.2692	1.3158	1.1471
No log	29.0	174	1.1936	0.2939	1.1936	1.0925

genki10/BERT_AugV8_k7_task1_organization_sp040_lw040_fold4

BERT_AugV8_k7_task1_organization_sp040_lw040_fold4