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	8.4335	0.0	8.4339	2.9041
No log	2.0	6	4.8952	0.0203	4.8957	2.2126
No log	3.0	9	3.1673	0.0	3.1677	1.7798
No log	4.0	12	1.9505	0.0700	1.9510	1.3968
No log	5.0	15	1.3534	0.0107	1.3539	1.1636
No log	6.0	18	0.9310	0.0	0.9315	0.9651
No log	7.0	21	1.0587	0.0067	1.0591	1.0291
No log	8.0	24	0.8247	0.2499	0.8250	0.9083
No log	9.0	27	0.9349	0.1281	0.9352	0.9671
No log	10.0	30	0.7192	0.4041	0.7196	0.8483
No log	11.0	33	0.7330	0.3158	0.7335	0.8564
No log	12.0	36	0.7938	0.3043	0.7939	0.8910
No log	13.0	39	0.5902	0.5299	0.5903	0.7683
No log	14.0	42	1.3043	0.2418	1.3044	1.1421
No log	15.0	45	0.5436	0.4035	0.5434	0.7372
No log	16.0	48	0.6578	0.3225	0.6576	0.8109
No log	17.0	51	0.5686	0.4605	0.5688	0.7542
No log	18.0	54	0.8095	0.4449	0.8097	0.8998
No log	19.0	57	0.5088	0.5028	0.5087	0.7132
No log	20.0	60	0.5904	0.4177	0.5902	0.7682
No log	21.0	63	0.6185	0.4196	0.6186	0.7865
No log	22.0	66	0.5203	0.4824	0.5203	0.7213
No log	23.0	69	0.5511	0.4847	0.5512	0.7424
No log	24.0	72	0.6307	0.4383	0.6311	0.7944
No log	25.0	75	0.5619	0.5237	0.5621	0.7497
No log	26.0	78	0.6441	0.4665	0.6443	0.8027
No log	27.0	81	0.5903	0.4874	0.5904	0.7684
No log	28.0	84	0.7989	0.2778	0.7991	0.8939

genki10/BERT_AugV8_k3_task1_organization_sp020_lw040_fold2

BERT_AugV8_k3_task1_organization_sp020_lw040_fold2