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	8.1054	0.0	8.1054	2.8470
No log	2.0	6	6.6971	0.0	6.6971	2.5879
No log	3.0	9	5.4424	0.0112	5.4424	2.3329
No log	4.0	12	4.2010	0.0039	4.2010	2.0496
No log	5.0	15	3.0730	0.0	3.0730	1.7530
No log	6.0	18	2.0771	0.0714	2.0771	1.4412
No log	7.0	21	1.4693	0.0316	1.4693	1.2121
No log	8.0	24	1.0371	0.0316	1.0371	1.0184
No log	9.0	27	1.3370	0.0638	1.3370	1.1563
No log	10.0	30	0.7105	0.4628	0.7105	0.8429
No log	11.0	33	0.9831	0.1220	0.9831	0.9915
No log	12.0	36	0.8157	0.2814	0.8157	0.9032
No log	13.0	39	0.7417	0.4210	0.7417	0.8612
No log	14.0	42	1.1859	0.2681	1.1859	1.0890
No log	15.0	45	0.5950	0.4451	0.5950	0.7713
No log	16.0	48	0.6312	0.3897	0.6312	0.7945
No log	17.0	51	0.9737	0.3681	0.9737	0.9868
No log	18.0	54	0.6279	0.3791	0.6279	0.7924
No log	19.0	57	0.5875	0.4062	0.5875	0.7665
No log	20.0	60	0.6447	0.4511	0.6447	0.8029
No log	21.0	63	0.7213	0.3703	0.7213	0.8493
No log	22.0	66	0.7467	0.3839	0.7467	0.8641
No log	23.0	69	0.7699	0.4137	0.7699	0.8774
No log	24.0	72	0.8262	0.3452	0.8262	0.9090
No log	25.0	75	0.7625	0.3925	0.7625	0.8732

genki10/BERT_AugV8_k3_task1_organization_sp010_lw050_fold0

BERT_AugV8_k3_task1_organization_sp010_lw050_fold0