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	5	7.8864	0.0018	7.8864	2.8083
No log	2.0	10	3.9419	0.0050	3.9419	1.9854
No log	3.0	15	1.9986	0.0610	1.9986	1.4137
No log	4.0	20	1.1620	0.0107	1.1620	1.0779
No log	5.0	25	1.0789	0.0107	1.0789	1.0387
No log	6.0	30	1.1126	0.0107	1.1126	1.0548
No log	7.0	35	1.0903	0.0329	1.0903	1.0442
No log	8.0	40	0.8853	0.2319	0.8853	0.9409
No log	9.0	45	0.8564	0.3254	0.8564	0.9254
No log	10.0	50	0.9124	0.3623	0.9124	0.9552
No log	11.0	55	0.6780	0.4172	0.6780	0.8234
No log	12.0	60	0.6274	0.4522	0.6274	0.7921
No log	13.0	65	0.7096	0.4518	0.7096	0.8424
No log	14.0	70	1.1526	0.3578	1.1526	1.0736
No log	15.0	75	0.6934	0.4842	0.6934	0.8327
No log	16.0	80	0.7286	0.4799	0.7286	0.8536
No log	17.0	85	1.4348	0.2293	1.4348	1.1978
No log	18.0	90	0.9149	0.3874	0.9149	0.9565
No log	19.0	95	0.8750	0.4119	0.8750	0.9354
No log	20.0	100	0.9184	0.3975	0.9184	0.9584
No log	21.0	105	0.8657	0.3991	0.8657	0.9305
No log	22.0	110	1.0798	0.3396	1.0798	1.0391
No log	23.0	115	0.8053	0.3797	0.8053	0.8974
No log	24.0	120	0.7777	0.3966	0.7777	0.8819
No log	25.0	125	0.8529	0.4181	0.8529	0.9235
No log	26.0	130	0.8452	0.4042	0.8452	0.9193
No log	27.0	135	1.0081	0.3919	1.0081	1.0040
No log	28.0	140	1.1053	0.3711	1.1053	1.0513
No log	29.0	145	0.9211	0.4038	0.9211	0.9597
No log	30.0	150	0.8173	0.4170	0.8173	0.9040

genki10/BERT_AugV8_k7_task1_organization_sp010_lw050_fold4

BERT_AugV8_k7_task1_organization_sp010_lw050_fold4