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	8.2931	0.0018	8.2931	2.8798
No log	2.0	10	4.6250	0.0200	4.6250	2.1506
No log	3.0	15	2.2807	0.1525	2.2807	1.5102
No log	4.0	20	1.0943	0.0316	1.0943	1.0461
No log	5.0	25	0.9755	0.0420	0.9755	0.9877
No log	6.0	30	0.7291	0.4434	0.7291	0.8539
No log	7.0	35	0.6776	0.4965	0.6776	0.8232
No log	8.0	40	1.6855	0.2483	1.6855	1.2983
No log	9.0	45	0.6023	0.4558	0.6023	0.7761
No log	10.0	50	0.9100	0.3852	0.9100	0.9540
No log	11.0	55	0.6107	0.5137	0.6107	0.7815
No log	12.0	60	0.5800	0.5242	0.5800	0.7616
No log	13.0	65	0.6183	0.5518	0.6183	0.7863
No log	14.0	70	1.0226	0.4091	1.0226	1.0112
No log	15.0	75	0.8641	0.4896	0.8641	0.9295
No log	16.0	80	0.6422	0.5619	0.6422	0.8014
No log	17.0	85	0.6845	0.5373	0.6845	0.8273
No log	18.0	90	0.6424	0.5409	0.6424	0.8015
No log	19.0	95	0.6617	0.5323	0.6617	0.8134
No log	20.0	100	0.6936	0.5335	0.6936	0.8328
No log	21.0	105	0.7207	0.4927	0.7207	0.8489
No log	22.0	110	0.6388	0.5134	0.6388	0.7992
No log	23.0	115	0.6363	0.5483	0.6363	0.7977
No log	24.0	120	0.7485	0.4995	0.7485	0.8651
No log	25.0	125	0.7019	0.4817	0.7019	0.8378
No log	26.0	130	0.8240	0.4501	0.8240	0.9078
No log	27.0	135	0.6050	0.5517	0.6050	0.7778
No log	28.0	140	0.6629	0.5245	0.6629	0.8142
No log	29.0	145	0.5935	0.5544	0.5935	0.7704
No log	30.0	150	0.6482	0.5024	0.6482	0.8051
No log	31.0	155	0.6329	0.5421	0.6329	0.7955

genki10/BERT_AugV8_k7_task1_organization_sp020_lw010_fold4

BERT_AugV8_k7_task1_organization_sp020_lw010_fold4