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	8.1136	0.0018	8.1136	2.8484
No log	2.0	10	5.7249	0.0423	5.7249	2.3927
No log	3.0	15	3.4896	0.0040	3.4896	1.8680
No log	4.0	20	1.5417	0.0407	1.5417	1.2416
No log	5.0	25	1.0288	0.0238	1.0288	1.0143
No log	6.0	30	0.7965	0.3796	0.7965	0.8925
No log	7.0	35	1.2284	0.1060	1.2284	1.1083
No log	8.0	40	0.8994	0.2669	0.8994	0.9484
No log	9.0	45	0.7162	0.4065	0.7162	0.8463
No log	10.0	50	0.6976	0.4691	0.6976	0.8353
No log	11.0	55	0.6247	0.4228	0.6247	0.7904
No log	12.0	60	0.5830	0.4868	0.5830	0.7635
No log	13.0	65	0.6164	0.5552	0.6164	0.7851
No log	14.0	70	0.6940	0.5382	0.6940	0.8330
No log	15.0	75	0.5493	0.5723	0.5493	0.7412
No log	16.0	80	0.6364	0.6304	0.6364	0.7977
No log	17.0	85	0.7519	0.5419	0.7519	0.8671
No log	18.0	90	0.7657	0.5569	0.7657	0.8750
No log	19.0	95	0.7159	0.5490	0.7159	0.8461
No log	20.0	100	0.8043	0.5532	0.8043	0.8968
No log	21.0	105	0.8023	0.4833	0.8023	0.8957
No log	22.0	110	0.7318	0.5331	0.7318	0.8555
No log	23.0	115	0.7293	0.5325	0.7293	0.8540
No log	24.0	120	0.6370	0.5411	0.6370	0.7981
No log	25.0	125	0.7507	0.5047	0.7507	0.8664
No log	26.0	130	0.8705	0.4657	0.8705	0.9330
No log	27.0	135	0.8103	0.5044	0.8103	0.9001
No log	28.0	140	0.6572	0.5357	0.6572	0.8107
No log	29.0	145	0.5929	0.5467	0.5929	0.7700
No log	30.0	150	0.9591	0.4237	0.9591	0.9793
No log	31.0	155	0.6397	0.5308	0.6397	0.7998

genki10/Trial3BERT_AugV8_k7_task1_organization_sp010_lw010_fold4

Trial3BERT_AugV8_k7_task1_organization_sp010_lw010_fold4