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	8.4162	0.0	8.4148	2.9008
No log	2.0	10	5.7051	0.0369	5.7037	2.3882
No log	3.0	15	2.9324	0.0010	2.9319	1.7123
No log	4.0	20	1.5346	0.0329	1.5339	1.2385
No log	5.0	25	1.5465	0.0427	1.5460	1.2434
No log	6.0	30	0.8697	0.3014	0.8695	0.9325
No log	7.0	35	0.9157	0.2460	0.9158	0.9570
No log	8.0	40	0.7463	0.3038	0.7464	0.8640
No log	9.0	45	0.6988	0.3865	0.6991	0.8361
No log	10.0	50	0.6562	0.4318	0.6567	0.8104
No log	11.0	55	0.6010	0.5339	0.6013	0.7754
No log	12.0	60	0.6213	0.5373	0.6214	0.7883
No log	13.0	65	0.7747	0.5160	0.7751	0.8804
No log	14.0	70	0.8711	0.4403	0.8713	0.9335
No log	15.0	75	0.6835	0.4995	0.6839	0.8270
No log	16.0	80	0.6391	0.5175	0.6395	0.7997
No log	17.0	85	0.6454	0.5507	0.6456	0.8035
No log	18.0	90	0.7625	0.4871	0.7627	0.8734
No log	19.0	95	0.9039	0.4536	0.9040	0.9508
No log	20.0	100	0.6869	0.5252	0.6871	0.8289
No log	21.0	105	0.6480	0.5588	0.6480	0.8050
No log	22.0	110	0.7180	0.5177	0.7182	0.8475
No log	23.0	115	0.7319	0.5085	0.7323	0.8557
No log	24.0	120	0.7141	0.5025	0.7144	0.8452
No log	25.0	125	0.7209	0.4794	0.7213	0.8493
No log	26.0	130	0.6650	0.5394	0.6652	0.8156
No log	27.0	135	0.7072	0.4873	0.7074	0.8411
No log	28.0	140	0.9707	0.3879	0.9710	0.9854
No log	29.0	145	0.9397	0.4034	0.9400	0.9695
No log	30.0	150	0.6748	0.4982	0.6751	0.8216
No log	31.0	155	0.7700	0.4540	0.7703	0.8777
No log	32.0	160	1.2308	0.3178	1.2311	1.1096
No log	33.0	165	0.7256	0.5050	0.7258	0.8519
No log	34.0	170	1.0749	0.3678	1.0751	1.0369
No log	35.0	175	0.7744	0.4466	0.7745	0.8801
No log	36.0	180	0.6579	0.4805	0.6581	0.8112

genki10/Trial3BERT_AugV8_k7_task1_organization_sp010_lw020_fold3

Trial3BERT_AugV8_k7_task1_organization_sp010_lw020_fold3