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	6.9500	0.0	6.9500	2.6363
No log	2.0	10	4.6233	0.0115	4.6233	2.1502
No log	3.0	15	2.4862	0.0737	2.4862	1.5768
No log	4.0	20	1.3540	0.0316	1.3540	1.1636
No log	5.0	25	0.9541	0.0106	0.9541	0.9768
No log	6.0	30	1.1695	0.0484	1.1695	1.0814
No log	7.0	35	0.9333	0.0584	0.9333	0.9661
No log	8.0	40	0.7909	0.3937	0.7909	0.8893
No log	9.0	45	0.6749	0.3263	0.6749	0.8215
No log	10.0	50	0.6672	0.2595	0.6672	0.8168
No log	11.0	55	0.8330	0.3120	0.8330	0.9127
No log	12.0	60	0.6026	0.3751	0.6026	0.7762
No log	13.0	65	0.6295	0.3536	0.6295	0.7934
No log	14.0	70	0.6479	0.4072	0.6479	0.8049
No log	15.0	75	0.7483	0.3518	0.7483	0.8651
No log	16.0	80	0.7231	0.3831	0.7231	0.8503
No log	17.0	85	0.6705	0.4658	0.6705	0.8188
No log	18.0	90	0.8503	0.3740	0.8503	0.9221
No log	19.0	95	0.8695	0.3262	0.8695	0.9325
No log	20.0	100	0.8503	0.2982	0.8503	0.9221
No log	21.0	105	0.7376	0.4208	0.7376	0.8588
No log	22.0	110	0.7270	0.4151	0.7270	0.8526
No log	23.0	115	0.6587	0.4831	0.6587	0.8116
No log	24.0	120	0.8145	0.3231	0.8145	0.9025
No log	25.0	125	0.8381	0.3071	0.8381	0.9155
No log	26.0	130	0.7530	0.4004	0.7530	0.8677
No log	27.0	135	0.8200	0.3292	0.8200	0.9055
No log	28.0	140	0.8207	0.3564	0.8207	0.9059
No log	29.0	145	0.8432	0.3597	0.8432	0.9182
No log	30.0	150	0.7027	0.4372	0.7027	0.8383
No log	31.0	155	0.7546	0.3816	0.7546	0.8687
No log	32.0	160	0.8423	0.3180	0.8423	0.9178
No log	33.0	165	0.9598	0.2797	0.9598	0.9797
No log	34.0	170	0.7748	0.3990	0.7748	0.8802
No log	35.0	175	0.8801	0.3672	0.8801	0.9381
No log	36.0	180	0.8000	0.3744	0.8000	0.8944
No log	37.0	185	0.8624	0.2742	0.8624	0.9287
No log	38.0	190	0.7352	0.3751	0.7352	0.8574

genki10/BERT_AugV8_k7_task1_organization_sp020_lw010_fold0

BERT_AugV8_k7_task1_organization_sp020_lw010_fold0