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	10.0327	0.0	10.0305	3.1671
No log	2.0	10	5.9742	0.0497	5.9727	2.4439
No log	3.0	15	3.6519	0.0	3.6509	1.9107
No log	4.0	20	1.9957	0.0302	1.9948	1.4124
No log	5.0	25	1.3409	0.0202	1.3401	1.1576
No log	6.0	30	1.2210	0.0302	1.2205	1.1048
No log	7.0	35	1.5403	0.0636	1.5395	1.2408
No log	8.0	40	0.9624	0.2017	0.9622	0.9809
No log	9.0	45	1.3011	0.0964	1.3011	1.1407
No log	10.0	50	0.6824	0.4291	0.6827	0.8263
No log	11.0	55	0.6557	0.3627	0.6561	0.8100
No log	12.0	60	0.6529	0.3624	0.6534	0.8083
No log	13.0	65	0.7906	0.4405	0.7909	0.8893
No log	14.0	70	0.6936	0.4626	0.6941	0.8331
No log	15.0	75	0.6366	0.4546	0.6369	0.7981
No log	16.0	80	0.7701	0.4752	0.7703	0.8777
No log	17.0	85	0.6514	0.5285	0.6516	0.8072
No log	18.0	90	0.6950	0.4914	0.6950	0.8337
No log	19.0	95	1.1482	0.3276	1.1482	1.0715
No log	20.0	100	1.0489	0.3186	1.0489	1.0241
No log	21.0	105	1.0820	0.3327	1.0820	1.0402
No log	22.0	110	1.0815	0.3658	1.0814	1.0399
No log	23.0	115	0.8258	0.4235	0.8259	0.9088
No log	24.0	120	0.9901	0.3347	0.9903	0.9951
No log	25.0	125	0.9835	0.3306	0.9836	0.9918
No log	26.0	130	0.9390	0.3931	0.9390	0.9690
No log	27.0	135	0.9611	0.3595	0.9610	0.9803
No log	28.0	140	1.3192	0.3003	1.3191	1.1485
No log	29.0	145	1.0484	0.3539	1.0484	1.0239
No log	30.0	150	0.9669	0.3527	0.9669	0.9833
No log	31.0	155	0.9305	0.4016	0.9305	0.9646
No log	32.0	160	0.9730	0.3553	0.9731	0.9864

genki10/BERT_AugV8_k7_task1_organization_sp040_lw030_fold3

BERT_AugV8_k7_task1_organization_sp040_lw030_fold3