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	4	9.0839	0.0	9.0814	3.0135
No log	2.0	8	7.6766	0.0	7.6742	2.7702
No log	3.0	12	6.1731	0.0	6.1708	2.4841
No log	4.0	16	4.5851	0.0	4.5830	2.1408
No log	5.0	20	3.1042	0.0	3.1024	1.7614
No log	6.0	24	2.0957	0.1011	2.0939	1.4470
No log	7.0	28	1.4092	0.0211	1.4076	1.1864
No log	8.0	32	0.9950	0.0211	0.9937	0.9969
No log	9.0	36	1.4801	0.0315	1.4786	1.2160
No log	10.0	40	1.6242	0.0430	1.6228	1.2739
No log	11.0	44	1.2791	0.0521	1.2779	1.1305
No log	12.0	48	0.7535	0.3371	0.7525	0.8675
No log	13.0	52	0.7761	0.3221	0.7751	0.8804
No log	14.0	56	0.7536	0.3182	0.7528	0.8676
No log	15.0	60	0.6791	0.3906	0.6786	0.8238
No log	16.0	64	0.9128	0.3218	0.9124	0.9552
No log	17.0	68	1.6498	0.0970	1.6492	1.2842
No log	18.0	72	1.3632	0.1523	1.3627	1.1674
No log	19.0	76	1.4327	0.1200	1.4321	1.1967
No log	20.0	80	1.7426	-0.0069	1.7416	1.3197
No log	21.0	84	1.1465	0.2032	1.1456	1.0703
No log	22.0	88	1.9487	0.0307	1.9475	1.3955
No log	23.0	92	1.2611	0.0964	1.2598	1.1224
No log	24.0	96	1.5920	0.0218	1.5905	1.2612
No log	25.0	100	1.7270	0.1064	1.7259	1.3137
No log	26.0	104	1.1039	0.2247	1.1029	1.0502
No log	27.0	108	1.9292	-0.0077	1.9278	1.3884
No log	28.0	112	1.0737	0.1910	1.0727	1.0357
No log	29.0	116	1.8041	0.0970	1.8030	1.3428
No log	30.0	120	1.5475	0.1226	1.5466	1.2436

genki10/BERT_AugV8_k5_task1_organization_sp010_lw050_fold1

BERT_AugV8_k5_task1_organization_sp010_lw050_fold1