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	8	8.2384	0.0	8.2368	2.8700
No log	2.0	16	4.6898	0.0	4.6886	2.1653
No log	3.0	24	2.0738	0.0706	2.0731	1.4398
No log	4.0	32	1.1936	0.0202	1.1931	1.0923
No log	5.0	40	0.9271	0.1581	0.9267	0.9626
No log	6.0	48	0.9106	0.2244	0.9106	0.9543
No log	7.0	56	0.9403	0.3095	0.9400	0.9695
No log	8.0	64	0.8209	0.3533	0.8211	0.9061
No log	9.0	72	0.6855	0.3816	0.6857	0.8280
No log	10.0	80	1.3894	0.2847	1.3893	1.1787
No log	11.0	88	1.9454	0.2230	1.9451	1.3947
No log	12.0	96	1.7179	0.2356	1.7175	1.3105
No log	13.0	104	1.2198	0.2800	1.2196	1.1044
No log	14.0	112	0.9986	0.3332	0.9985	0.9992
No log	15.0	120	0.7715	0.4286	0.7716	0.8784
No log	16.0	128	1.0546	0.3498	1.0545	1.0269
No log	17.0	136	1.4476	0.1948	1.4471	1.2030
No log	18.0	144	1.2817	0.2563	1.2814	1.1320
No log	19.0	152	0.7648	0.4436	0.7648	0.8745
No log	20.0	160	1.0068	0.3484	1.0067	1.0033
No log	21.0	168	0.9256	0.3673	0.9255	0.9621
No log	22.0	176	1.1067	0.3227	1.1064	1.0518
No log	23.0	184	1.7529	0.2322	1.7524	1.3238
No log	24.0	192	1.3244	0.2805	1.3240	1.1507
No log	25.0	200	1.2523	0.2859	1.2521	1.1190
No log	26.0	208	1.0745	0.3166	1.0741	1.0364
No log	27.0	216	1.1169	0.3276	1.1167	1.0567
No log	28.0	224	1.5555	0.2439	1.5550	1.2470
No log	29.0	232	1.2682	0.3032	1.2679	1.1260
No log	30.0	240	1.7281	0.2210	1.7276	1.3144
No log	31.0	248	1.4993	0.2382	1.4989	1.2243
No log	32.0	256	1.4468	0.2485	1.4465	1.2027
No log	33.0	264	1.7322	0.2147	1.7317	1.3159
No log	34.0	272	1.1718	0.2929	1.1715	1.0823

genki10/BERT_AugV8_k10_task1_organization_sp010_lw070_fold3

BERT_AugV8_k10_task1_organization_sp010_lw070_fold3