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	7.6053	0.0	7.6053	2.7578
No log	2.0	8	5.8328	0.0222	5.8328	2.4151
No log	3.0	12	4.1277	0.0039	4.1277	2.0317
No log	4.0	16	2.4977	0.1207	2.4977	1.5804
No log	5.0	20	1.5899	0.0316	1.5899	1.2609
No log	6.0	24	1.7074	0.0316	1.7074	1.3067
No log	7.0	28	2.0797	0.1644	2.0797	1.4421
No log	8.0	32	1.2283	0.0382	1.2283	1.1083
No log	9.0	36	1.0856	0.0548	1.0856	1.0419
No log	10.0	40	1.6394	0.1456	1.6394	1.2804
No log	11.0	44	1.1642	0.1316	1.1642	1.0790
No log	12.0	48	0.8547	0.2745	0.8547	0.9245
No log	13.0	52	0.8518	0.3514	0.8518	0.9229
No log	14.0	56	0.8299	0.2736	0.8299	0.9110
No log	15.0	60	1.0068	0.1882	1.0068	1.0034
No log	16.0	64	0.8424	0.2573	0.8424	0.9178
No log	17.0	68	1.0888	0.1722	1.0888	1.0434
No log	18.0	72	0.9527	0.2158	0.9527	0.9760
No log	19.0	76	1.0876	0.2008	1.0876	1.0429
No log	20.0	80	1.5051	0.1480	1.5051	1.2268
No log	21.0	84	1.0783	0.2166	1.0783	1.0384
No log	22.0	88	1.2701	0.1698	1.2701	1.1270
No log	23.0	92	1.1286	0.2005	1.1286	1.0623
No log	24.0	96	1.0629	0.2624	1.0629	1.0310
No log	25.0	100	1.1246	0.2434	1.1246	1.0605
No log	26.0	104	1.0084	0.2407	1.0084	1.0042
No log	27.0	108	1.0411	0.2496	1.0411	1.0203
No log	28.0	112	1.1096	0.2498	1.1096	1.0534

genki10/BERT_AugV8_k5_task1_organization_sp060_lw040_fold0

BERT_AugV8_k5_task1_organization_sp060_lw040_fold0