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	6.7101	0.0	6.7101	2.5904
No log	2.0	8	3.7258	0.0040	3.7258	1.9302
No log	3.0	12	2.2722	0.0694	2.2722	1.5074
No log	4.0	16	1.3270	0.0316	1.3270	1.1520
No log	5.0	20	1.2888	0.0915	1.2888	1.1353
No log	6.0	24	0.8341	0.2696	0.8341	0.9133
No log	7.0	28	0.9449	0.4104	0.9449	0.9721
No log	8.0	32	1.3487	0.2361	1.3487	1.1613
No log	9.0	36	0.9866	0.2903	0.9866	0.9933
No log	10.0	40	1.2075	0.2041	1.2075	1.0989
No log	11.0	44	1.2874	0.4151	1.2874	1.1346
No log	12.0	48	1.6379	0.1501	1.6379	1.2798
No log	13.0	52	0.9638	0.3350	0.9638	0.9817
No log	14.0	56	2.2294	0.0086	2.2294	1.4931
No log	15.0	60	1.0271	0.3693	1.0271	1.0135
No log	16.0	64	1.3469	0.2457	1.3469	1.1606
No log	17.0	68	1.0820	0.3205	1.0820	1.0402
No log	18.0	72	1.4861	0.1550	1.4861	1.2191
No log	19.0	76	1.0488	0.3737	1.0488	1.0241
No log	20.0	80	1.8401	0.1367	1.8401	1.3565
No log	21.0	84	0.9669	0.4081	0.9669	0.9833
No log	22.0	88	1.3645	0.2037	1.3645	1.1681
No log	23.0	92	1.1929	0.2785	1.1929	1.0922
No log	24.0	96	1.1796	0.2611	1.1796	1.0861
No log	25.0	100	1.5387	0.1254	1.5387	1.2405
No log	26.0	104	1.0778	0.2890	1.0778	1.0381

genki10/Trial3BERT_AugV8_k5_task1_organization_sp030_lw010_fold4

Trial3BERT_AugV8_k5_task1_organization_sp030_lw010_fold4