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	7	5.9583	0.0692	5.9570	2.4407
No log	2.0	14	2.3571	0.1863	2.3562	1.5350
No log	3.0	21	1.3638	0.0202	1.3630	1.1675
No log	4.0	28	1.0959	0.0292	1.0955	1.0466
No log	5.0	35	0.8749	0.2781	0.8746	0.9352
No log	6.0	42	1.0594	0.0672	1.0599	1.0295
No log	7.0	49	0.8647	0.1519	0.8648	0.9300
No log	8.0	56	1.0482	0.1123	1.0482	1.0238
No log	9.0	63	1.4294	-0.0312	1.4291	1.1955
No log	10.0	70	1.3130	0.0954	1.3127	1.1457
No log	11.0	77	1.3294	0.0013	1.3293	1.1529
No log	12.0	84	1.1284	0.2154	1.1279	1.0620
No log	13.0	91	1.8174	-0.0148	1.8164	1.3477
No log	14.0	98	1.3951	0.0131	1.3944	1.1809
No log	15.0	105	1.1126	0.1987	1.1122	1.0546
No log	16.0	112	1.1884	0.1488	1.1879	1.0899
No log	17.0	119	1.6623	0.0426	1.6615	1.2890
No log	18.0	126	1.2077	0.1650	1.2073	1.0988
No log	19.0	133	1.2796	0.0531	1.2791	1.1310
No log	20.0	140	1.2392	0.1235	1.2387	1.1130

genki10/BERT_AugV8_k10_task1_organization_sp040_lw030_fold3

BERT_AugV8_k10_task1_organization_sp040_lw030_fold3