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	8.8829	0.0018	8.8829	2.9804
No log	2.0	14	4.7056	0.0079	4.7056	2.1692
No log	3.0	21	2.1131	0.1441	2.1131	1.4536
No log	4.0	28	1.0119	0.0366	1.0119	1.0059
No log	5.0	35	0.8045	0.3099	0.8045	0.8970
No log	6.0	42	1.0690	0.0354	1.0690	1.0339
No log	7.0	49	1.1573	0.1894	1.1573	1.0758
No log	8.0	56	2.3000	0.0263	2.3000	1.5166
No log	9.0	63	2.0733	0.0694	2.0733	1.4399
No log	10.0	70	0.9567	0.3194	0.9567	0.9781
No log	11.0	77	0.9521	0.3163	0.9521	0.9758
No log	12.0	84	2.2319	0.1096	2.2319	1.4940
No log	13.0	91	0.9134	0.3589	0.9134	0.9557
No log	14.0	98	0.8310	0.3378	0.8310	0.9116
No log	15.0	105	1.5593	0.2203	1.5593	1.2487
No log	16.0	112	1.8502	0.1895	1.8502	1.3602
No log	17.0	119	2.2169	0.1307	2.2169	1.4889
No log	18.0	126	0.8411	0.3565	0.8411	0.9171
No log	19.0	133	1.3437	0.2337	1.3437	1.1592
No log	20.0	140	1.2364	0.2554	1.2364	1.1119
No log	21.0	147	1.4952	0.2322	1.4952	1.2228
No log	22.0	154	1.5519	0.2270	1.5519	1.2458
No log	23.0	161	1.5168	0.2070	1.5168	1.2316
No log	24.0	168	2.0383	0.1567	2.0383	1.4277
No log	25.0	175	1.0739	0.2923	1.0739	1.0363
No log	26.0	182	1.2706	0.2645	1.2706	1.1272
No log	27.0	189	1.2886	0.2719	1.2886	1.1352
No log	28.0	196	1.5817	0.2379	1.5817	1.2576

genki10/Trial3BERT_AugV8_k10_task1_organization_sp010_lw030_fold4

Trial3BERT_AugV8_k10_task1_organization_sp010_lw030_fold4