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	6.1594	0.0365	6.1580	2.4815
No log	2.0	14	2.6641	0.0023	2.6632	1.6319
No log	3.0	21	1.2536	0.0202	1.2528	1.1193
No log	4.0	28	1.0411	0.0401	1.0406	1.0201
No log	5.0	35	0.7805	0.3798	0.7801	0.8832
No log	6.0	42	0.7532	0.4306	0.7532	0.8679
No log	7.0	49	0.9112	0.3717	0.9116	0.9548
No log	8.0	56	0.8614	0.3351	0.8618	0.9283
No log	9.0	63	0.6056	0.4379	0.6061	0.7785
No log	10.0	70	0.7634	0.4411	0.7637	0.8739
No log	11.0	77	0.8862	0.4446	0.8865	0.9416
No log	12.0	84	1.2133	0.3406	1.2138	1.1017
No log	13.0	91	0.6806	0.5158	0.6808	0.8251
No log	14.0	98	0.6828	0.4837	0.6831	0.8265
No log	15.0	105	0.8663	0.3822	0.8668	0.9310
No log	16.0	112	1.1120	0.3269	1.1123	1.0547
No log	17.0	119	1.1731	0.3110	1.1734	1.0832
No log	18.0	126	0.7072	0.4855	0.7075	0.8411
No log	19.0	133	0.8550	0.4142	0.8552	0.9248
No log	20.0	140	0.7394	0.4752	0.7396	0.8600
No log	21.0	147	0.7168	0.4765	0.7169	0.8467
No log	22.0	154	1.5294	0.2366	1.5296	1.2368
No log	23.0	161	1.1010	0.3435	1.1012	1.0494
No log	24.0	168	1.0575	0.3335	1.0577	1.0284
No log	25.0	175	0.9278	0.3787	0.9280	0.9633
No log	26.0	182	0.9620	0.3593	0.9621	0.9809
No log	27.0	189	1.2750	0.2678	1.2751	1.1292
No log	28.0	196	1.1426	0.3075	1.1427	1.0690

genki10/BERT_AugV8_k10_task1_organization_sp010_lw060_fold3

BERT_AugV8_k10_task1_organization_sp010_lw060_fold3