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	8.9299	0.0	8.9275	2.9879
No log	2.0	8	6.4920	0.0	6.4896	2.5475
No log	3.0	12	3.7055	0.0040	3.7033	1.9244
No log	4.0	16	2.5180	0.0319	2.5164	1.5863
No log	5.0	20	1.6422	0.0337	1.6406	1.2808
No log	6.0	24	1.2080	0.0106	1.2066	1.0984
No log	7.0	28	1.0103	0.0	1.0089	1.0044
No log	8.0	32	1.8821	-0.0177	1.8802	1.3712
No log	9.0	36	0.9367	0.1206	0.9351	0.9670
No log	10.0	40	1.2235	0.0899	1.2214	1.1052
No log	11.0	44	0.8783	0.1263	0.8769	0.9364
No log	12.0	48	0.8966	0.1634	0.8952	0.9461
No log	13.0	52	0.9089	0.2493	0.9074	0.9526
No log	14.0	56	0.7741	0.2822	0.7732	0.8793
No log	15.0	60	0.7589	0.4012	0.7579	0.8706
No log	16.0	64	0.9230	0.3353	0.9217	0.9601
No log	17.0	68	0.7892	0.4026	0.7881	0.8878
No log	18.0	72	0.9596	0.3439	0.9585	0.9790
No log	19.0	76	1.4122	0.2097	1.4109	1.1878
No log	20.0	80	0.8604	0.3984	0.8594	0.9271
No log	21.0	84	0.9168	0.3687	0.9155	0.9568
No log	22.0	88	0.8929	0.3561	0.8914	0.9442
No log	23.0	92	0.9912	0.3099	0.9896	0.9948
No log	24.0	96	1.0915	0.2604	1.0898	1.0439
No log	25.0	100	1.0013	0.2244	1.0000	1.0000
No log	26.0	104	1.3239	0.1951	1.3221	1.1498
No log	27.0	108	0.8862	0.3462	0.8848	0.9406
No log	28.0	112	1.4632	0.2089	1.4612	1.2088
No log	29.0	116	0.9920	0.3163	0.9904	0.9952
No log	30.0	120	1.0264	0.2743	1.0248	1.0123
No log	31.0	124	1.2750	0.2256	1.2732	1.1284
No log	32.0	128	0.9164	0.3092	0.9150	0.9566

genki10/BERT_AugV8_k5_task1_organization_sp020_lw040_fold1

BERT_AugV8_k5_task1_organization_sp020_lw040_fold1