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	10.4999	0.0	10.4979	3.2401
No log	2.0	8	8.0203	0.0	8.0188	2.8317
No log	3.0	12	6.5949	0.0	6.5933	2.5678
No log	4.0	16	4.5435	0.0	4.5424	2.1313
No log	5.0	20	2.9794	0.0	2.9784	1.7258
No log	6.0	24	1.8590	0.0391	1.8583	1.3632
No log	7.0	28	1.2711	0.0102	1.2705	1.1272
No log	8.0	32	0.9577	0.0166	0.9572	0.9784
No log	9.0	36	1.2811	0.0365	1.2804	1.1315
No log	10.0	40	1.0754	0.1138	1.0750	1.0368
No log	11.0	44	1.2394	0.0658	1.2387	1.1130
No log	12.0	48	0.8773	0.2698	0.8770	0.9365
No log	13.0	52	1.0175	0.1659	1.0176	1.0088
No log	14.0	56	0.6767	0.3707	0.6767	0.8226
No log	15.0	60	0.8902	0.2795	0.8903	0.9435
No log	16.0	64	0.6477	0.3804	0.6478	0.8049
No log	17.0	68	0.9136	0.2818	0.9140	0.9560
No log	18.0	72	0.5588	0.4850	0.5589	0.7476
No log	19.0	76	1.1700	0.1784	1.1697	1.0815
No log	20.0	80	0.6785	0.4335	0.6787	0.8238
No log	21.0	84	1.4482	0.1017	1.4480	1.2033
No log	22.0	88	0.5642	0.5646	0.5642	0.7511
No log	23.0	92	0.7224	0.3589	0.7222	0.8498
No log	24.0	96	0.9461	0.2630	0.9458	0.9725
No log	25.0	100	0.6192	0.5185	0.6189	0.7867
No log	26.0	104	0.8401	0.3519	0.8394	0.9162
No log	27.0	108	0.8224	0.3516	0.8220	0.9066
No log	28.0	112	1.1071	0.2357	1.1065	1.0519
No log	29.0	116	0.6662	0.5024	0.6660	0.8161
No log	30.0	120	1.0811	0.2537	1.0807	1.0396
No log	31.0	124	0.6397	0.5339	0.6396	0.7997
No log	32.0	128	1.3103	0.2457	1.3098	1.1445
No log	33.0	132	0.6251	0.5599	0.6249	0.7905
No log	34.0	136	1.1167	0.2610	1.1164	1.0566
No log	35.0	140	0.7331	0.4648	0.7329	0.8561
No log	36.0	144	0.9268	0.3228	0.9265	0.9626
No log	37.0	148	0.9821	0.2906	0.9820	0.9909

genki10/BERT_AugV8_k5_task1_organization_sp010_lw050_fold3

BERT_AugV8_k5_task1_organization_sp010_lw050_fold3