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	2	11.0011	0.0058	11.0013	3.3168
No log	2.0	4	10.4917	0.0	10.4918	3.2391
No log	3.0	6	9.9694	0.0	9.9696	3.1575
No log	4.0	8	9.3395	0.0	9.3396	3.0561
No log	5.0	10	8.5744	0.0	8.5745	2.9282
No log	6.0	12	7.7620	0.0	7.7622	2.7861
No log	7.0	14	6.8761	0.0	6.8763	2.6223
No log	8.0	16	5.9238	-0.0013	5.9241	2.4339
No log	9.0	18	5.1163	0.0	5.1166	2.2620
No log	10.0	20	4.3666	0.0	4.3670	2.0897
No log	11.0	22	3.5755	0.0	3.5759	1.8910
No log	12.0	24	2.9412	0.0	2.9417	1.7151
No log	13.0	26	2.3623	0.0481	2.3628	1.5371
No log	14.0	28	1.8063	0.0107	1.8068	1.3442
No log	15.0	30	1.4639	0.0	1.4644	1.2101
No log	16.0	32	1.2651	0.0	1.2656	1.1250
No log	17.0	34	1.2125	0.0	1.2130	1.1014
No log	18.0	36	1.2266	0.0	1.2272	1.1078
No log	19.0	38	1.1610	0.0	1.1615	1.0777
No log	20.0	40	0.8938	0.1339	0.8942	0.9456
No log	21.0	42	0.7567	0.3790	0.7571	0.8701
No log	22.0	44	0.8614	0.2426	0.8618	0.9283
No log	23.0	46	0.6791	0.4350	0.6793	0.8242
No log	24.0	48	0.6251	0.3914	0.6252	0.7907
No log	25.0	50	0.7530	0.3607	0.7531	0.8678
No log	26.0	52	0.8288	0.3533	0.8289	0.9104
No log	27.0	54	0.6485	0.4148	0.6484	0.8052
No log	28.0	56	0.6999	0.3951	0.6997	0.8365
No log	29.0	58	0.7776	0.3410	0.7774	0.8817
No log	30.0	60	1.0973	0.2450	1.0972	1.0475
No log	31.0	62	0.9749	0.2976	0.9747	0.9873
No log	32.0	64	0.7738	0.3225	0.7736	0.8795
No log	33.0	66	0.9958	0.2546	0.9956	0.9978
No log	34.0	68	0.9446	0.2737	0.9443	0.9717
No log	35.0	70	0.8213	0.3512	0.8207	0.9059
No log	36.0	72	1.1270	0.2656	1.1262	1.0612
No log	37.0	74	1.1413	0.2536	1.1404	1.0679
No log	38.0	76	0.8159	0.3636	0.8150	0.9028

genki10/Trial3BERT_AugV8_k1_task1_organization_sp020_lw020_fold2

Trial3BERT_AugV8_k1_task1_organization_sp020_lw020_fold2