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	9.0010	0.0	9.0010	3.0002
No log	2.0	4	7.9460	0.0	7.9460	2.8189
No log	3.0	6	6.7236	0.0	6.7236	2.5930
No log	4.0	8	6.0687	-0.0072	6.0687	2.4635
No log	5.0	10	5.1731	0.0115	5.1731	2.2744
No log	6.0	12	4.4003	0.0039	4.4003	2.0977
No log	7.0	14	3.6304	0.0	3.6304	1.9054
No log	8.0	16	2.8665	0.0	2.8665	1.6931
No log	9.0	18	2.2428	0.0717	2.2428	1.4976
No log	10.0	20	1.8255	0.0409	1.8255	1.3511
No log	11.0	22	1.4465	0.0316	1.4465	1.2027
No log	12.0	24	1.2419	0.0316	1.2419	1.1144
No log	13.0	26	1.2146	0.0484	1.2146	1.1021
No log	14.0	28	0.9664	0.0484	0.9664	0.9831
No log	15.0	30	1.3609	0.1288	1.3609	1.1666
No log	16.0	32	1.7650	0.1901	1.7650	1.3285
No log	17.0	34	1.1725	0.1519	1.1725	1.0828
No log	18.0	36	0.7795	0.3738	0.7795	0.8829
No log	19.0	38	0.9747	0.3063	0.9747	0.9873
No log	20.0	40	1.6840	0.2075	1.6840	1.2977
No log	21.0	42	1.0587	0.3379	1.0587	1.0289
No log	22.0	44	0.6534	0.4485	0.6534	0.8083
No log	23.0	46	0.7838	0.4505	0.7838	0.8853
No log	24.0	48	1.7251	0.1896	1.7251	1.3134
No log	25.0	50	1.1556	0.2733	1.1556	1.0750
No log	26.0	52	0.6977	0.3774	0.6977	0.8353
No log	27.0	54	0.8688	0.3197	0.8688	0.9321
No log	28.0	56	1.3748	0.2130	1.3748	1.1725
No log	29.0	58	1.2345	0.2577	1.2345	1.1111
No log	30.0	60	0.8257	0.3421	0.8257	0.9087
No log	31.0	62	0.9450	0.3366	0.9450	0.9721
No log	32.0	64	1.0109	0.3564	1.0109	1.0054
No log	33.0	66	0.8716	0.3716	0.8716	0.9336
No log	34.0	68	1.0303	0.3596	1.0303	1.0150
No log	35.0	70	1.3050	0.2763	1.3050	1.1424
No log	36.0	72	1.0369	0.3332	1.0369	1.0183
No log	37.0	74	1.0428	0.3342	1.0428	1.0212
No log	38.0	76	1.1966	0.3082	1.1966	1.0939

genki10/BERT_AugV8_k1_task1_organization_sp060_lw030_fold0

BERT_AugV8_k1_task1_organization_sp060_lw030_fold0