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	5	9.2500	0.0	9.2475	3.0410
No log	2.0	10	5.4513	0.0404	5.4492	2.3344
No log	3.0	15	3.2322	0.0	3.2303	1.7973
No log	4.0	20	1.7113	0.0211	1.7097	1.3076
No log	5.0	25	1.0606	0.0	1.0591	1.0291
No log	6.0	30	1.0008	-0.0488	0.9993	0.9996
No log	7.0	35	1.1676	0.1219	1.1657	1.0797
No log	8.0	40	0.8094	0.3010	0.8077	0.8987
No log	9.0	45	0.9247	0.2240	0.9234	0.9609
No log	10.0	50	0.8733	0.2712	0.8718	0.9337
No log	11.0	55	0.7908	0.4297	0.7893	0.8884
No log	12.0	60	1.1192	0.2811	1.1172	1.0570
No log	13.0	65	0.9951	0.3183	0.9932	0.9966
No log	14.0	70	0.9339	0.3508	0.9320	0.9654
No log	15.0	75	1.0149	0.2988	1.0131	1.0065
No log	16.0	80	1.0048	0.3194	1.0033	1.0016
No log	17.0	85	1.0066	0.2698	1.0050	1.0025
No log	18.0	90	1.4612	0.2286	1.4594	1.2081
No log	19.0	95	0.8734	0.3644	0.8719	0.9338
No log	20.0	100	1.2049	0.2401	1.2030	1.0968
No log	21.0	105	1.3094	0.1983	1.3074	1.1434
No log	22.0	110	0.9830	0.2361	0.9814	0.9907
No log	23.0	115	1.2641	0.2155	1.2623	1.1235
No log	24.0	120	0.9324	0.2895	0.9308	0.9648
No log	25.0	125	1.2634	0.2683	1.2615	1.1231
No log	26.0	130	0.9599	0.2562	0.9583	0.9789

genki10/BERT_AugV8_k7_task1_organization_sp010_lw050_fold1

BERT_AugV8_k7_task1_organization_sp010_lw050_fold1