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	3	9.8031	0.0018	9.8031	3.1310
No log	2.0	6	6.7009	0.0003	6.7011	2.5886
No log	3.0	9	4.4780	0.0189	4.4785	2.1162
No log	4.0	12	3.2592	0.0039	3.2596	1.8054
No log	5.0	15	2.0970	0.1574	2.0973	1.4482
No log	6.0	18	1.8768	0.0810	1.8772	1.3701
No log	7.0	21	1.2348	0.0384	1.2352	1.1114
No log	8.0	24	1.1556	0.0449	1.1560	1.0752
No log	9.0	27	1.4894	0.0943	1.4897	1.2205
No log	10.0	30	1.2796	0.1084	1.2798	1.1313
No log	11.0	33	0.8286	0.3160	0.8286	0.9103
No log	12.0	36	1.3200	0.2270	1.3201	1.1489
No log	13.0	39	0.7285	0.4651	0.7283	0.8534
No log	14.0	42	0.7957	0.3727	0.7955	0.8919
No log	15.0	45	0.9526	0.3353	0.9525	0.9760
No log	16.0	48	0.6157	0.4299	0.6155	0.7845
No log	17.0	51	0.6044	0.5217	0.6040	0.7772
No log	18.0	54	0.7140	0.5284	0.7134	0.8446
No log	19.0	57	0.7528	0.4981	0.7521	0.8673
No log	20.0	60	1.3277	0.3480	1.3267	1.1518
No log	21.0	63	0.6553	0.4953	0.6545	0.8090
No log	22.0	66	0.8119	0.4285	0.8112	0.9007
No log	23.0	69	0.7766	0.4416	0.7759	0.8808
No log	24.0	72	0.8742	0.4356	0.8733	0.9345
No log	25.0	75	1.0245	0.3901	1.0236	1.0117
No log	26.0	78	0.9790	0.3865	0.9780	0.9889
No log	27.0	81	1.3288	0.3019	1.3279	1.1523
No log	28.0	84	0.7544	0.4518	0.7537	0.8681
No log	29.0	87	1.1568	0.3520	1.1561	1.0752
No log	30.0	90	0.7186	0.4895	0.7179	0.8473
No log	31.0	93	0.8998	0.3946	0.8990	0.9482
No log	32.0	96	0.7892	0.4189	0.7884	0.8879
No log	33.0	99	1.2141	0.3474	1.2133	1.1015

genki10/BERT_AugV8_k3_task1_organization_sp060_lw030_fold2

BERT_AugV8_k3_task1_organization_sp060_lw030_fold2