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	7	7.1330	0.0	7.1330	2.6708
No log	2.0	14	4.3895	0.0077	4.3895	2.0951
No log	3.0	21	2.2092	0.0511	2.2092	1.4863
No log	4.0	28	1.1784	0.0316	1.1784	1.0855
No log	5.0	35	0.9272	0.0348	0.9272	0.9629
No log	6.0	42	0.8805	0.1096	0.8805	0.9383
No log	7.0	49	0.7029	0.2965	0.7029	0.8384
No log	8.0	56	1.9178	0.1433	1.9178	1.3849
No log	9.0	63	0.8073	0.2964	0.8073	0.8985
No log	10.0	70	0.7562	0.3133	0.7562	0.8696
No log	11.0	77	1.0268	0.1703	1.0268	1.0133
No log	12.0	84	0.9408	0.3355	0.9408	0.9700
No log	13.0	91	0.7292	0.3299	0.7292	0.8540
No log	14.0	98	0.8202	0.3876	0.8202	0.9056
No log	15.0	105	0.8316	0.3750	0.8316	0.9119
No log	16.0	112	0.7819	0.4314	0.7819	0.8843
No log	17.0	119	0.8461	0.3873	0.8461	0.9198
No log	18.0	126	0.9774	0.3342	0.9774	0.9887
No log	19.0	133	1.3417	0.1921	1.3417	1.1583
No log	20.0	140	1.0253	0.2799	1.0253	1.0126
No log	21.0	147	0.8252	0.4180	0.8252	0.9084
No log	22.0	154	0.7400	0.3601	0.7400	0.8602
No log	23.0	161	0.8455	0.3605	0.8455	0.9195
No log	24.0	168	0.9569	0.2999	0.9569	0.9782
No log	25.0	175	0.7666	0.3793	0.7666	0.8756
No log	26.0	182	1.0041	0.2920	1.0041	1.0021
No log	27.0	189	0.9963	0.2903	0.9963	0.9981
No log	28.0	196	1.1455	0.2140	1.1455	1.0703
No log	29.0	203	0.8852	0.2511	0.8852	0.9409
No log	30.0	210	0.7899	0.3629	0.7899	0.8888
No log	31.0	217	0.8615	0.2732	0.8615	0.9281

genki10/Trial3BERT_AugV8_k10_task1_organization_sp010_lw030_fold0

Trial3BERT_AugV8_k10_task1_organization_sp010_lw030_fold0