learning_rate: 1e-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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.6188	0.0305	500	0.3788	0.5431	0.6547	0.5937	0.9030
0.1746	0.0609	1000	0.1576	0.7686	0.8381	0.8019	0.9565
0.0857	0.0914	1500	0.1094	0.8148	0.8787	0.8455	0.9669
0.0624	0.1219	2000	0.0882	0.8475	0.8979	0.8720	0.9728
0.0512	0.1524	2500	0.0610	0.8834	0.9161	0.8994	0.9811
0.0445	0.1828	3000	0.0584	0.8968	0.9216	0.9090	0.9814
0.0398	0.2133	3500	0.0545	0.9097	0.9324	0.9209	0.9836
0.0355	0.2438	4000	0.0500	0.9125	0.9342	0.9232	0.9845
0.0337	0.2743	4500	0.0477	0.9068	0.9355	0.9209	0.9843
0.0309	0.3047	5000	0.0489	0.9214	0.9408	0.9310	0.9854
0.0284	0.3352	5500	0.0444	0.9173	0.9433	0.9301	0.9861
0.0278	0.3657	6000	0.0423	0.9247	0.9416	0.9331	0.9865
0.0258	0.3962	6500	0.0410	0.9291	0.9471	0.9380	0.9873
0.0242	0.4266	7000	0.0375	0.9301	0.9499	0.9399	0.9881
0.0241	0.4571	7500	0.0380	0.9321	0.9500	0.9410	0.9882
0.0217	0.4876	8000	0.0347	0.9404	0.9545	0.9474	0.9890
0.0207	0.5181	8500	0.0335	0.9360	0.9526	0.9442	0.9892
0.0204	0.5485	9000	0.0366	0.9364	0.9542	0.9452	0.9888
0.019	0.5790	9500	0.0362	0.9355	0.9534	0.9444	0.9887

gaodrew/deberta-pii-masking-augmented-test5

deberta-pii-masking-augmented-test5