learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_steps: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0656	0.3591	500	0.0333	0.8816	0.9458	0.9125	0.9910
0.0408	0.7181	1000	0.0189	0.9444	0.9723	0.9582	0.9949
0.0156	1.0768	1500	0.0099	0.9639	0.9865	0.9751	0.9969
0.0136	1.4359	2000	0.0104	0.9695	0.9935	0.9814	0.9972
0.0163	1.7950	2500	0.0094	0.9617	0.9769	0.9692	0.9969
0.0061	2.1537	3000	0.0080	0.9728	0.9917	0.9822	0.9978
0.0080	2.5127	3500	0.0069	0.9757	0.9935	0.9845	0.9980
0.0075	2.8718	4000	0.0076	0.9778	0.9917	0.9847	0.9981
0.0023	3.2305	4500	0.0078	0.9778	0.9929	0.9853	0.9981
0.0020	3.5896	5000	0.0076	0.9783	0.9916	0.9849	0.9980
0.0017	3.9487	5500	0.0073	0.9766	0.9890	0.9828	0.9981
0.0005	4.3074	6000	0.0078	0.9792	0.9925	0.9858	0.9982
0.0006	4.6664	6500	0.0076	0.9787	0.9906	0.9846	0.9982
0.0007	5.0	6965	0.0077	0.9787	0.9909	0.9848	0.9982

jefftherover/modernbert-pii-mapped-v12

modernbert-pii-mapped-v12