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
0.1180	0.3322	500	0.0509	0.7814	0.8566	0.8173	0.9844
0.0591	0.6645	1000	0.0326	0.8853	0.9299	0.9070	0.9910
0.0383	0.9967	1500	0.0202	0.9219	0.9577	0.9395	0.9936
0.0359	1.3289	2000	0.0172	0.9408	0.9617	0.9511	0.9953
0.0233	1.6611	2500	0.0149	0.9469	0.9655	0.9561	0.9961
0.0226	1.9934	3000	0.0154	0.9458	0.9647	0.9551	0.9957
0.0137	2.3256	3500	0.0142	0.9583	0.9732	0.9657	0.9964
0.0112	2.6578	4000	0.0141	0.9542	0.9700	0.9620	0.9964
0.0105	2.9900	4500	0.0142	0.9523	0.9657	0.9589	0.9962
0.0049	3.3223	5000	0.0151	0.9599	0.9700	0.9650	0.9966

jefftherover/modernbert-pii-mapped-v13

modernbert-pii-mapped-v13