pii-layout-synth-v11

jefftherover/pii-layout-synth-v11

pii-layout-synth-v11 is a token classification model from jefftherover. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.

<a href="https://huggingface.co/spaces/jefftherover/huggingface-static-94c355" target="blank"<img src="https://raw.githubusercontent.com/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in T…

Downloads · 30 days

1% of all-time downloads

All-time downloads

1.1K

Public

Parameters

150M

58.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors599 MB · 99%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: modernbert
Access: Public
Created: Jun 26, 2026
Updated: Jun 26, 2026
SHA: 9d0e76e1

Try a prompt

Base models

answerdotai/ModernBERT-base

Model card

From the Hugging Face model README

pii-layout-synth-v11

This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0059
Precision: 0.9907
Recall: 0.9945
F1: 0.9926
Accuracy: 0.9987

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

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: 200
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0473	0.2455	500	0.0251	0.9491	0.9732	0.9610	0.9930
0.0235	0.4909	1000	0.0111	0.9727	0.9823	0.9775	0.9965
0.0194	0.7364	1500	0.0102	0.9796	0.9892	0.9844	0.9973
0.0156	0.9818	2000	0.0072	0.9812	0.9867	0.9839	0.9976
0.0091	1.2273	2500	0.0063	0.9865	0.9911	0.9888	0.9981
0.0111	1.4728	3000	0.0058	0.9860	0.9923	0.9891	0.9981
0.0071	1.7182	3500	0.0054	0.9873	0.9924	0.9899	0.9983
0.0081	1.9637	4000	0.0052	0.9883	0.9936	0.9910	0.9983
0.0055	2.2091	4500	0.0055	0.9874	0.9907	0.9891	0.9982
0.0051	2.4546	5000	0.0067	0.9882	0.9934	0.9908	0.9982
0.0031	2.7000	5500	0.0047	0.9896	0.9934	0.9915	0.9986
0.0037	2.9455	6000	0.0055	0.9893	0.9943	0.9918	0.9984
0.0013	3.1910	6500	0.0053	0.9901	0.9947	0.9924	0.9986
0.0012	3.4364	7000	0.0054	0.9899	0.9939	0.9919	0.9985
0.0011	3.6819	7500	0.0057	0.9904	0.9943	0.9924	0.9985
0.0010	3.9273	8000	0.0055	0.9906	0.9947	0.9926	0.9987
0.0003	4.1728	8500	0.0055	0.9910	0.9943	0.9926	0.9987
0.0003	4.4183	9000	0.0057	0.9907	0.9943	0.9925	0.9987
0.0004	4.6637	9500	0.0059	0.9907	0.9943	0.9925	0.9987
0.0002	4.9092	10000	0.0059	0.9907	0.9945	0.9926	0.9987

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

Task: Token Classification
Library: transformers
Type: modernbert
License: apache-2.0
Created: Jun 26, 2026
Updated: Jun 26, 2026