deberta-pii-owndlp-checkpoints

Vaibhav3311v/deberta-pii-owndlp-checkpoints

deberta-pii-owndlp-checkpoints is a token classification model from Vaibhav3311v. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

32% of all-time downloads

All-time downloads

Public

Parameters

184M

368 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors368 MB · 98%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: deberta-v2
Access: Public
Created: Sep 20, 2026
Updated: Sep 27, 2026
SHA: 4224c21b

Try a prompt

Base models

microsoft/deberta-v3-base

Model card

From the Hugging Face model README

deberta-pii-owndlp-checkpoints

This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

Address F1: 0.0
Contact Email F1: 0.0
Contact Phone F1: 0.0
Credential Secret F1: 0.0
Date Of Birth F1: 0.0
Financial Bank Account F1: 0.0
Financial Credit Card F1: 0.0
Financial Iban F1: 0.0
Financial Ifsc F1: 0.0
Gov Id Aadhaar F1: 0.0
Gov Id Gstin F1: 0.0
Gov Id National Generic F1: 0.0
Gov Id Pan F1: 0.0
Job Title F1: 0.0
Medical Condition F1: 0.0
Network Ip F1: 0.0
Organization F1: 0.0
Person Name F1: 0.0
Username F1: 0.0
F1: 0.0
Loss: 3.2529
Precision: 0.0
Recall: 0.0

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: 2e-06
train_batch_size: 8
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
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
lr_scheduler_warmup_steps: 260
num_epochs: 4

Training results

Training Loss	Epoch	Step	Address F1	Contact Email F1	Contact Phone F1	Credential Secret F1	Date Of Birth F1	Financial Bank Account F1	Financial Credit Card F1	Financial Ifsc F1	Gov Id Aadhaar F1	Gov Id Gstin F1	Gov Id Pan F1	Job Title F1	Medical Condition F1	Organization F1	Person Name F1	Username F1	F1	Validation Loss	Precision	Recall
13.6149	0.1538	100	0.0	0.1572	0.0	0.0	0.1015	0.0	0.0	0.0	0.0	0.0	0.0	0.0105	0.0861	0.0024	0.1355	0.0	0.0589	2.0031	0.1247	0.0385
3.7565	0.3077	200	0.9971	1.0	1.0	0.0333	1.0	0.9519	0.0	0.9960	0.8116	0.9945	0.9399	0.9712	1.0	0.9938	0.9921	0.9574	0.9557	0.0772	0.9811	0.9317
0.4267	0.4615	300	1.0	0.9969	1.0	0.8954	1.0	1.0	0.9962	1.0	1.0	1.0	1.0	0.8665	1.0	0.9801	0.9943	0.9465	0.9812	0.0397	0.9764	0.9859
0.8863	0.6154	400	0.7898	0.9937	0.9869	0.9658	0.9372	0.9836	0.9618	0.8848	0.9893	0.7910	0.9622	0.9436	0.9925	0.9306	0.8154	0.88	0.8986	0.1106	0.8581	0.9431
4.9823	0.7692	500	0.2505	0.8256	0.8631	0.0	0.9019	0.0	0.0	0.8802	0.0279	0.5150	0.3720	0.7924	0.8040	0.4516	0.9124	0.4823	0.5937	0.7189	0.5845	0.6033
10.0716	0.9231	600	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2442	0.0	0.0
12.9110	1.0769	700	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2475	0.0	0.0
12.4971	1.2308	800	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2321	0.0	0.0
12.2021	1.3846	900	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2752	0.0	0.0
11.8339	1.5385	1000	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.3241	0.0	0.0
11.7611	1.6923	1100	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.3389	0.0	0.0
11.3559	1.8462	1200	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.3377	0.0	0.0
11.3732	2.0	1300	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2793	0.0	0.0
11.1335	2.1538	1400	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2968	0.0	0.0
10.9102	2.3077	1500	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2718	0.0	0.0
10.8216	2.4615	1600	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2493	0.0	0.0
10.8056	2.6154	1700	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2489	0.0	0.0
10.6459	2.7692	1800	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2440	0.0	0.0
10.6274	2.9231	1900	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2527	0.0	0.0
10.5310	3.0769	2000	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2445	0.0	0.0
10.5055	3.2308	2100	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2535	0.0	0.0
10.4186	3.3846	2200	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2479	0.0	0.0
10.3759	3.5385	2300	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2522	0.0	0.0
10.4262	3.6923	2400	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2546	0.0	0.0
10.4413	3.8462	2500	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2530	0.0	0.0
10.3997	4.0	2600	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3.2529	0.0	0.0

Framework versions

Transformers 5.16.1
Pytorch 2.11.0+cu128
Datasets 4.8.5
Tokenizers 0.23.1

Task: Token Classification
Library: transformers
Type: deberta-v2
License: mit
Created: Sep 20, 2026
Updated: Sep 27, 2026