deberta-v3-base_ai4privacy_en

xXiaobuding/deberta-v3-base_ai4privacy_en

deberta-v3-base_ai4privacy_en is a token classification model from xXiaobuding. 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

9% of all-time downloads

All-time downloads

Public

Repo size

4.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin736 MB · 99%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: deberta-v2
Access: Public
Created: Mar 10, 2024
Updated: Mar 10, 2024
SHA: 9e3d28f3

Try a prompt

Model card

From the Hugging Face model README

deberta-v3-base_ai4privacy_en

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1055
Overall Precision: 0.8683
Overall Recall: 0.8949
Overall F1: 0.8814
Overall Accuracy: 0.9609
Accountname F1: 0.9898
Accountnumber F1: 0.9939
Age F1: 0.8397
Amount F1: 0.9169
Bic F1: 0.9012
Bitcoinaddress F1: 0.9583
Buildingnumber F1: 0.8109
City F1: 0.8011
Companyname F1: 0.9437
County F1: 0.8752
Creditcardcvv F1: 0.8635
Creditcardissuer F1: 0.9738
Creditcardnumber F1: 0.8771
Currency F1: 0.6542
Currencycode F1: 0.5566
Currencyname F1: 0.2214
Currencysymbol F1: 0.8640
Date F1: 0.8365
Dob F1: 0.5696
Email F1: 0.9914
Ethereumaddress F1: 0.9903
Eyecolor F1: 0.9076
Firstname F1: 0.8759
Gender F1: 0.9324
Height F1: 0.9046
Iban F1: 0.9899
Ip F1: 0.1137
Ipv4 F1: 0.8118
Ipv6 F1: 0.8091
Jobarea F1: 0.7895
Jobtitle F1: 0.9806
Jobtype F1: 0.9056
Lastname F1: 0.8179
Litecoinaddress F1: 0.8739
Mac F1: 1.0
Maskednumber F1: 0.8319
Middlename F1: 0.8419
Nearbygpscoordinate F1: 1.0
Ordinaldirection F1: 0.9682
Password F1: 0.9595
Phoneimei F1: 0.9930
Phonenumber F1: 0.9807
Pin F1: 0.7868
Prefix F1: 0.9355
Secondaryaddress F1: 0.9967
Sex F1: 0.9692
Ssn F1: 0.9898
State F1: 0.7407
Street F1: 0.7823
Time F1: 0.9500
Url F1: 0.9936
Useragent F1: 0.9976
Username F1: 0.9331
Vehiclevin F1: 0.9713
Vehiclevrm F1: 0.9493
Zipcode F1: 0.8634

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: 8
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.2
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Overall Precision	Overall Recall	Overall F1	Overall Accuracy	Accountname F1	Accountnumber F1	Age F1	Amount F1	Bic F1	Bitcoinaddress F1	Buildingnumber F1	City F1	Companyname F1	County F1	Creditcardcvv F1	Creditcardissuer F1	Creditcardnumber F1	Currency F1	Currencycode F1	Currencyname F1	Currencysymbol F1	Date F1	Dob F1	Email F1	Ethereumaddress F1	Eyecolor F1	Firstname F1	Gender F1	Height F1	Iban F1	Ip F1	Ipv4 F1	Ipv6 F1	Jobarea F1	Jobtitle F1	Jobtype F1	Lastname F1	Litecoinaddress F1	Mac F1	Maskednumber F1	Middlename F1	Nearbygpscoordinate F1	Ordinaldirection F1	Password F1	Phoneimei F1	Phonenumber F1	Pin F1	Prefix F1	Secondaryaddress F1	Sex F1	Ssn F1	State F1	Street F1	Time F1	Url F1	Useragent F1	Username F1	Vehiclevin F1	Vehiclevrm F1	Zipcode F1
0.463	1.0	4350	0.3229	0.5378	0.5277	0.5327	0.8941	0.8722	0.7667	0.5849	0.2284	0.5391	0.7502	0.3143	0.1514	0.2844	0.2640	0.0086	0.5288	0.0	0.0956	0.0	0.0	0.3410	0.7146	0.0169	0.8043	0.9458	0.0090	0.4894	0.1550	0.0	0.8653	0.0	0.8168	0.7474	0.1611	0.4548	0.0035	0.3781	0.1472	0.8989	0.4641	0.0035	0.9955	0.0	0.7959	0.9464	0.7831	0.2258	0.7847	0.8639	0.5481	0.7480	0.0643	0.1795	0.7463	0.9683	0.9080	0.4569	0.8724	0.5152	0.5458
0.1944	2.0	8700	0.1709	0.7179	0.7495	0.7334	0.9387	0.9789	0.9718	0.6535	0.4640	0.6039	0.9240	0.6723	0.4777	0.8654	0.6234	0.7241	0.8713	0.6077	0.4598	0.0698	0.0104	0.6163	0.7518	0.4439	0.9803	0.9848	0.6276	0.6714	0.7937	0.6295	0.9538	0.0	0.8285	0.7976	0.5304	0.9253	0.6957	0.4694	0.7181	0.9892	0.6301	0.2027	0.9865	0.8016	0.7931	0.9888	0.9658	0.3231	0.8959	0.9721	0.8506	0.9692	0.3841	0.4389	0.9064	0.9905	0.9670	0.8341	0.9563	0.8449	0.7487
0.1275	3.0	13050	0.1174	0.8276	0.8506	0.8390	0.9559	0.9881	0.9896	0.7347	0.8484	0.8214	0.9571	0.7815	0.7437	0.9289	0.7794	0.8323	0.9754	0.8624	0.4890	0.4318	0.2006	0.8043	0.8066	0.5459	0.9858	0.9903	0.8511	0.8071	0.8187	0.8657	0.9486	0.0	0.8396	0.8049	0.7326	0.9720	0.8699	0.6714	0.8655	0.9957	0.8194	0.6478	1.0	0.9660	0.9331	0.9916	0.9711	0.6899	0.9302	0.9902	0.9413	0.9847	0.5684	0.7259	0.9381	0.9929	0.9953	0.9094	0.9598	0.9115	0.8324
0.0976	4.0	17400	0.1065	0.8624	0.8877	0.8749	0.9598	0.9907	0.9939	0.8312	0.9141	0.8689	0.9511	0.8027	0.8014	0.9538	0.8827	0.8599	0.9701	0.8634	0.6637	0.5488	0.1181	0.8541	0.8224	0.5333	0.9926	0.9876	0.9041	0.8664	0.9303	0.9207	0.9861	0.0591	0.8174	0.8098	0.7798	0.9686	0.9013	0.7845	0.8661	1.0	0.8091	0.8103	1.0	0.9785	0.9430	0.9916	0.9806	0.7778	0.9354	0.9913	0.9692	0.9885	0.7476	0.7658	0.9427	0.9889	0.9976	0.9346	0.9797	0.9570	0.8362
0.0886	5.0	21750	0.1055	0.8683	0.8949	0.8814	0.9609	0.9898	0.9939	0.8397	0.9169	0.9012	0.9583	0.8109	0.8011	0.9437	0.8752	0.8635	0.9738	0.8771	0.6542	0.5566	0.2214	0.8640	0.8365	0.5696	0.9914	0.9903	0.9076	0.8759	0.9324	0.9046	0.9899	0.1137	0.8118	0.8091	0.7895	0.9806	0.9056	0.8179	0.8739	1.0	0.8319	0.8419	1.0	0.9682	0.9595	0.9930	0.9807	0.7868	0.9355	0.9967	0.9692	0.9898	0.7407	0.7823	0.9500	0.9936	0.9976	0.9331	0.9713	0.9493	0.8634

Framework versions

Transformers 4.26.1
Pytorch 2.0.0.post101
Datasets 2.10.1
Tokenizers 0.13.3

Task: Token Classification
Library: transformers
Type: deberta-v2
License: mit
Created: Mar 10, 2024
Updated: Mar 10, 2024