roberta-base_ai4privacy_en

xXiaobuding/roberta-base_ai4privacy_en

roberta-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

17% of all-time downloads

All-time downloads

Public

Repo size

3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin497 MB · 99%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: roberta
Access: Public
Created: Apr 4, 2024
Updated: Apr 4, 2024
SHA: 0e7cf6ce

Try a prompt

Model card

From the Hugging Face model README

roberta-base_ai4privacy_en

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

Loss: 0.0962
Overall Precision: 0.8739
Overall Recall: 0.9046
Overall F1: 0.8890
Overall Accuracy: 0.9623
Accountname F1: 0.9898
Accountnumber F1: 0.9896
Age F1: 0.8745
Amount F1: 0.8663
Bic F1: 0.8782
Bitcoinaddress F1: 0.9414
Buildingnumber F1: 0.8279
City F1: 0.8312
Companyname F1: 0.9434
County F1: 0.9279
Creditcardcvv F1: 0.8947
Creditcardissuer F1: 0.9755
Creditcardnumber F1: 0.8770
Currency F1: 0.6753
Currencycode F1: 0.6398
Currencyname F1: 0.2105
Currencysymbol F1: 0.9223
Date F1: 0.8276
Dob F1: 0.5470
Email F1: 0.9840
Ethereumaddress F1: 0.9972
Eyecolor F1: 0.9027
Firstname F1: 0.8696
Gender F1: 0.9627
Height F1: 0.9811
Iban F1: 0.9912
Ip F1: 0.0124
Ipv4 F1: 0.8377
Ipv6 F1: 0.7585
Jobarea F1: 0.8212
Jobtitle F1: 0.9833
Jobtype F1: 0.9110
Lastname F1: 0.8305
Litecoinaddress F1: 0.8793
Mac F1: 0.9957
Maskednumber F1: 0.8315
Middlename F1: 0.9441
Nearbygpscoordinate F1: 0.9970
Ordinaldirection F1: 0.9682
Password F1: 0.9654
Phoneimei F1: 0.9944
Phonenumber F1: 0.9860
Pin F1: 0.8150
Prefix F1: 0.9306
Secondaryaddress F1: 0.9935
Sex F1: 0.9721
Ssn F1: 0.9759
State F1: 0.8817
Street F1: 0.8264
Time F1: 0.9485
Url F1: 0.9936
Useragent F1: 0.9976
Username F1: 0.9108
Vehiclevin F1: 0.9568
Vehiclevrm F1: 0.9239
Zipcode F1: 0.8543

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
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
0.3911	1.0	2175	0.2642	0.6000	0.6420	0.6203	0.9119	0.9177	0.8043	0.6417	0.2664	0.4444	0.7762	0.2639	0.3614	0.6320	0.5282	0.5097	0.8493	0.4381	0.2180	0.0	0.0	0.4754	0.6817	0.0	0.9518	0.9710	0.5435	0.5869	0.6865	0.5455	0.7382	0.0	0.7780	0.7260	0.3064	0.6099	0.5096	0.4491	0.5872	0.8521	0.4547	0.0365	0.9822	0.7915	0.7728	0.9553	0.8337	0.1159	0.8853	0.8930	0.9520	0.7916	0.1731	0.2881	0.7877	0.9793	0.9202	0.6108	0.7374	0.4551	0.5222
0.1748	2.0	4350	0.1410	0.7732	0.8035	0.7880	0.9479	0.9831	0.9575	0.8131	0.6771	0.8161	0.8795	0.6822	0.6022	0.8531	0.6954	0.8056	0.9663	0.8012	0.5330	0.3009	0.0571	0.8293	0.7760	0.3798	0.9646	0.9675	0.8677	0.6901	0.9239	0.9655	0.9073	0.0	0.8345	0.7913	0.7190	0.9331	0.8958	0.5220	0.7748	0.9913	0.7372	0.4010	0.9925	0.9558	0.8982	0.9359	0.9586	0.6094	0.8621	0.9891	0.9702	0.9464	0.5906	0.5943	0.9437	0.9936	0.9369	0.8300	0.9157	0.8207	0.7405
0.1081	3.0	6525	0.1143	0.8376	0.8825	0.8595	0.9559	0.9865	0.9803	0.8586	0.7828	0.8154	0.8297	0.7920	0.7957	0.9143	0.8413	0.8218	0.9628	0.8634	0.6290	0.5636	0.1324	0.8788	0.8283	0.4895	0.9797	0.9917	0.8895	0.8303	0.9294	0.9718	0.9746	0.0	0.8325	0.7976	0.7521	0.9647	0.9140	0.7495	0.7371	0.9848	0.7944	0.8836	0.9955	0.9701	0.9227	0.9944	0.9785	0.7427	0.9254	0.9924	0.9701	0.9527	0.8031	0.7519	0.9288	0.9929	0.9848	0.8880	0.9391	0.9251	0.8403
0.0804	4.0	8700	0.0962	0.8739	0.9046	0.8890	0.9623	0.9898	0.9896	0.8745	0.8663	0.8782	0.9414	0.8279	0.8312	0.9434	0.9279	0.8947	0.9755	0.8770	0.6753	0.6398	0.2105	0.9223	0.8276	0.5470	0.9840	0.9972	0.9027	0.8696	0.9627	0.9811	0.9912	0.0124	0.8377	0.7585	0.8212	0.9833	0.9110	0.8305	0.8793	0.9957	0.8315	0.9441	0.9970	0.9682	0.9654	0.9944	0.9860	0.8150	0.9306	0.9935	0.9721	0.9759	0.8817	0.8264	0.9485	0.9936	0.9976	0.9108	0.9568	0.9239	0.8543
0.0663	5.0	10875	0.0965	0.8761	0.9089	0.8922	0.9632	0.9882	0.9896	0.8845	0.8676	0.8750	0.9463	0.8280	0.8415	0.9482	0.9365	0.8954	0.9774	0.8897	0.6571	0.6773	0.2690	0.9217	0.8259	0.6135	0.9859	0.9972	0.9180	0.8840	0.9708	0.975	0.9667	0.1201	0.8109	0.7064	0.8298	0.9885	0.9265	0.8520	0.8844	0.9935	0.8523	0.9462	0.9985	0.9744	0.9682	0.9958	0.9881	0.8166	0.9333	0.9935	0.9721	0.9772	0.8889	0.8294	0.9632	0.9952	0.9976	0.9172	0.9538	0.9418	0.8638

Framework versions

Transformers 4.26.1
Pytorch 2.0.0.post200
Datasets 2.10.1
Tokenizers 0.13.3

Task: Token Classification
Library: transformers
Type: roberta
License: mit
Created: Apr 4, 2024
Updated: Apr 4, 2024