xlm-roberta-base_ai4privacy_en

xXiaobuding/xlm-roberta-base_ai4privacy_en

xlm-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

6.7 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.1 GB · 98%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: xlm-roberta
Access: Public
Created: Mar 10, 2024
Updated: Mar 12, 2024
SHA: 718ead74

Try a prompt

Model card

From the Hugging Face model README

xlm-roberta-base_ai4privacy_en

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

Loss: 0.1063
Overall Precision: 0.9013
Overall Recall: 0.9238
Overall F1: 0.9124
Overall Accuracy: 0.9651
Accountname F1: 0.9932
Accountnumber F1: 0.9939
Age F1: 0.9002
Amount F1: 0.8985
Bic F1: 0.8820
Bitcoinaddress F1: 0.9592
Buildingnumber F1: 0.8566
City F1: 0.8694
Companyname F1: 0.9675
County F1: 0.9727
Creditcardcvv F1: 0.9067
Creditcardissuer F1: 0.9775
Creditcardnumber F1: 0.8987
Currency F1: 0.7436
Currencycode F1: 0.7229
Currencyname F1: 0.2329
Currencysymbol F1: 0.9477
Date F1: 0.8368
Dob F1: 0.6093
Email F1: 0.992
Ethereumaddress F1: 0.9931
Eyecolor F1: 0.9465
Firstname F1: 0.9244
Gender F1: 0.9758
Height F1: 0.9781
Iban F1: 0.9862
Ip F1: 0.0575
Ipv4 F1: 0.8350
Ipv6 F1: 0.8063
Jobarea F1: 0.8548
Jobtitle F1: 0.9789
Jobtype F1: 0.9298
Lastname F1: 0.9075
Litecoinaddress F1: 0.8739
Mac F1: 0.9849
Maskednumber F1: 0.8504
Middlename F1: 0.9595
Nearbygpscoordinate F1: 0.9955
Ordinaldirection F1: 0.9723
Password F1: 0.9469
Phoneimei F1: 0.9944
Phonenumber F1: 0.9828
Pin F1: 0.8348
Prefix F1: 0.9362
Secondaryaddress F1: 0.9902
Sex F1: 0.9722
Ssn F1: 0.9772
State F1: 0.9462
Street F1: 0.8983
Time F1: 0.9665
Url F1: 0.9944
Useragent F1: 0.9859
Username F1: 0.9385
Vehiclevin F1: 0.9766
Vehiclevrm F1: 0.9199
Zipcode F1: 0.8565

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: 2
eval_batch_size: 2
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
0.2518	1.0	17398	0.2143	0.6947	0.7367	0.7151	0.9323	0.9707	0.9222	0.7076	0.5415	0.6505	0.7706	0.6596	0.2664	0.7131	0.6703	0.6667	0.8615	0.5074	0.4166	0.2531	0.0170	0.7633	0.7359	0.2656	0.9324	0.9146	0.825	0.6515	0.8004	0.8310	0.7544	0.0	0.7822	0.7785	0.6935	0.9019	0.8237	0.4787	0.5847	0.9429	0.5205	0.1667	0.9970	0.9538	0.8033	0.9576	0.8437	0.5534	0.9126	0.9428	0.96	0.8784	0.3854	0.5525	0.8787	0.9621	0.9099	0.7158	0.7584	0.7146	0.6748
0.1671	2.0	34796	0.1478	0.8137	0.8681	0.8400	0.9533	0.9832	0.9659	0.8195	0.7536	0.7788	0.9311	0.7936	0.6928	0.8637	0.9132	0.7308	0.9630	0.7972	0.4755	0.4894	0.2028	0.8631	0.8271	0.5392	0.9674	0.9876	0.7395	0.8259	0.9225	0.9235	0.9202	0.0	0.8132	0.8014	0.7758	0.9466	0.8900	0.7645	0.7861	0.9744	0.7449	0.9263	0.9955	0.9682	0.9079	0.9793	0.9239	0.7352	0.8539	0.9762	0.9690	0.9488	0.6922	0.6695	0.9484	0.9833	0.9496	0.8646	0.9337	0.9129	0.7705
0.1137	3.0	52194	0.1194	0.8691	0.9014	0.8849	0.9592	0.9924	0.9836	0.8851	0.8444	0.8802	0.7832	0.8296	0.8442	0.9428	0.9556	0.9079	0.9719	0.8341	0.5643	0.6472	0.4229	0.9137	0.8459	0.5960	0.9799	0.9834	0.8969	0.8974	0.9660	0.9592	0.96	0.0046	0.8214	0.7859	0.8490	0.9738	0.9132	0.8641	0.6235	0.9507	0.7521	0.9442	0.9970	0.9806	0.9346	0.9944	0.9670	0.8369	0.9318	0.9913	0.9690	0.9787	0.9154	0.8266	0.9460	0.9889	0.9812	0.9120	0.9570	0.9387	0.8042
0.079	4.0	69592	0.1063	0.9013	0.9238	0.9124	0.9651	0.9932	0.9939	0.9002	0.8985	0.8820	0.9592	0.8566	0.8694	0.9675	0.9727	0.9067	0.9775	0.8987	0.7436	0.7229	0.2329	0.9477	0.8368	0.6093	0.992	0.9931	0.9465	0.9244	0.9758	0.9781	0.9862	0.0575	0.8350	0.8063	0.8548	0.9789	0.9298	0.9075	0.8739	0.9849	0.8504	0.9595	0.9955	0.9723	0.9469	0.9944	0.9828	0.8348	0.9362	0.9902	0.9722	0.9772	0.9462	0.8983	0.9665	0.9944	0.9859	0.9385	0.9766	0.9199	0.8565
0.0762	5.0	86990	0.1087	0.9009	0.9260	0.9133	0.9657	0.9932	0.9914	0.9061	0.9137	0.9049	0.9553	0.8787	0.8822	0.9716	0.9699	0.9267	0.9812	0.8821	0.7145	0.7319	0.2778	0.9553	0.8484	0.6517	0.9908	0.9903	0.9524	0.9288	0.9748	0.9718	0.9925	0.13	0.8044	0.7502	0.8678	0.9859	0.9428	0.9176	0.8837	0.9602	0.8415	0.9595	0.9970	0.9806	0.9624	0.9903	0.9775	0.8788	0.9344	0.9913	0.9721	0.9898	0.9441	0.8973	0.9698	0.9937	0.9988	0.9371	0.9825	0.9604	0.8811

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: xlm-roberta
License: mit
Created: Mar 10, 2024
Updated: Mar 12, 2024