ai4privacy_v2_adapter_it

This model is a fine-tuned version of distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0807
Overall Precision: 0.8556
Overall Recall: 0.8901
Overall F1: 0.8725
Overall Accuracy: 0.9669
Accountname F1: 0.9869
Accountnumber F1: 0.9762
Age F1: 0.9719
Amount F1: 0.7971
Bic F1: 0.9536
Bitcoinaddress F1: 0.9092
Buildingnumber F1: 0.8371
City F1: 0.8562
Companyname F1: 0.9699
County F1: 0.8920
Creditcardcvv F1: 0.8794
Creditcardissuer F1: 0.9681
Creditcardnumber F1: 0.8276
Currency F1: 0.5914
Currencycode F1: 0.6059
Currencyname F1: 0.0
Currencysymbol F1: 0.8541
Date F1: 0.6932
Dob F1: 0.4620
Email F1: 0.9911
Ethereumaddress F1: 0.9856
Eyecolor F1: 0.9257
Firstname F1: 0.8746
Gender F1: 0.9656
Height F1: 0.9689
Iban F1: 0.9936
Ip F1: 0.0
Ipv4 F1: 0.8059
Ipv6 F1: 0.7656
Jobarea F1: 0.9611
Jobtitle F1: 0.9633
Jobtype F1: 0.9625
Lastname F1: 0.8054
Litecoinaddress F1: 0.7454
Mac F1: 0.9646
Maskednumber F1: 0.7425
Middlename F1: 0.4467
Nearbygpscoordinate F1: 0.9989
Ordinaldirection F1: 0.9868
Password F1: 0.9839
Phoneimei F1: 0.9878
Phonenumber F1: 0.9787
Pin F1: 0.6881
Prefix F1: 0.9727
Secondaryaddress F1: 0.9697
Sex F1: 0.9858
Ssn F1: 0.9778
State F1: 0.8914
Street F1: 0.8813
Time F1: 0.9567
Url F1: 0.9915
Useragent F1: 0.9769
Username F1: 0.9686
Vehiclevin F1: 0.9635
Vehiclevrm F1: 0.9747
Zipcode F1: 0.8485

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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.2
num_epochs: 6

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	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
0.7047	1.0	1275	0.3394	0.3552	0.4679	0.4038	0.8991	0.7758	0.6518	0.8829	0.1009	0.3687	0.7553	0.3720	0.0	0.1118	0.0698	0.0	0.0	0.5544	0.0	0.0	0.2279	0.3929	0.0953	0.9181	0.8440	0.0	0.3652	0.1346	0.1034	0.8137	0.0	0.7184	0.6402	0.0143	0.5859	0.0	0.0661	0.0	0.7596	0.0112	0.0	0.9590	0.0	0.7307	0.9290	0.4443	0.0	0.0132	0.5173	0.6060	0.1941	0.0113	0.1307	0.7603	0.9491	0.8830	0.0048	0.4413	0.1774	0.3969
0.16	2.0	2550	0.1239	0.7404	0.8016	0.7698	0.9550	0.9820	0.9461	0.9464	0.4123	0.6098	0.8438	0.7318	0.5930	0.9095	0.6646	0.7774	0.9154	0.6495	0.4255	0.3522	0.6151	0.5260	0.1902	0.9729	0.9601	0.6775	0.8040	0.7830	0.8411	0.9417	0.0	0.8056	0.7966	0.8342	0.9225	0.7701	0.6583	0.5681	0.9002	0.6007	0.0633	0.9935	0.9803	0.9649	0.9900	0.9462	0.0103	0.9599	0.9538	0.9509	0.9607	0.7129	0.7718	0.9339	0.9847	0.9481	0.8711	0.9539	0.8225	0.6985
0.1169	3.0	3825	0.1027	0.7616	0.8481	0.8025	0.9573	0.9836	0.9518	0.9628	0.5499	0.9358	0.9409	0.7946	0.7442	0.9514	0.8136	0.8579	0.9422	0.7882	0.5091	0.5460	0.6629	0.7015	0.3203	0.9834	0.9885	0.8499	0.8486	0.9179	0.9423	0.9465	0.0086	0.8009	0.3113	0.9312	0.9444	0.9125	0.7483	0.7813	0.9513	0.6076	0.3184	0.9957	0.9837	0.9646	0.9911	0.9541	0.3744	0.9662	0.9657	0.9781	0.9667	0.7927	0.8152	0.9317	0.9890	0.9595	0.9338	0.9545	0.9578	0.7431
0.0928	4.0	5100	0.0893	0.8261	0.8714	0.8482	0.9647	0.9861	0.9574	0.9691	0.6684	0.9497	0.9340	0.8159	0.8093	0.9498	0.8534	0.87	0.9569	0.7950	0.5274	0.5591	0.7556	0.5915	0.4577	0.9893	0.9828	0.8894	0.8577	0.9431	0.9630	0.9801	0.0	0.8068	0.8130	0.9414	0.9530	0.9425	0.7637	0.8190	0.9515	0.6809	0.4021	0.9989	0.9868	0.9747	0.9878	0.9736	0.6169	0.9639	0.9649	0.9851	0.9778	0.8287	0.8536	0.9459	0.9890	0.9567	0.9385	0.9408	0.9531	0.8158
0.0827	5.0	6375	0.0821	0.8531	0.8845	0.8685	0.9666	0.9885	0.9687	0.9712	0.7602	0.9500	0.9053	0.8303	0.8370	0.9699	0.8782	0.8691	0.9709	0.8098	0.5908	0.6369	0.8270	0.6587	0.4759	0.9881	0.9871	0.9303	0.8716	0.9633	0.9727	0.9810	0.0	0.8149	0.8104	0.9588	0.9655	0.9573	0.8000	0.7339	0.9690	0.7423	0.4433	0.9989	0.9868	0.9831	0.9944	0.9787	0.6794	0.9735	0.9681	0.9858	0.9787	0.8805	0.8731	0.9544	0.9907	0.9740	0.9616	0.9536	0.9650	0.8385
0.077	6.0	7650	0.0807	0.8556	0.8901	0.8725	0.9669	0.9869	0.9762	0.9719	0.7971	0.9536	0.9092	0.8371	0.8562	0.9699	0.8920	0.8794	0.9681	0.8276	0.5914	0.6059	0.8541	0.6932	0.4620	0.9911	0.9856	0.9257	0.8746	0.9656	0.9689	0.9936	0.0	0.8059	0.7656	0.9611	0.9633	0.9625	0.8054	0.7454	0.9646	0.7425	0.4467	0.9989	0.9868	0.9839	0.9878	0.9787	0.6881	0.9727	0.9697	0.9858	0.9778	0.8914	0.8813	0.9567	0.9915	0.9769	0.9686	0.9635	0.9747	0.8485

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.1

Isotonic/ai4privacy_v2_adapter_it

ai4privacy_v2_adapter_it

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

为此模型做种