Update README.md

README.md

@@ -26,7 +26,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the english only section of ai4privacy/pii-masking-65k dataset.
 
-Latest Model: [electra_large_finetuned_ai4privacy_50k](https://huggingface.co/Isotonic/electra_large_finetuned_ai4privacy_50k)
+Latest Model: [Isotonic/mdeberta-v3-base_finetuned_ai4privacy_v2](https://huggingface.co/Isotonic/mdeberta-v3-base_finetuned_ai4privacy_v2)
 
 ## Useage
 GitHub Implementation: [Ai4Privacy](https://github.com/Sripaad/ai4privacy)
@@ -57,70 +57,12 @@ The following hyperparameters were used during training:
 
 ## Class wise metrics
 It achieves the following results on the evaluation set:
+
 - Loss: 0.0106
 - Overall Precision: 0.9760
 - Overall Recall: 0.9801
 - Overall F1: 0.9780
 - Overall Accuracy: 0.9977
-- Accountname F1: 1.0
-- Accountnumber F1: 1.0
-- Amount F1: 0.9565
-- Bic F1: 1.0
-- Bitcoinaddress F1: 1.0
-- Buildingnumber F1: 0.9753
-- City F1: 0.9987
-- Company Name F1: 1.0
-- County F1: 1.0
-- Creditcardcvv F1: 0.9701
-- Creditcardissuer F1: 0.9939
-- Creditcardnumber F1: 1.0
-- Currency F1: 0.8668
-- Currencycode F1: 0.8662
-- Currencyname F1: 0.7582
-- Currencysymbol F1: 0.36
-- Date F1: 0.9944
-- Displayname F1: 0.5970
-- Email F1: 1.0
-- Ethereumaddress F1: 1.0
-- Firstname F1: 0.9493
-- Fullname F1: 0.9982
-- Gender F1: 0.9524
-- Iban F1: 1.0
-- Ip F1: 0.5543
-- Ipv4 F1: 0.8700
-- Ipv6 F1: 0.8863
-- Jobarea F1: 0.9806
-- Jobdescriptor F1: 0.6875
-- Jobtitle F1: 0.9424
-- Jobtype F1: 0.8811
-- Lastname F1: 0.9052
-- Litecoinaddress F1: 0.9848
-- Mac F1: 1.0
-- Maskednumber F1: 1.0
-- Middlename F1: 0.7364
-- Name F1: 0.9994
-- Nearbygpscoordinate F1: 0.5
-- Number F1: 1.0
-- Password F1: 1.0
-- Phoneimei F1: 1.0
-- Phone Number F1: 1.0
-- Pin F1: 0.9697
-- Prefix F1: 0.9540
-- Secondaryaddress F1: 0.9947
-- Sex F1: 0.9650
-- Sextype F1: 0.0
-- Ssn F1: 1.0
-- State F1: 0.9965
-- Street F1: 0.9810
-- Streetaddress F1: 0.9832
-- Suffix F1: 0.7928
-- Time F1: 0.9880
-- Url F1: 0.9974
-- Useragent F1: 1.0
-- Username F1: 0.9746
-- Vehiclevin F1: 1.0
-- Vehiclevrm F1: 1.0
-- Zipcode F1: 0.9969
 
 ## Training results