--- license: mit base_model: microsoft/deberta-v3-base tags: - generated_from_trainer model-index: - name: deberta-v3-base_finetuned_ai4privacy_v2 results: [] --- # deberta-v3-base_finetuned_ai4privacy_v2 This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0101 - Overall Precision: 0.9818 - Overall Recall: 0.9871 - Overall F1: 0.9844 - Overall Accuracy: 0.9965 - Accountname F1: 1.0 - Accountnumber F1: 1.0 - Age F1: 0.9951 - Amount F1: 1.0 - Bic F1: 1.0 - Bitcoinaddress F1: 0.9915 - Buildingnumber F1: 0.9969 - City F1: 1.0 - Companyname F1: 1.0 - County F1: 0.9985 - Creditcardcvv F1: 0.9831 - Creditcardissuer F1: 0.9964 - Creditcardnumber F1: 0.9889 - Currency F1: 0.9678 - Currencycode F1: 0.9949 - Currencyname F1: 0.9266 - Currencysymbol F1: 0.9984 - Date F1: 0.9895 - Dob F1: 0.9774 - Email F1: 0.9776 - Ethereumaddress F1: 1.0 - Eyecolor F1: 1.0 - Firstname F1: 1.0 - Gender F1: 0.9976 - Height F1: 1.0 - Iban F1: 1.0 - Ip F1: 0.7367 - Ipv4 F1: 0.8360 - Ipv6 F1: 0.9797 - Jobarea F1: 0.9667 - Jobtitle F1: 1.0 - Jobtype F1: 1.0 - Lastname F1: 1.0 - Litecoinaddress F1: 0.9688 - Mac F1: 1.0 - Maskednumber F1: 0.9887 - Middlename F1: 0.9583 - Nearbygpscoordinate F1: 1.0 - Ordinaldirection F1: 0.8571 - Password F1: 0.9949 - Phoneimei F1: 0.9961 - Phonenumber F1: 0.9838 - Pin F1: 0.9963 - Prefix F1: 0.9949 - Secondaryaddress F1: 1.0 - Sex F1: 1.0 - Ssn F1: 0.9938 - State F1: 1.0 - Street F1: 0.9989 - Time F1: 0.9958 - Url F1: 1.0 - Useragent F1: 1.0 - Username F1: 1.0 - Vehiclevin F1: 1.0 - Vehiclevrm F1: 0.9929 - Zipcode F1: 0.9966 ## 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: 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: 7 ### 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 | |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|:--------------:|:----------------:|:------:|:---------:|:------:|:-----------------:|:-----------------:|:-------:|:--------------:|:---------:|:----------------:|:-------------------:|:-------------------:|:-----------:|:---------------:|:---------------:|:-----------------:|:-------:|:------:|:--------:|:------------------:|:-----------:|:------------:|:---------:|:---------:|:-------:|:------:|:-------:|:-------:|:----------:|:-----------:|:----------:|:-----------:|:------------------:|:------:|:---------------:|:-------------:|:----------------------:|:-------------------:|:-----------:|:------------:|:--------------:|:------:|:---------:|:-------------------:|:------:|:------:|:--------:|:---------:|:-------:|:------:|:------------:|:-----------:|:-------------:|:-------------:|:----------:| | 0.0484 | 1.0 | 535 | 0.1039 | 0.9213 | 0.9437 | 0.9324 | 0.9686 | 0.9973 | 1.0 | 0.9642 | 0.9918 | 0.9868 | 0.9543 | 0.9752 | 0.9978 | 0.9948 | 0.9955 | 0.9667 | 0.9964 | 0.9317 | 0.8788 | 0.9949 | 0.7526 | 0.9969 | 0.8814 | 0.6186 | 0.9987 | 0.9196 | 0.9804 | 0.9882 | 0.9988 | 1.0 | 0.9949 | 0.0922 | 0.8337 | 0.5216 | 0.9492 | 0.9983 | 0.98 | 0.9471 | 0.9351 | 0.5688 | 0.9115 | 0.1538 | 1.0 | 0.4 | 0.9732 | 0.9947 | 0.9967 | 0.9704 | 0.9806 | 0.9966 | 0.9783 | 0.9926 | 0.9715 | 0.9989 | 0.9890 | 0.9983 | 1.0 | 0.9966 | 0.9944 | 0.9976 | 0.9854 | | 0.0607 | 2.0 | 1070 | 0.0445 | 0.9510 | 0.9612 | 0.9560 | 0.9797 | 0.9938 | 0.9860 | 0.9723 | 0.9887 | 0.9733 | 0.9779 | 0.9813 | 0.9946 | 0.9906 | 0.9985 | 0.9474 | 0.9929 | 0.9331 | 0.8508 | 0.9898 | 0.7176 | 0.9969 | 0.9530 | 0.9028 | 0.9969 | 1.0 | 0.9804 | 0.9847 | 0.9918 | 0.9779 | 0.9758 | 0.2269 | 0.8362 | 0.7929 | 0.8667 | 0.9941 | 0.9245 | 0.9710 | 0.9491 | 0.9954 | 0.9351 | 0.2222 | 1.0 | 0.0 | 0.9919 | 0.9961 | 0.9892 | 0.9779 | 0.9669 | 0.9989 | 0.9670 | 0.9840 | 0.9923 | 0.9979 | 0.9834 | 0.9974 | 0.9975 | 0.9923 | 0.9808 | 0.9837 | 0.9776 | | 0.0585 | 3.0 | 1605 | 0.0391 | 0.9584 | 0.9652 | 0.9618 | 0.9834 | 1.0 | 0.9895 | 0.9706 | 0.9969 | 0.9868 | 0.9894 | 0.9788 | 0.9935 | 0.9990 | 0.9985 | 0.9825 | 0.9964 | 0.9639 | 0.8127 | 0.9897 | 0.7173 | 0.9953 | 0.9519 | 0.875 | 0.9981 | 1.0 | 1.0 | 0.9912 | 0.9988 | 0.9925 | 0.9923 | 0.3031 | 0.8371 | 0.8252 | 0.9836 | 0.9831 | 1.0 | 0.9581 | 0.9608 | 0.9954 | 0.9645 | 0.7805 | 1.0 | 0.8571 | 0.9850 | 0.9961 | 0.9967 | 0.9926 | 0.9790 | 0.9989 | 0.9890 | 0.9829 | 0.9904 | 0.9968 | 0.9903 | 1.0 | 1.0 | 0.9974 | 0.9833 | 0.9953 | 0.9818 | | 0.0449 | 4.0 | 2140 | 0.0396 | 0.9668 | 0.9747 | 0.9707 | 0.9866 | 1.0 | 0.9956 | 0.9821 | 0.9928 | 0.9868 | 0.9936 | 0.9891 | 0.9989 | 0.9958 | 1.0 | 0.9655 | 0.9893 | 0.9721 | 0.9329 | 0.9949 | 0.8498 | 1.0 | 0.9763 | 0.9611 | 0.9839 | 1.0 | 0.9903 | 0.9965 | 0.9988 | 0.9925 | 0.9949 | 0.5304 | 0.8240 | 0.8382 | 0.9508 | 0.9949 | 1.0 | 0.9753 | 0.8916 | 0.9954 | 0.9666 | 0.8889 | 0.9984 | 0.75 | 1.0 | 0.9948 | 0.9967 | 0.9888 | 0.9840 | 0.9989 | 1.0 | 0.9914 | 0.9923 | 0.9989 | 0.9889 | 1.0 | 1.0 | 0.9983 | 1.0 | 0.9929 | 0.9910 | | 0.0405 | 5.0 | 2675 | 0.0204 | 0.9756 | 0.9807 | 0.9782 | 0.9912 | 1.0 | 1.0 | 0.9755 | 1.0 | 0.9934 | 0.9925 | 0.9969 | 0.9978 | 1.0 | 0.9985 | 0.9831 | 1.0 | 0.9839 | 0.9449 | 0.9897 | 0.8794 | 1.0 | 0.9884 | 0.9762 | 0.9863 | 1.0 | 1.0 | 0.9982 | 0.9976 | 0.9813 | 0.9949 | 0.5933 | 0.8519 | 0.8759 | 0.9667 | 0.9882 | 1.0 | 0.9867 | 0.9791 | 1.0 | 0.9822 | 0.8636 | 1.0 | 0.5714 | 1.0 | 0.9974 | 1.0 | 1.0 | 0.9949 | 1.0 | 1.0 | 0.9975 | 0.9981 | 0.9979 | 0.9930 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.9966 | | 0.026 | 6.0 | 3210 | 0.0116 | 0.9819 | 0.9863 | 0.9841 | 0.9960 | 1.0 | 1.0 | 0.9951 | 1.0 | 1.0 | 0.9883 | 1.0 | 1.0 | 1.0 | 0.9985 | 0.9831 | 1.0 | 0.9828 | 0.9663 | 0.9949 | 0.9225 | 0.9984 | 0.9872 | 0.9749 | 0.9800 | 1.0 | 1.0 | 1.0 | 0.9976 | 1.0 | 1.0 | 0.7247 | 0.8389 | 0.9779 | 0.9667 | 0.9958 | 1.0 | 0.9956 | 0.9688 | 1.0 | 0.9850 | 0.9583 | 1.0 | 0.8571 | 0.9949 | 0.9961 | 0.9967 | 0.9963 | 0.9940 | 1.0 | 1.0 | 0.9975 | 0.9981 | 0.9989 | 0.9958 | 1.0 | 1.0 | 1.0 | 1.0 | 0.9929 | 0.9977 | | 0.0175 | 7.0 | 3745 | 0.0101 | 0.9818 | 0.9871 | 0.9844 | 0.9965 | 1.0 | 1.0 | 0.9951 | 1.0 | 1.0 | 0.9915 | 0.9969 | 1.0 | 1.0 | 0.9985 | 0.9831 | 0.9964 | 0.9889 | 0.9678 | 0.9949 | 0.9266 | 0.9984 | 0.9895 | 0.9774 | 0.9776 | 1.0 | 1.0 | 1.0 | 0.9976 | 1.0 | 1.0 | 0.7367 | 0.8360 | 0.9797 | 0.9667 | 1.0 | 1.0 | 1.0 | 0.9688 | 1.0 | 0.9887 | 0.9583 | 1.0 | 0.8571 | 0.9949 | 0.9961 | 0.9838 | 0.9963 | 0.9949 | 1.0 | 1.0 | 0.9938 | 1.0 | 0.9989 | 0.9958 | 1.0 | 1.0 | 1.0 | 1.0 | 0.9929 | 0.9966 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0