|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: deberta-v3-base_finetuned_ai4privacy_v2 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# 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: 0.0424 |
|
- Overall Precision: 0.9550 |
|
- Overall Recall: 0.9680 |
|
- Overall F1: 0.9614 |
|
- Overall Accuracy: 0.9818 |
|
- Accountname F1: 0.9965 |
|
- Accountnumber F1: 1.0 |
|
- Age F1: 0.9676 |
|
- Amount F1: 0.9897 |
|
- Bic F1: 0.9868 |
|
- Bitcoinaddress F1: 0.9926 |
|
- Buildingnumber F1: 0.9818 |
|
- City F1: 0.9968 |
|
- Companyname F1: 0.9979 |
|
- County F1: 1.0 |
|
- Creditcardcvv F1: 1.0 |
|
- Creditcardissuer F1: 0.9964 |
|
- Creditcardnumber F1: 0.9631 |
|
- Currency F1: 0.8896 |
|
- Currencycode F1: 0.9949 |
|
- Currencyname F1: 0.7481 |
|
- Currencysymbol F1: 0.9984 |
|
- Date F1: 0.9609 |
|
- Dob F1: 0.9160 |
|
- Email F1: 1.0 |
|
- Ethereumaddress F1: 1.0 |
|
- Eyecolor F1: 0.9608 |
|
- Firstname F1: 0.9908 |
|
- Gender F1: 0.9988 |
|
- Height F1: 0.9925 |
|
- Iban F1: 0.9974 |
|
- Ip F1: 0.2177 |
|
- Ipv4 F1: 0.8145 |
|
- Ipv6 F1: 0.7835 |
|
- Jobarea F1: 0.9831 |
|
- Jobtitle F1: 0.9992 |
|
- Jobtype F1: 0.9899 |
|
- Lastname F1: 0.9643 |
|
- Litecoinaddress F1: 0.9815 |
|
- Mac F1: 1.0 |
|
- Maskednumber F1: 0.9590 |
|
- Middlename F1: 0.4375 |
|
- Nearbygpscoordinate F1: 1.0 |
|
- Ordinaldirection F1: 0.4 |
|
- Password F1: 0.9960 |
|
- Phoneimei F1: 0.9961 |
|
- Phonenumber F1: 0.9978 |
|
- Pin F1: 0.9814 |
|
- Prefix F1: 0.9807 |
|
- Secondaryaddress F1: 0.9989 |
|
- Sex F1: 0.9783 |
|
- Ssn F1: 0.9950 |
|
- State F1: 0.9923 |
|
- Street F1: 0.9968 |
|
- Time F1: 0.9862 |
|
- Url F1: 1.0 |
|
- Useragent F1: 0.9975 |
|
- Username F1: 1.0 |
|
- Vehiclevin F1: 1.0 |
|
- Vehiclevrm F1: 0.9929 |
|
- Zipcode F1: 0.9943 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|:--------------:|:----------------:|:------:|:---------:|:------:|:-----------------:|:-----------------:|:-------:|:--------------:|:---------:|:----------------:|:-------------------:|:-------------------:|:-----------:|:---------------:|:---------------:|:-----------------:|:-------:|:------:|:--------:|:------------------:|:-----------:|:------------:|:---------:|:---------:|:-------:|:------:|:-------:|:-------:|:----------:|:-----------:|:----------:|:-----------:|:------------------:|:------:|:---------------:|:-------------:|:----------------------:|:-------------------:|:-----------:|:------------:|:--------------:|:------:|:---------:|:-------------------:|:------:|:------:|:--------:|:---------:|:-------:|:------:|:------------:|:-----------:|:-------------:|:-------------:|:----------:| |
|
| 0.2542 | 1.0 | 1070 | 0.1744 | 0.7933 | 0.8151 | 0.8040 | 0.9469 | 0.9734 | 0.9011 | 0.8465 | 0.8807 | 0.5502 | 0.7683 | 0.8006 | 0.6202 | 0.8908 | 0.8431 | 0.0 | 0.8100 | 0.6975 | 0.5052 | 0.0 | 0.0 | 0.7156 | 0.8292 | 0.3902 | 0.9907 | 0.9810 | 0.4808 | 0.8015 | 0.8076 | 0.9744 | 0.9529 | 0.0 | 0.8335 | 0.7879 | 0.0 | 0.9365 | 0.0 | 0.0 | 0.0 | 0.9355 | 0.0890 | 0.0 | 1.0 | 0.0 | 0.9670 | 0.9882 | 0.9706 | 0.7341 | 0.8914 | 0.9112 | 0.0851 | 0.9072 | 0.6932 | 0.7065 | 0.9543 | 0.9939 | 0.9667 | 0.8542 | 0.9642 | 0.0184 | 0.7480 | |
|
| 0.1494 | 2.0 | 2140 | 0.1213 | 0.8470 | 0.8747 | 0.8606 | 0.9590 | 0.9832 | 0.8908 | 0.9126 | 0.5531 | 0.9419 | 0.7910 | 0.7723 | 0.8919 | 0.9175 | 0.9560 | 0.0 | 0.9858 | 0.8649 | 0.6121 | 0.8738 | 0.0 | 0.9287 | 0.8676 | 0.5886 | 0.9882 | 0.9873 | 0.8319 | 0.9381 | 0.8815 | 0.9744 | 0.9580 | 0.0 | 0.8388 | 0.8040 | 0.0 | 0.9355 | 0.6122 | 0.5918 | 0.1882 | 0.9908 | 0.7311 | 0.0 | 0.9967 | 0.0 | 0.9440 | 0.9738 | 0.9257 | 0.7566 | 0.9015 | 0.9467 | 0.8776 | 0.9010 | 0.6753 | 0.9297 | 0.9021 | 0.9836 | 0.9637 | 0.9585 | 0.9451 | 0.9417 | 0.6969 | |
|
| 0.1008 | 3.0 | 3210 | 0.0728 | 0.9038 | 0.9222 | 0.9129 | 0.9708 | 0.9773 | 0.9091 | 0.9144 | 0.8619 | 0.9610 | 0.9546 | 0.9023 | 0.9711 | 0.9906 | 0.8943 | 0.3889 | 0.9680 | 0.8853 | 0.7540 | 0.9239 | 0.0633 | 0.9665 | 0.8906 | 0.6993 | 0.9987 | 0.9905 | 0.9804 | 0.9640 | 0.9763 | 0.7631 | 0.9724 | 0.0 | 0.8374 | 0.8081 | 0.6087 | 0.9882 | 0.8649 | 0.5698 | 0.8708 | 0.9931 | 0.8410 | 0.0 | 1.0 | 0.0 | 0.9858 | 0.9921 | 0.9903 | 0.8889 | 0.9173 | 0.9897 | 0.9263 | 0.9042 | 0.8811 | 0.9503 | 0.9836 | 0.9965 | 0.9692 | 0.9847 | 0.9584 | 0.9763 | 0.9171 | |
|
| 0.0793 | 4.0 | 4280 | 0.0675 | 0.9356 | 0.9446 | 0.9401 | 0.9742 | 0.9894 | 0.9810 | 0.9608 | 0.9825 | 0.9539 | 0.9633 | 0.9435 | 0.9881 | 0.9793 | 0.9894 | 0.8462 | 0.9893 | 0.9303 | 0.8391 | 0.9694 | 0.4124 | 0.9922 | 0.8978 | 0.7260 | 0.9975 | 0.9968 | 0.9804 | 0.9757 | 0.9834 | 0.9925 | 0.9949 | 0.0 | 0.8325 | 0.8106 | 0.8333 | 0.9899 | 0.9495 | 0.7368 | 0.9086 | 1.0 | 0.9003 | 0.0 | 1.0 | 0.0 | 0.9919 | 0.9934 | 0.9913 | 0.9556 | 0.9338 | 0.9943 | 0.9474 | 0.9888 | 0.9788 | 0.9915 | 0.9699 | 0.9948 | 0.9778 | 0.9898 | 0.9752 | 0.9835 | 0.9559 | |
|
| 0.0656 | 5.0 | 5350 | 0.0469 | 0.9524 | 0.9588 | 0.9556 | 0.9780 | 0.9965 | 0.9965 | 0.9626 | 0.9866 | 0.9770 | 0.9789 | 0.9657 | 0.9935 | 0.9958 | 0.9970 | 0.9655 | 0.9964 | 0.9432 | 0.8342 | 0.9744 | 0.6977 | 0.9938 | 0.9382 | 0.8596 | 1.0 | 1.0 | 0.9608 | 0.9822 | 0.9941 | 0.9925 | 0.9949 | 0.1360 | 0.8390 | 0.8003 | 0.9333 | 0.9992 | 0.98 | 0.9157 | 0.9570 | 1.0 | 0.9361 | 0.0 | 1.0 | 0.4 | 0.9828 | 0.9921 | 0.9978 | 0.9814 | 0.9652 | 0.9989 | 0.9574 | 0.9938 | 0.9923 | 0.9957 | 0.9766 | 0.9991 | 0.9975 | 0.9983 | 0.9944 | 0.9976 | 0.9765 | |
|
| 0.057 | 6.0 | 6420 | 0.0448 | 0.9595 | 0.9662 | 0.9628 | 0.9803 | 0.9965 | 1.0 | 0.9582 | 0.9897 | 0.9836 | 0.9851 | 0.9833 | 0.9978 | 0.9979 | 0.9985 | 1.0 | 0.9964 | 0.9581 | 0.8956 | 0.9949 | 0.7294 | 0.9984 | 0.9524 | 0.8848 | 1.0 | 1.0 | 0.9608 | 0.9886 | 0.9988 | 0.9925 | 0.9974 | 0.1663 | 0.8377 | 0.8195 | 0.9123 | 0.9992 | 0.9608 | 0.9556 | 0.9563 | 1.0 | 0.9527 | 0.2857 | 1.0 | 0.4 | 0.9960 | 0.9961 | 0.9978 | 0.9852 | 0.9798 | 0.9989 | 0.9783 | 0.9975 | 0.9942 | 0.9979 | 0.9807 | 1.0 | 0.9975 | 1.0 | 0.9808 | 0.9929 | 0.9932 | |
|
| 0.0455 | 7.0 | 7490 | 0.0424 | 0.9550 | 0.9680 | 0.9614 | 0.9818 | 0.9965 | 1.0 | 0.9676 | 0.9897 | 0.9868 | 0.9926 | 0.9818 | 0.9968 | 0.9979 | 1.0 | 1.0 | 0.9964 | 0.9631 | 0.8896 | 0.9949 | 0.7481 | 0.9984 | 0.9609 | 0.9160 | 1.0 | 1.0 | 0.9608 | 0.9908 | 0.9988 | 0.9925 | 0.9974 | 0.2177 | 0.8145 | 0.7835 | 0.9831 | 0.9992 | 0.9899 | 0.9643 | 0.9815 | 1.0 | 0.9590 | 0.4375 | 1.0 | 0.4 | 0.9960 | 0.9961 | 0.9978 | 0.9814 | 0.9807 | 0.9989 | 0.9783 | 0.9950 | 0.9923 | 0.9968 | 0.9862 | 1.0 | 0.9975 | 1.0 | 1.0 | 0.9929 | 0.9943 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
