Model save
Browse files- README.md +91 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: distilbert-base-uncased
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: PII-Detection-V2.1
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# PII-Detection-V2.1
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0368
|
20 |
+
- Overall Precision: 0.9351
|
21 |
+
- Overall Recall: 0.9512
|
22 |
+
- Overall F1: 0.9431
|
23 |
+
- Overall Accuracy: 0.9916
|
24 |
+
- Accountname F1: 0.9871
|
25 |
+
- Accountnumber F1: 0.9910
|
26 |
+
- Buildingnumber F1: 0.7900
|
27 |
+
- City F1: 0.9636
|
28 |
+
- Companyname F1: 0.9590
|
29 |
+
- County F1: 0.9427
|
30 |
+
- Creditcardcvv F1: 0.8543
|
31 |
+
- Creditcardissuer F1: 0.9043
|
32 |
+
- Creditcardnumber F1: 0.8696
|
33 |
+
- Email F1: 0.9979
|
34 |
+
- Firstname F1: 0.9195
|
35 |
+
- Fullname F1: 0.9831
|
36 |
+
- Iban F1: 0.9658
|
37 |
+
- Lastname F1: 0.8370
|
38 |
+
- Middlename F1: 0.8452
|
39 |
+
- Name F1: 0.9926
|
40 |
+
- Number F1: 0.9157
|
41 |
+
- Phonenumber F1: 0.9792
|
42 |
+
- Pin F1: 0.8959
|
43 |
+
- Secondaryaddress F1: 0.9787
|
44 |
+
- State F1: 0.9286
|
45 |
+
- Street F1: 0.8457
|
46 |
+
- Streetaddress F1: 0.7259
|
47 |
+
- Url F1: 0.9980
|
48 |
+
- Username F1: 0.9509
|
49 |
+
|
50 |
+
## Model description
|
51 |
+
|
52 |
+
More information needed
|
53 |
+
|
54 |
+
## Intended uses & limitations
|
55 |
+
|
56 |
+
More information needed
|
57 |
+
|
58 |
+
## Training and evaluation data
|
59 |
+
|
60 |
+
More information needed
|
61 |
+
|
62 |
+
## Training procedure
|
63 |
+
|
64 |
+
### Training hyperparameters
|
65 |
+
|
66 |
+
The following hyperparameters were used during training:
|
67 |
+
- learning_rate: 5e-05
|
68 |
+
- train_batch_size: 32
|
69 |
+
- eval_batch_size: 32
|
70 |
+
- seed: 42
|
71 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
72 |
+
- lr_scheduler_type: linear
|
73 |
+
- num_epochs: 5
|
74 |
+
|
75 |
+
### Training results
|
76 |
+
|
77 |
+
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Accountname F1 | Accountnumber F1 | Buildingnumber F1 | City F1 | Companyname F1 | County F1 | Creditcardcvv F1 | Creditcardissuer F1 | Creditcardnumber F1 | Email F1 | Firstname F1 | Fullname F1 | Iban F1 | Lastname F1 | Middlename F1 | Name F1 | Number F1 | Phonenumber F1 | Pin F1 | Secondaryaddress F1 | State F1 | Street F1 | Streetaddress F1 | Url F1 | Username F1 |
|
78 |
+
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|:--------------:|:----------------:|:-----------------:|:-------:|:--------------:|:---------:|:----------------:|:-------------------:|:-------------------:|:--------:|:------------:|:-----------:|:-------:|:-----------:|:-------------:|:-------:|:---------:|:--------------:|:------:|:-------------------:|:--------:|:---------:|:----------------:|:------:|:-----------:|
|
79 |
+
| 0.0885 | 1.0 | 1361 | 0.0489 | 0.8436 | 0.8993 | 0.8705 | 0.9846 | 0.9573 | 0.9269 | 0.6452 | 0.9295 | 0.8956 | 0.8195 | 0.7291 | 0.8274 | 0.7974 | 0.9931 | 0.8206 | 0.9634 | 0.9363 | 0.7408 | 0.4829 | 0.9732 | 0.6385 | 0.9037 | 0.7326 | 0.9648 | 0.8559 | 0.6673 | 0.0246 | 0.9901 | 0.9369 |
|
80 |
+
| 0.0338 | 2.0 | 2722 | 0.0345 | 0.9069 | 0.9333 | 0.9199 | 0.9898 | 0.9667 | 0.9713 | 0.7312 | 0.9521 | 0.9363 | 0.9009 | 0.8538 | 0.9093 | 0.8471 | 0.9970 | 0.8864 | 0.9819 | 0.9136 | 0.7901 | 0.7787 | 0.9864 | 0.8854 | 0.9589 | 0.8097 | 0.9732 | 0.9124 | 0.7673 | 0.5046 | 0.9975 | 0.9530 |
|
81 |
+
| 0.0172 | 3.0 | 4083 | 0.0313 | 0.9277 | 0.9439 | 0.9358 | 0.9908 | 0.9889 | 0.9727 | 0.7592 | 0.9611 | 0.9551 | 0.9357 | 0.8656 | 0.9076 | 0.8629 | 0.9982 | 0.9062 | 0.9813 | 0.9710 | 0.8314 | 0.8107 | 0.9913 | 0.9435 | 0.9727 | 0.8847 | 0.9779 | 0.9173 | 0.7895 | 0.6915 | 0.9980 | 0.9521 |
|
82 |
+
| 0.0103 | 4.0 | 5444 | 0.0342 | 0.9330 | 0.9493 | 0.9411 | 0.9913 | 0.9895 | 0.9910 | 0.7939 | 0.9633 | 0.9490 | 0.9365 | 0.8577 | 0.9051 | 0.8660 | 0.9996 | 0.9149 | 0.9833 | 0.9753 | 0.8289 | 0.8430 | 0.9899 | 0.8456 | 0.9588 | 0.8824 | 0.9795 | 0.9299 | 0.8361 | 0.7332 | 0.9980 | 0.9527 |
|
83 |
+
| 0.0058 | 5.0 | 6805 | 0.0368 | 0.9351 | 0.9512 | 0.9431 | 0.9916 | 0.9871 | 0.9910 | 0.7900 | 0.9636 | 0.9590 | 0.9427 | 0.8543 | 0.9043 | 0.8696 | 0.9979 | 0.9195 | 0.9831 | 0.9658 | 0.8370 | 0.8452 | 0.9926 | 0.9157 | 0.9792 | 0.8959 | 0.9787 | 0.9286 | 0.8457 | 0.7259 | 0.9980 | 0.9509 |
|
84 |
+
|
85 |
+
|
86 |
+
### Framework versions
|
87 |
+
|
88 |
+
- Transformers 4.45.2
|
89 |
+
- Pytorch 2.2.0
|
90 |
+
- Datasets 3.0.1
|
91 |
+
- Tokenizers 0.20.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 265620748
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:579012feb0908d3001021e2b156fc8fccc6ac815f146171c2394bf493ec0ae3b
|
3 |
size 265620748
|