Isotonic commited on
Commit
3fe84a2
1 Parent(s): f22f901

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -69
README.md CHANGED
@@ -6,6 +6,17 @@ tags:
6
  model-index:
7
  - name: distilbert-base-german-cased_finetuned_ai4privacy_v2
8
  results: []
 
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,81 +24,13 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # distilbert-base-german-cased_finetuned_ai4privacy_v2
15
 
16
- This model is a fine-tuned version of [distilbert-base-german-cased](https://huggingface.co/distilbert-base-german-cased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
  - Loss: 0.0821
19
  - Overall Precision: 0.9086
20
  - Overall Recall: 0.9379
21
  - Overall F1: 0.9230
22
  - Overall Accuracy: 0.9679
23
- - Accountname F1: 0.9985
24
- - Accountnumber F1: 0.9849
25
- - Age F1: 0.9792
26
- - Amount F1: 0.9387
27
- - Bic F1: 0.9641
28
- - Bitcoinaddress F1: 0.9637
29
- - Buildingnumber F1: 0.9011
30
- - City F1: 0.9260
31
- - Companyname F1: 0.9782
32
- - County F1: 0.9778
33
- - Creditcardcvv F1: 0.9543
34
- - Creditcardissuer F1: 1.0
35
- - Creditcardnumber F1: 0.8796
36
- - Currency F1: 0.7027
37
- - Currencycode F1: 0.8328
38
- - Currencyname F1: 0.3466
39
- - Currencysymbol F1: 0.9420
40
- - Date F1: 0.8156
41
- - Dob F1: 0.6575
42
- - Email F1: 0.9971
43
- - Ethereumaddress F1: 0.9947
44
- - Eyecolor F1: 0.9833
45
- - Firstname F1: 0.9614
46
- - Gender F1: 0.9881
47
- - Height F1: 0.9842
48
- - Iban F1: 0.9819
49
- - Ip F1: 0.2023
50
- - Ipv4 F1: 0.6631
51
- - Ipv6 F1: 0.7243
52
- - Jobarea F1: 0.9722
53
- - Jobtitle F1: 0.9904
54
- - Jobtype F1: 0.9725
55
- - Lastname F1: 0.9185
56
- - Litecoinaddress F1: 0.8545
57
- - Mac F1: 0.9780
58
- - Maskednumber F1: 0.8365
59
- - Middlename F1: 0.9156
60
- - Nearbygpscoordinate F1: 1.0
61
- - Ordinaldirection F1: 0.9853
62
- - Password F1: 0.9782
63
- - Phoneimei F1: 0.9947
64
- - Phonenumber F1: 0.9883
65
- - Pin F1: 0.9189
66
- - Prefix F1: 0.9594
67
- - Secondaryaddress F1: 0.9831
68
- - Sex F1: 0.9993
69
- - Ssn F1: 0.9898
70
- - State F1: 0.9739
71
- - Street F1: 0.9355
72
- - Time F1: 0.9764
73
- - Url F1: 0.9984
74
- - Useragent F1: 0.9885
75
- - Username F1: 0.9798
76
- - Vehiclevin F1: 0.9614
77
- - Vehiclevrm F1: 1.0
78
- - Zipcode F1: 0.9100
79
-
80
- ## Model description
81
-
82
- More information needed
83
-
84
- ## Intended uses & limitations
85
-
86
- More information needed
87
-
88
- ## Training and evaluation data
89
-
90
- More information needed
91
 
92
  ## Training procedure
93
 
 
6
  model-index:
7
  - name: distilbert-base-german-cased_finetuned_ai4privacy_v2
8
  results: []
9
+ datasets:
10
+ - ai4privacy/pii-masking-200k
11
+ - Isotonic/pii-masking-200k
12
+ language:
13
+ - de
14
+ metrics:
15
+ - accuracy
16
+ - f1
17
+ - precision
18
+ - recall
19
+ pipeline_tag: token-classification
20
  ---
21
 
22
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
24
 
25
  # distilbert-base-german-cased_finetuned_ai4privacy_v2
26
 
27
+ This model is a fine-tuned version of [distilbert-base-german-cased](https://huggingface.co/distilbert-base-german-cased) on the German subset of [pii-masking-200k](https://huggingface.co/ai4privacy/pii-masking-200k) dataset.
28
  It achieves the following results on the evaluation set:
29
  - Loss: 0.0821
30
  - Overall Precision: 0.9086
31
  - Overall Recall: 0.9379
32
  - Overall F1: 0.9230
33
  - Overall Accuracy: 0.9679
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
 
35
  ## Training procedure
36