Isotonic commited on
Commit
283e33f
1 Parent(s): 2166c61

Model save

Browse files
Files changed (6) hide show
  1. README.md +122 -0
  2. all_results.json +74 -0
  3. eval_results.json +68 -0
  4. model.safetensors +1 -1
  5. train_results.json +9 -0
  6. trainer_state.json +748 -0
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-german-cased
4
+ tags:
5
+ - generated_from_trainer
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
12
+ 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
+
94
+ ### Training hyperparameters
95
+
96
+ The following hyperparameters were used during training:
97
+ - learning_rate: 5e-05
98
+ - train_batch_size: 8
99
+ - eval_batch_size: 8
100
+ - seed: 42
101
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
102
+ - lr_scheduler_type: linear
103
+ - lr_scheduler_warmup_ratio: 0.2
104
+ - num_epochs: 5
105
+
106
+ ### Training results
107
+
108
+ | 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 |
109
+ |:-------------:|:-----:|:-----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|:--------------:|:----------------:|:------:|:---------:|:------:|:-----------------:|:-----------------:|:-------:|:--------------:|:---------:|:----------------:|:-------------------:|:-------------------:|:-----------:|:---------------:|:---------------:|:-----------------:|:-------:|:------:|:--------:|:------------------:|:-----------:|:------------:|:---------:|:---------:|:-------:|:------:|:-------:|:-------:|:----------:|:-----------:|:----------:|:-----------:|:------------------:|:------:|:---------------:|:-------------:|:----------------------:|:-------------------:|:-----------:|:------------:|:--------------:|:------:|:---------:|:-------------------:|:------:|:------:|:--------:|:---------:|:-------:|:------:|:------------:|:-----------:|:-------------:|:-------------:|:----------:|
110
+ | 0.1449 | 1.0 | 5282 | 0.1365 | 0.8213 | 0.8741 | 0.8469 | 0.9504 | 0.9954 | 0.9180 | 0.9509 | 0.7478 | 0.8315 | 0.8265 | 0.7908 | 0.8030 | 0.9011 | 0.9118 | 0.8669 | 0.9831 | 0.8053 | 0.4935 | 0.6482 | 0.0 | 0.8430 | 0.7672 | 0.4751 | 0.9870 | 0.9103 | 0.9501 | 0.8810 | 0.9552 | 0.9507 | 0.9086 | 0.0 | 0.8124 | 0.7776 | 0.8698 | 0.9758 | 0.9445 | 0.8140 | 0.5210 | 0.9819 | 0.6555 | 0.4114 | 1.0 | 0.9837 | 0.8093 | 0.9761 | 0.9254 | 0.7705 | 0.8613 | 0.9676 | 0.9978 | 0.9570 | 0.8585 | 0.8164 | 0.9643 | 0.9879 | 0.9534 | 0.9415 | 0.8778 | 0.9716 | 0.7313 |
111
+ | 0.1039 | 2.0 | 10564 | 0.0841 | 0.8875 | 0.9213 | 0.9041 | 0.9649 | 0.9923 | 0.9598 | 0.9721 | 0.8979 | 0.9240 | 0.9218 | 0.8937 | 0.8803 | 0.9648 | 0.9595 | 0.9563 | 0.9848 | 0.8427 | 0.5724 | 0.7677 | 0.2210 | 0.9244 | 0.8003 | 0.5866 | 0.9932 | 0.9636 | 0.9835 | 0.9473 | 0.9794 | 0.9753 | 0.9644 | 0.0173 | 0.7042 | 0.7564 | 0.9439 | 0.9911 | 0.9710 | 0.8988 | 0.7288 | 0.9801 | 0.7913 | 0.8977 | 0.9978 | 0.9853 | 0.9581 | 0.9937 | 0.9761 | 0.9146 | 0.9166 | 0.9741 | 0.9978 | 0.9787 | 0.9448 | 0.9031 | 0.9591 | 0.9968 | 0.9638 | 0.9719 | 0.9455 | 0.9829 | 0.8863 |
112
+ | 0.0804 | 3.0 | 15846 | 0.0821 | 0.9086 | 0.9379 | 0.9230 | 0.9679 | 0.9985 | 0.9849 | 0.9792 | 0.9387 | 0.9641 | 0.9637 | 0.9011 | 0.9260 | 0.9782 | 0.9778 | 0.9543 | 1.0 | 0.8796 | 0.7027 | 0.8328 | 0.3466 | 0.9420 | 0.8156 | 0.6575 | 0.9971 | 0.9947 | 0.9833 | 0.9614 | 0.9881 | 0.9842 | 0.9819 | 0.2023 | 0.6631 | 0.7243 | 0.9722 | 0.9904 | 0.9725 | 0.9185 | 0.8545 | 0.9780 | 0.8365 | 0.9156 | 1.0 | 0.9853 | 0.9782 | 0.9947 | 0.9883 | 0.9189 | 0.9594 | 0.9831 | 0.9993 | 0.9898 | 0.9739 | 0.9355 | 0.9764 | 0.9984 | 0.9885 | 0.9798 | 0.9614 | 1.0 | 0.9100 |
113
+ | 0.0622 | 4.0 | 21128 | 0.0848 | 0.9095 | 0.9420 | 0.9255 | 0.9713 | 0.9977 | 0.9932 | 0.9815 | 0.9566 | 0.9550 | 0.9704 | 0.9187 | 0.9277 | 0.9735 | 0.9756 | 0.9679 | 0.9966 | 0.8885 | 0.6985 | 0.8598 | 0.4217 | 0.9602 | 0.8262 | 0.6809 | 0.9960 | 0.9947 | 0.9852 | 0.9641 | 0.9952 | 0.9955 | 0.9909 | 0.3053 | 0.7067 | 0.6156 | 0.9784 | 0.9948 | 0.9773 | 0.9176 | 0.8856 | 0.9880 | 0.8598 | 0.9186 | 1.0 | 0.9886 | 0.9871 | 0.9968 | 0.9916 | 0.9419 | 0.9621 | 0.9887 | 1.0 | 0.9926 | 0.9717 | 0.9441 | 0.9835 | 0.9992 | 0.9858 | 0.9838 | 0.9818 | 0.9856 | 0.8972 |
114
+ | 0.032 | 5.0 | 26410 | 0.0998 | 0.9210 | 0.9497 | 0.9351 | 0.9741 | 0.9985 | 0.9962 | 0.9847 | 0.9622 | 0.9614 | 0.9738 | 0.9269 | 0.9431 | 0.9782 | 0.9749 | 0.9708 | 0.9949 | 0.8990 | 0.7116 | 0.8447 | 0.4615 | 0.9646 | 0.8296 | 0.7235 | 0.9966 | 0.9947 | 0.9853 | 0.9672 | 0.9929 | 0.9932 | 0.9919 | 0.3706 | 0.7690 | 0.6836 | 0.9838 | 0.9941 | 0.9789 | 0.9252 | 0.8876 | 0.9960 | 0.8849 | 0.9172 | 1.0 | 0.9886 | 0.9847 | 0.9958 | 0.9925 | 0.9483 | 0.9700 | 0.9912 | 1.0 | 0.9944 | 0.9756 | 0.9468 | 0.99 | 0.9984 | 0.9947 | 0.9806 | 0.9939 | 1.0 | 0.9108 |
115
+
116
+
117
+ ### Framework versions
118
+
119
+ - Transformers 4.35.2
120
+ - Pytorch 2.1.0+cu121
121
+ - Datasets 2.16.1
122
+ - Tokenizers 0.15.0
all_results.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_ACCOUNTNAME_f1": 0.998468606431853,
4
+ "eval_ACCOUNTNUMBER_f1": 0.9848714069591529,
5
+ "eval_AGE_f1": 0.9791505791505791,
6
+ "eval_AMOUNT_f1": 0.9386854874283194,
7
+ "eval_BIC_f1": 0.964071856287425,
8
+ "eval_BITCOINADDRESS_f1": 0.9637305699481865,
9
+ "eval_BUILDINGNUMBER_f1": 0.9010676156583629,
10
+ "eval_CITY_f1": 0.9259574468085108,
11
+ "eval_COMPANYNAME_f1": 0.9782082324455207,
12
+ "eval_COUNTY_f1": 0.977810650887574,
13
+ "eval_CREDITCARDCVV_f1": 0.9542857142857143,
14
+ "eval_CREDITCARDISSUER_f1": 1.0,
15
+ "eval_CREDITCARDNUMBER_f1": 0.8796223446105429,
16
+ "eval_CURRENCYCODE_f1": 0.8328267477203648,
17
+ "eval_CURRENCYNAME_f1": 0.34657039711191334,
18
+ "eval_CURRENCYSYMBOL_f1": 0.9420289855072463,
19
+ "eval_CURRENCY_f1": 0.7027027027027027,
20
+ "eval_DATE_f1": 0.8156424581005587,
21
+ "eval_DOB_f1": 0.6575121163166397,
22
+ "eval_EMAIL_f1": 0.9971477467199088,
23
+ "eval_ETHEREUMADDRESS_f1": 0.9946524064171123,
24
+ "eval_EYECOLOR_f1": 0.9833024118738404,
25
+ "eval_FIRSTNAME_f1": 0.9613659383591375,
26
+ "eval_GENDER_f1": 0.9881235154394298,
27
+ "eval_HEIGHT_f1": 0.9841986455981941,
28
+ "eval_IBAN_f1": 0.9818548387096774,
29
+ "eval_IPV4_f1": 0.6631419939577039,
30
+ "eval_IPV6_f1": 0.7243163340724317,
31
+ "eval_IP_f1": 0.20231822971549,
32
+ "eval_JOBAREA_f1": 0.9722222222222222,
33
+ "eval_JOBTITLE_f1": 0.9903774981495189,
34
+ "eval_JOBTYPE_f1": 0.9725058915946583,
35
+ "eval_LASTNAME_f1": 0.9185051778478163,
36
+ "eval_LITECOINADDRESS_f1": 0.8545454545454546,
37
+ "eval_MAC_f1": 0.9780439121756487,
38
+ "eval_MASKEDNUMBER_f1": 0.8365079365079364,
39
+ "eval_MIDDLENAME_f1": 0.915574963609898,
40
+ "eval_NEARBYGPSCOORDINATE_f1": 1.0,
41
+ "eval_ORDINALDIRECTION_f1": 0.9853181076672104,
42
+ "eval_PASSWORD_f1": 0.9782433521353747,
43
+ "eval_PHONEIMEI_f1": 0.9947312961011593,
44
+ "eval_PHONENUMBER_f1": 0.9882747068676717,
45
+ "eval_PIN_f1": 0.918918918918919,
46
+ "eval_PREFIX_f1": 0.9593727726300785,
47
+ "eval_SECONDARYADDRESS_f1": 0.9831053901850363,
48
+ "eval_SEX_f1": 0.9992790194664743,
49
+ "eval_SSN_f1": 0.9898242368177612,
50
+ "eval_STATE_f1": 0.973913043478261,
51
+ "eval_STREET_f1": 0.9355281207133058,
52
+ "eval_TIME_f1": 0.9764453961456102,
53
+ "eval_URL_f1": 0.9983766233766234,
54
+ "eval_USERAGENT_f1": 0.9884853852967228,
55
+ "eval_USERNAME_f1": 0.9797898140662894,
56
+ "eval_VEHICLEVIN_f1": 0.9614243323442138,
57
+ "eval_VEHICLEVRM_f1": 1.0,
58
+ "eval_ZIPCODE_f1": 0.909952606635071,
59
+ "eval_loss": 0.08207416534423828,
60
+ "eval_overall_accuracy": 0.9679481731535213,
61
+ "eval_overall_f1": 0.9230016748432613,
62
+ "eval_overall_precision": 0.9085789320105048,
63
+ "eval_overall_recall": 0.9378896954727552,
64
+ "eval_runtime": 89.4277,
65
+ "eval_samples": 10564,
66
+ "eval_samples_per_second": 118.129,
67
+ "eval_steps_per_second": 14.772,
68
+ "total_flos": 8429647356614820.0,
69
+ "train_loss": 0.19417928484794272,
70
+ "train_runtime": 3867.2299,
71
+ "train_samples": 42253,
72
+ "train_samples_per_second": 54.63,
73
+ "train_steps_per_second": 6.829
74
+ }
eval_results.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_ACCOUNTNAME_f1": 0.998468606431853,
4
+ "eval_ACCOUNTNUMBER_f1": 0.9848714069591529,
5
+ "eval_AGE_f1": 0.9791505791505791,
6
+ "eval_AMOUNT_f1": 0.9386854874283194,
7
+ "eval_BIC_f1": 0.964071856287425,
8
+ "eval_BITCOINADDRESS_f1": 0.9637305699481865,
9
+ "eval_BUILDINGNUMBER_f1": 0.9010676156583629,
10
+ "eval_CITY_f1": 0.9259574468085108,
11
+ "eval_COMPANYNAME_f1": 0.9782082324455207,
12
+ "eval_COUNTY_f1": 0.977810650887574,
13
+ "eval_CREDITCARDCVV_f1": 0.9542857142857143,
14
+ "eval_CREDITCARDISSUER_f1": 1.0,
15
+ "eval_CREDITCARDNUMBER_f1": 0.8796223446105429,
16
+ "eval_CURRENCYCODE_f1": 0.8328267477203648,
17
+ "eval_CURRENCYNAME_f1": 0.34657039711191334,
18
+ "eval_CURRENCYSYMBOL_f1": 0.9420289855072463,
19
+ "eval_CURRENCY_f1": 0.7027027027027027,
20
+ "eval_DATE_f1": 0.8156424581005587,
21
+ "eval_DOB_f1": 0.6575121163166397,
22
+ "eval_EMAIL_f1": 0.9971477467199088,
23
+ "eval_ETHEREUMADDRESS_f1": 0.9946524064171123,
24
+ "eval_EYECOLOR_f1": 0.9833024118738404,
25
+ "eval_FIRSTNAME_f1": 0.9613659383591375,
26
+ "eval_GENDER_f1": 0.9881235154394298,
27
+ "eval_HEIGHT_f1": 0.9841986455981941,
28
+ "eval_IBAN_f1": 0.9818548387096774,
29
+ "eval_IPV4_f1": 0.6631419939577039,
30
+ "eval_IPV6_f1": 0.7243163340724317,
31
+ "eval_IP_f1": 0.20231822971549,
32
+ "eval_JOBAREA_f1": 0.9722222222222222,
33
+ "eval_JOBTITLE_f1": 0.9903774981495189,
34
+ "eval_JOBTYPE_f1": 0.9725058915946583,
35
+ "eval_LASTNAME_f1": 0.9185051778478163,
36
+ "eval_LITECOINADDRESS_f1": 0.8545454545454546,
37
+ "eval_MAC_f1": 0.9780439121756487,
38
+ "eval_MASKEDNUMBER_f1": 0.8365079365079364,
39
+ "eval_MIDDLENAME_f1": 0.915574963609898,
40
+ "eval_NEARBYGPSCOORDINATE_f1": 1.0,
41
+ "eval_ORDINALDIRECTION_f1": 0.9853181076672104,
42
+ "eval_PASSWORD_f1": 0.9782433521353747,
43
+ "eval_PHONEIMEI_f1": 0.9947312961011593,
44
+ "eval_PHONENUMBER_f1": 0.9882747068676717,
45
+ "eval_PIN_f1": 0.918918918918919,
46
+ "eval_PREFIX_f1": 0.9593727726300785,
47
+ "eval_SECONDARYADDRESS_f1": 0.9831053901850363,
48
+ "eval_SEX_f1": 0.9992790194664743,
49
+ "eval_SSN_f1": 0.9898242368177612,
50
+ "eval_STATE_f1": 0.973913043478261,
51
+ "eval_STREET_f1": 0.9355281207133058,
52
+ "eval_TIME_f1": 0.9764453961456102,
53
+ "eval_URL_f1": 0.9983766233766234,
54
+ "eval_USERAGENT_f1": 0.9884853852967228,
55
+ "eval_USERNAME_f1": 0.9797898140662894,
56
+ "eval_VEHICLEVIN_f1": 0.9614243323442138,
57
+ "eval_VEHICLEVRM_f1": 1.0,
58
+ "eval_ZIPCODE_f1": 0.909952606635071,
59
+ "eval_loss": 0.08207416534423828,
60
+ "eval_overall_accuracy": 0.9679481731535213,
61
+ "eval_overall_f1": 0.9230016748432613,
62
+ "eval_overall_precision": 0.9085789320105048,
63
+ "eval_overall_recall": 0.9378896954727552,
64
+ "eval_runtime": 89.4277,
65
+ "eval_samples": 10564,
66
+ "eval_samples_per_second": 118.129,
67
+ "eval_steps_per_second": 14.772
68
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cadf646bafe7ff9cfc8125bd5596c12883756beb3a0d3882dca1b27ba6836c38
3
  size 267593220
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c66108e8021aa24eb5357165373ed2719353cbcad97ecf588fa507d28a18b30
3
  size 267593220
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 8429647356614820.0,
4
+ "train_loss": 0.19417928484794272,
5
+ "train_runtime": 3867.2299,
6
+ "train_samples": 42253,
7
+ "train_samples_per_second": 54.63,
8
+ "train_steps_per_second": 6.829
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,748 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.08207416534423828,
3
+ "best_model_checkpoint": "distilbert-base-german-cased_finetuned_ai4privacy_v2/checkpoint-15846",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 26410,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.09,
13
+ "learning_rate": 4.733055660734571e-06,
14
+ "loss": 3.2085,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.19,
19
+ "learning_rate": 9.466111321469142e-06,
20
+ "loss": 1.327,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.28,
25
+ "learning_rate": 1.4199166982203713e-05,
26
+ "loss": 0.7825,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.38,
31
+ "learning_rate": 1.8932222642938283e-05,
32
+ "loss": 0.4966,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.47,
37
+ "learning_rate": 2.3665278303672853e-05,
38
+ "loss": 0.3448,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.57,
43
+ "learning_rate": 2.8398333964407427e-05,
44
+ "loss": 0.258,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.66,
49
+ "learning_rate": 3.3131389625142e-05,
50
+ "loss": 0.2085,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.76,
55
+ "learning_rate": 3.786444528587657e-05,
56
+ "loss": 0.1772,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.85,
61
+ "learning_rate": 4.259750094661114e-05,
62
+ "loss": 0.1621,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.95,
67
+ "learning_rate": 4.733055660734571e-05,
68
+ "loss": 0.1449,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 1.0,
73
+ "eval_ACCOUNTNAME_f1": 0.9954198473282443,
74
+ "eval_ACCOUNTNUMBER_f1": 0.9179856115107913,
75
+ "eval_AGE_f1": 0.9508963367108341,
76
+ "eval_AMOUNT_f1": 0.7477624084621644,
77
+ "eval_BIC_f1": 0.8314606741573033,
78
+ "eval_BITCOINADDRESS_f1": 0.826487845766974,
79
+ "eval_BUILDINGNUMBER_f1": 0.7907608695652174,
80
+ "eval_CITY_f1": 0.8030176026823136,
81
+ "eval_COMPANYNAME_f1": 0.9011494252873564,
82
+ "eval_COUNTY_f1": 0.911849710982659,
83
+ "eval_CREDITCARDCVV_f1": 0.8668555240793201,
84
+ "eval_CREDITCARDISSUER_f1": 0.983108108108108,
85
+ "eval_CREDITCARDNUMBER_f1": 0.8052902277736959,
86
+ "eval_CURRENCYCODE_f1": 0.6481994459833795,
87
+ "eval_CURRENCYNAME_f1": 0.0,
88
+ "eval_CURRENCYSYMBOL_f1": 0.842998585572843,
89
+ "eval_CURRENCY_f1": 0.4935064935064935,
90
+ "eval_DATE_f1": 0.767189384800965,
91
+ "eval_DOB_f1": 0.47512864493996565,
92
+ "eval_EMAIL_f1": 0.9869835880022637,
93
+ "eval_ETHEREUMADDRESS_f1": 0.9102564102564104,
94
+ "eval_EYECOLOR_f1": 0.9500924214417744,
95
+ "eval_FIRSTNAME_f1": 0.8809652928416485,
96
+ "eval_GENDER_f1": 0.9551999999999999,
97
+ "eval_HEIGHT_f1": 0.9506726457399103,
98
+ "eval_IBAN_f1": 0.9085545722713864,
99
+ "eval_IPV4_f1": 0.8124098124098125,
100
+ "eval_IPV6_f1": 0.7776119402985074,
101
+ "eval_IP_f1": 0.0,
102
+ "eval_JOBAREA_f1": 0.8697788697788698,
103
+ "eval_JOBTITLE_f1": 0.9757887013939838,
104
+ "eval_JOBTYPE_f1": 0.9445324881141047,
105
+ "eval_LASTNAME_f1": 0.8139637649138312,
106
+ "eval_LITECOINADDRESS_f1": 0.5210084033613446,
107
+ "eval_MAC_f1": 0.9818913480885312,
108
+ "eval_MASKEDNUMBER_f1": 0.6554621848739496,
109
+ "eval_MIDDLENAME_f1": 0.4113980409617097,
110
+ "eval_NEARBYGPSCOORDINATE_f1": 1.0,
111
+ "eval_ORDINALDIRECTION_f1": 0.9836601307189542,
112
+ "eval_PASSWORD_f1": 0.8093333333333332,
113
+ "eval_PHONEIMEI_f1": 0.976066597294485,
114
+ "eval_PHONENUMBER_f1": 0.9253981559094719,
115
+ "eval_PIN_f1": 0.7704918032786884,
116
+ "eval_PREFIX_f1": 0.8613026819923371,
117
+ "eval_SECONDARYADDRESS_f1": 0.9675850891410049,
118
+ "eval_SEX_f1": 0.9978401727861772,
119
+ "eval_SSN_f1": 0.956989247311828,
120
+ "eval_STATE_f1": 0.8584831899921814,
121
+ "eval_STREET_f1": 0.8163538873994638,
122
+ "eval_TIME_f1": 0.964336661911555,
123
+ "eval_URL_f1": 0.9878934624697336,
124
+ "eval_USERAGENT_f1": 0.9533861037818822,
125
+ "eval_USERNAME_f1": 0.9415481832543444,
126
+ "eval_VEHICLEVIN_f1": 0.8777777777777778,
127
+ "eval_VEHICLEVRM_f1": 0.9715909090909092,
128
+ "eval_ZIPCODE_f1": 0.731284475965327,
129
+ "eval_loss": 0.13650085031986237,
130
+ "eval_overall_accuracy": 0.9504213707552718,
131
+ "eval_overall_f1": 0.8468665645290726,
132
+ "eval_overall_precision": 0.8212587729227983,
133
+ "eval_overall_recall": 0.8741227145395946,
134
+ "eval_runtime": 101.0692,
135
+ "eval_samples_per_second": 104.522,
136
+ "eval_steps_per_second": 13.07,
137
+ "step": 5282
138
+ },
139
+ {
140
+ "epoch": 1.04,
141
+ "learning_rate": 4.9484096932979936e-05,
142
+ "loss": 0.1457,
143
+ "step": 5500
144
+ },
145
+ {
146
+ "epoch": 1.14,
147
+ "learning_rate": 4.830083301779629e-05,
148
+ "loss": 0.1332,
149
+ "step": 6000
150
+ },
151
+ {
152
+ "epoch": 1.23,
153
+ "learning_rate": 4.711756910261265e-05,
154
+ "loss": 0.1257,
155
+ "step": 6500
156
+ },
157
+ {
158
+ "epoch": 1.33,
159
+ "learning_rate": 4.5934305187429e-05,
160
+ "loss": 0.1162,
161
+ "step": 7000
162
+ },
163
+ {
164
+ "epoch": 1.42,
165
+ "learning_rate": 4.4751041272245366e-05,
166
+ "loss": 0.114,
167
+ "step": 7500
168
+ },
169
+ {
170
+ "epoch": 1.51,
171
+ "learning_rate": 4.356777735706172e-05,
172
+ "loss": 0.1133,
173
+ "step": 8000
174
+ },
175
+ {
176
+ "epoch": 1.61,
177
+ "learning_rate": 4.238451344187808e-05,
178
+ "loss": 0.106,
179
+ "step": 8500
180
+ },
181
+ {
182
+ "epoch": 1.7,
183
+ "learning_rate": 4.120124952669443e-05,
184
+ "loss": 0.1071,
185
+ "step": 9000
186
+ },
187
+ {
188
+ "epoch": 1.8,
189
+ "learning_rate": 4.0017985611510796e-05,
190
+ "loss": 0.1018,
191
+ "step": 9500
192
+ },
193
+ {
194
+ "epoch": 1.89,
195
+ "learning_rate": 3.883472169632715e-05,
196
+ "loss": 0.1012,
197
+ "step": 10000
198
+ },
199
+ {
200
+ "epoch": 1.99,
201
+ "learning_rate": 3.765145778114351e-05,
202
+ "loss": 0.1039,
203
+ "step": 10500
204
+ },
205
+ {
206
+ "epoch": 2.0,
207
+ "eval_ACCOUNTNAME_f1": 0.9923430321592649,
208
+ "eval_ACCOUNTNUMBER_f1": 0.9598214285714286,
209
+ "eval_AGE_f1": 0.9720930232558139,
210
+ "eval_AMOUNT_f1": 0.8978704910908301,
211
+ "eval_BIC_f1": 0.9240121580547113,
212
+ "eval_BITCOINADDRESS_f1": 0.9217970049916806,
213
+ "eval_BUILDINGNUMBER_f1": 0.8937093275488069,
214
+ "eval_CITY_f1": 0.8802698145025295,
215
+ "eval_COMPANYNAME_f1": 0.9648000000000001,
216
+ "eval_COUNTY_f1": 0.9595375722543353,
217
+ "eval_CREDITCARDCVV_f1": 0.9562682215743439,
218
+ "eval_CREDITCARDISSUER_f1": 0.9847715736040609,
219
+ "eval_CREDITCARDNUMBER_f1": 0.842687747035573,
220
+ "eval_CURRENCYCODE_f1": 0.7677419354838709,
221
+ "eval_CURRENCYNAME_f1": 0.22096317280453254,
222
+ "eval_CURRENCYSYMBOL_f1": 0.9243937232524965,
223
+ "eval_CURRENCY_f1": 0.5723684210526316,
224
+ "eval_DATE_f1": 0.8003341687552213,
225
+ "eval_DOB_f1": 0.5865546218487394,
226
+ "eval_EMAIL_f1": 0.9931662870159453,
227
+ "eval_ETHEREUMADDRESS_f1": 0.9636363636363636,
228
+ "eval_EYECOLOR_f1": 0.98348623853211,
229
+ "eval_FIRSTNAME_f1": 0.9472764346053015,
230
+ "eval_GENDER_f1": 0.9794303797468354,
231
+ "eval_HEIGHT_f1": 0.9752808988764045,
232
+ "eval_IBAN_f1": 0.9643564356435643,
233
+ "eval_IPV4_f1": 0.7041666666666666,
234
+ "eval_IPV6_f1": 0.7563636363636365,
235
+ "eval_IP_f1": 0.01729106628242075,
236
+ "eval_JOBAREA_f1": 0.9438893159108378,
237
+ "eval_JOBTITLE_f1": 0.9911111111111112,
238
+ "eval_JOBTYPE_f1": 0.9709803921568626,
239
+ "eval_LASTNAME_f1": 0.8987566607460035,
240
+ "eval_LITECOINADDRESS_f1": 0.728813559322034,
241
+ "eval_MAC_f1": 0.9800796812749004,
242
+ "eval_MASKEDNUMBER_f1": 0.7912772585669782,
243
+ "eval_MIDDLENAME_f1": 0.8976608187134503,
244
+ "eval_NEARBYGPSCOORDINATE_f1": 0.9977728285077951,
245
+ "eval_ORDINALDIRECTION_f1": 0.9853181076672104,
246
+ "eval_PASSWORD_f1": 0.958102766798419,
247
+ "eval_PHONEIMEI_f1": 0.9936974789915967,
248
+ "eval_PHONENUMBER_f1": 0.9760923330585326,
249
+ "eval_PIN_f1": 0.9146341463414634,
250
+ "eval_PREFIX_f1": 0.916604057099925,
251
+ "eval_SECONDARYADDRESS_f1": 0.9741100323624595,
252
+ "eval_SEX_f1": 0.9978370583994233,
253
+ "eval_SSN_f1": 0.9787234042553191,
254
+ "eval_STATE_f1": 0.9448329448329448,
255
+ "eval_STREET_f1": 0.9031396125584502,
256
+ "eval_TIME_f1": 0.9591397849462365,
257
+ "eval_URL_f1": 0.9967637540453074,
258
+ "eval_USERAGENT_f1": 0.9638128861429833,
259
+ "eval_USERNAME_f1": 0.9718875502008032,
260
+ "eval_VEHICLEVIN_f1": 0.9454545454545454,
261
+ "eval_VEHICLEVRM_f1": 0.9828571428571428,
262
+ "eval_ZIPCODE_f1": 0.8863287250384024,
263
+ "eval_loss": 0.08413301408290863,
264
+ "eval_overall_accuracy": 0.9649157995052562,
265
+ "eval_overall_f1": 0.9040715288553904,
266
+ "eval_overall_precision": 0.8874543027911566,
267
+ "eval_overall_recall": 0.9213229314135968,
268
+ "eval_runtime": 89.7232,
269
+ "eval_samples_per_second": 117.74,
270
+ "eval_steps_per_second": 14.723,
271
+ "step": 10564
272
+ },
273
+ {
274
+ "epoch": 2.08,
275
+ "learning_rate": 3.646819386595986e-05,
276
+ "loss": 0.0819,
277
+ "step": 11000
278
+ },
279
+ {
280
+ "epoch": 2.18,
281
+ "learning_rate": 3.5284929950776226e-05,
282
+ "loss": 0.0851,
283
+ "step": 11500
284
+ },
285
+ {
286
+ "epoch": 2.27,
287
+ "learning_rate": 3.4101666035592575e-05,
288
+ "loss": 0.0801,
289
+ "step": 12000
290
+ },
291
+ {
292
+ "epoch": 2.37,
293
+ "learning_rate": 3.291840212040894e-05,
294
+ "loss": 0.0781,
295
+ "step": 12500
296
+ },
297
+ {
298
+ "epoch": 2.46,
299
+ "learning_rate": 3.173513820522529e-05,
300
+ "loss": 0.0845,
301
+ "step": 13000
302
+ },
303
+ {
304
+ "epoch": 2.56,
305
+ "learning_rate": 3.0551874290041656e-05,
306
+ "loss": 0.0789,
307
+ "step": 13500
308
+ },
309
+ {
310
+ "epoch": 2.65,
311
+ "learning_rate": 2.9368610374858008e-05,
312
+ "loss": 0.0744,
313
+ "step": 14000
314
+ },
315
+ {
316
+ "epoch": 2.75,
317
+ "learning_rate": 2.8185346459674367e-05,
318
+ "loss": 0.0878,
319
+ "step": 14500
320
+ },
321
+ {
322
+ "epoch": 2.84,
323
+ "learning_rate": 2.7002082544490726e-05,
324
+ "loss": 0.0784,
325
+ "step": 15000
326
+ },
327
+ {
328
+ "epoch": 2.93,
329
+ "learning_rate": 2.5818818629307086e-05,
330
+ "loss": 0.0804,
331
+ "step": 15500
332
+ },
333
+ {
334
+ "epoch": 3.0,
335
+ "eval_ACCOUNTNAME_f1": 0.998468606431853,
336
+ "eval_ACCOUNTNUMBER_f1": 0.9848714069591529,
337
+ "eval_AGE_f1": 0.9791505791505791,
338
+ "eval_AMOUNT_f1": 0.9386854874283194,
339
+ "eval_BIC_f1": 0.964071856287425,
340
+ "eval_BITCOINADDRESS_f1": 0.9637305699481865,
341
+ "eval_BUILDINGNUMBER_f1": 0.9010676156583629,
342
+ "eval_CITY_f1": 0.9259574468085108,
343
+ "eval_COMPANYNAME_f1": 0.9782082324455207,
344
+ "eval_COUNTY_f1": 0.977810650887574,
345
+ "eval_CREDITCARDCVV_f1": 0.9542857142857143,
346
+ "eval_CREDITCARDISSUER_f1": 1.0,
347
+ "eval_CREDITCARDNUMBER_f1": 0.8796223446105429,
348
+ "eval_CURRENCYCODE_f1": 0.8328267477203648,
349
+ "eval_CURRENCYNAME_f1": 0.34657039711191334,
350
+ "eval_CURRENCYSYMBOL_f1": 0.9420289855072463,
351
+ "eval_CURRENCY_f1": 0.7027027027027027,
352
+ "eval_DATE_f1": 0.8156424581005587,
353
+ "eval_DOB_f1": 0.6575121163166397,
354
+ "eval_EMAIL_f1": 0.9971477467199088,
355
+ "eval_ETHEREUMADDRESS_f1": 0.9946524064171123,
356
+ "eval_EYECOLOR_f1": 0.9833024118738404,
357
+ "eval_FIRSTNAME_f1": 0.9613659383591375,
358
+ "eval_GENDER_f1": 0.9881235154394298,
359
+ "eval_HEIGHT_f1": 0.9841986455981941,
360
+ "eval_IBAN_f1": 0.9818548387096774,
361
+ "eval_IPV4_f1": 0.6631419939577039,
362
+ "eval_IPV6_f1": 0.7243163340724317,
363
+ "eval_IP_f1": 0.20231822971549,
364
+ "eval_JOBAREA_f1": 0.9722222222222222,
365
+ "eval_JOBTITLE_f1": 0.9903774981495189,
366
+ "eval_JOBTYPE_f1": 0.9725058915946583,
367
+ "eval_LASTNAME_f1": 0.9185051778478163,
368
+ "eval_LITECOINADDRESS_f1": 0.8545454545454546,
369
+ "eval_MAC_f1": 0.9780439121756487,
370
+ "eval_MASKEDNUMBER_f1": 0.8365079365079364,
371
+ "eval_MIDDLENAME_f1": 0.915574963609898,
372
+ "eval_NEARBYGPSCOORDINATE_f1": 1.0,
373
+ "eval_ORDINALDIRECTION_f1": 0.9853181076672104,
374
+ "eval_PASSWORD_f1": 0.9782433521353747,
375
+ "eval_PHONEIMEI_f1": 0.9947312961011593,
376
+ "eval_PHONENUMBER_f1": 0.9882747068676717,
377
+ "eval_PIN_f1": 0.918918918918919,
378
+ "eval_PREFIX_f1": 0.9593727726300785,
379
+ "eval_SECONDARYADDRESS_f1": 0.9831053901850363,
380
+ "eval_SEX_f1": 0.9992790194664743,
381
+ "eval_SSN_f1": 0.9898242368177612,
382
+ "eval_STATE_f1": 0.973913043478261,
383
+ "eval_STREET_f1": 0.9355281207133058,
384
+ "eval_TIME_f1": 0.9764453961456102,
385
+ "eval_URL_f1": 0.9983766233766234,
386
+ "eval_USERAGENT_f1": 0.9884853852967228,
387
+ "eval_USERNAME_f1": 0.9797898140662894,
388
+ "eval_VEHICLEVIN_f1": 0.9614243323442138,
389
+ "eval_VEHICLEVRM_f1": 1.0,
390
+ "eval_ZIPCODE_f1": 0.909952606635071,
391
+ "eval_loss": 0.08207416534423828,
392
+ "eval_overall_accuracy": 0.9679481731535213,
393
+ "eval_overall_f1": 0.9230016748432613,
394
+ "eval_overall_precision": 0.9085789320105048,
395
+ "eval_overall_recall": 0.9378896954727552,
396
+ "eval_runtime": 86.3533,
397
+ "eval_samples_per_second": 122.335,
398
+ "eval_steps_per_second": 15.298,
399
+ "step": 15846
400
+ },
401
+ {
402
+ "epoch": 3.03,
403
+ "learning_rate": 2.463555471412344e-05,
404
+ "loss": 0.0752,
405
+ "step": 16000
406
+ },
407
+ {
408
+ "epoch": 3.12,
409
+ "learning_rate": 2.3452290798939797e-05,
410
+ "loss": 0.0593,
411
+ "step": 16500
412
+ },
413
+ {
414
+ "epoch": 3.22,
415
+ "learning_rate": 2.2269026883756153e-05,
416
+ "loss": 0.0639,
417
+ "step": 17000
418
+ },
419
+ {
420
+ "epoch": 3.31,
421
+ "learning_rate": 2.1085762968572512e-05,
422
+ "loss": 0.0602,
423
+ "step": 17500
424
+ },
425
+ {
426
+ "epoch": 3.41,
427
+ "learning_rate": 1.9902499053388868e-05,
428
+ "loss": 0.0628,
429
+ "step": 18000
430
+ },
431
+ {
432
+ "epoch": 3.5,
433
+ "learning_rate": 1.8719235138205227e-05,
434
+ "loss": 0.0585,
435
+ "step": 18500
436
+ },
437
+ {
438
+ "epoch": 3.6,
439
+ "learning_rate": 1.7535971223021583e-05,
440
+ "loss": 0.0622,
441
+ "step": 19000
442
+ },
443
+ {
444
+ "epoch": 3.69,
445
+ "learning_rate": 1.6352707307837942e-05,
446
+ "loss": 0.0637,
447
+ "step": 19500
448
+ },
449
+ {
450
+ "epoch": 3.79,
451
+ "learning_rate": 1.5169443392654298e-05,
452
+ "loss": 0.0585,
453
+ "step": 20000
454
+ },
455
+ {
456
+ "epoch": 3.88,
457
+ "learning_rate": 1.3986179477470657e-05,
458
+ "loss": 0.0583,
459
+ "step": 20500
460
+ },
461
+ {
462
+ "epoch": 3.98,
463
+ "learning_rate": 1.2802915562287013e-05,
464
+ "loss": 0.0622,
465
+ "step": 21000
466
+ },
467
+ {
468
+ "epoch": 4.0,
469
+ "eval_ACCOUNTNAME_f1": 0.9977046671767406,
470
+ "eval_ACCOUNTNUMBER_f1": 0.9931558935361217,
471
+ "eval_AGE_f1": 0.9815100154083205,
472
+ "eval_AMOUNT_f1": 0.9566383549396513,
473
+ "eval_BIC_f1": 0.9549549549549549,
474
+ "eval_BITCOINADDRESS_f1": 0.9703832752613241,
475
+ "eval_BUILDINGNUMBER_f1": 0.9186875891583453,
476
+ "eval_CITY_f1": 0.9277310924369748,
477
+ "eval_COMPANYNAME_f1": 0.9734513274336283,
478
+ "eval_COUNTY_f1": 0.975609756097561,
479
+ "eval_CREDITCARDCVV_f1": 0.967930029154519,
480
+ "eval_CREDITCARDISSUER_f1": 0.9966101694915255,
481
+ "eval_CREDITCARDNUMBER_f1": 0.8885245901639344,
482
+ "eval_CURRENCYCODE_f1": 0.8598130841121496,
483
+ "eval_CURRENCYNAME_f1": 0.4216524216524216,
484
+ "eval_CURRENCYSYMBOL_f1": 0.9601737871107893,
485
+ "eval_CURRENCY_f1": 0.6984815618221258,
486
+ "eval_DATE_f1": 0.8262008733624454,
487
+ "eval_DOB_f1": 0.6809184481393508,
488
+ "eval_EMAIL_f1": 0.996011396011396,
489
+ "eval_ETHEREUMADDRESS_f1": 0.9946524064171123,
490
+ "eval_EYECOLOR_f1": 0.985239852398524,
491
+ "eval_FIRSTNAME_f1": 0.9641085497519696,
492
+ "eval_GENDER_f1": 0.9952229299363058,
493
+ "eval_HEIGHT_f1": 0.995475113122172,
494
+ "eval_IBAN_f1": 0.9908998988877654,
495
+ "eval_IPV4_f1": 0.7066974595842956,
496
+ "eval_IPV6_f1": 0.6156133828996281,
497
+ "eval_IP_f1": 0.30528052805280526,
498
+ "eval_JOBAREA_f1": 0.9783616692426584,
499
+ "eval_JOBTITLE_f1": 0.9947955390334573,
500
+ "eval_JOBTYPE_f1": 0.9772905246671887,
501
+ "eval_LASTNAME_f1": 0.9176365264100268,
502
+ "eval_LITECOINADDRESS_f1": 0.8856304985337244,
503
+ "eval_MAC_f1": 0.9879518072289156,
504
+ "eval_MASKEDNUMBER_f1": 0.8597842835130971,
505
+ "eval_MIDDLENAME_f1": 0.9186046511627907,
506
+ "eval_NEARBYGPSCOORDINATE_f1": 1.0,
507
+ "eval_ORDINALDIRECTION_f1": 0.9885807504078303,
508
+ "eval_PASSWORD_f1": 0.9870967741935484,
509
+ "eval_PHONEIMEI_f1": 0.9968387776606955,
510
+ "eval_PHONENUMBER_f1": 0.9916387959866221,
511
+ "eval_PIN_f1": 0.9418960244648319,
512
+ "eval_PREFIX_f1": 0.9620817843866171,
513
+ "eval_SECONDARYADDRESS_f1": 0.9887278582930757,
514
+ "eval_SEX_f1": 1.0,
515
+ "eval_SSN_f1": 0.9925925925925926,
516
+ "eval_STATE_f1": 0.9716981132075472,
517
+ "eval_STREET_f1": 0.944141689373297,
518
+ "eval_TIME_f1": 0.9835125448028673,
519
+ "eval_URL_f1": 0.9991889699918897,
520
+ "eval_USERAGENT_f1": 0.9858407079646019,
521
+ "eval_USERNAME_f1": 0.9838449111470113,
522
+ "eval_VEHICLEVIN_f1": 0.9818181818181819,
523
+ "eval_VEHICLEVRM_f1": 0.9855907780979827,
524
+ "eval_ZIPCODE_f1": 0.897196261682243,
525
+ "eval_loss": 0.08476997166872025,
526
+ "eval_overall_accuracy": 0.9712797047401802,
527
+ "eval_overall_f1": 0.9254694227838361,
528
+ "eval_overall_precision": 0.9095218706375058,
529
+ "eval_overall_recall": 0.9419862044037471,
530
+ "eval_runtime": 88.3564,
531
+ "eval_samples_per_second": 119.561,
532
+ "eval_steps_per_second": 14.951,
533
+ "step": 21128
534
+ },
535
+ {
536
+ "epoch": 4.07,
537
+ "learning_rate": 1.161965164710337e-05,
538
+ "loss": 0.0435,
539
+ "step": 21500
540
+ },
541
+ {
542
+ "epoch": 4.17,
543
+ "learning_rate": 1.0436387731919728e-05,
544
+ "loss": 0.0397,
545
+ "step": 22000
546
+ },
547
+ {
548
+ "epoch": 4.26,
549
+ "learning_rate": 9.253123816736086e-06,
550
+ "loss": 0.0336,
551
+ "step": 22500
552
+ },
553
+ {
554
+ "epoch": 4.35,
555
+ "learning_rate": 8.069859901552443e-06,
556
+ "loss": 0.0382,
557
+ "step": 23000
558
+ },
559
+ {
560
+ "epoch": 4.45,
561
+ "learning_rate": 6.886595986368801e-06,
562
+ "loss": 0.0343,
563
+ "step": 23500
564
+ },
565
+ {
566
+ "epoch": 4.54,
567
+ "learning_rate": 5.703332071185157e-06,
568
+ "loss": 0.0339,
569
+ "step": 24000
570
+ },
571
+ {
572
+ "epoch": 4.64,
573
+ "learning_rate": 4.520068156001515e-06,
574
+ "loss": 0.0315,
575
+ "step": 24500
576
+ },
577
+ {
578
+ "epoch": 4.73,
579
+ "learning_rate": 3.3368042408178722e-06,
580
+ "loss": 0.033,
581
+ "step": 25000
582
+ },
583
+ {
584
+ "epoch": 4.83,
585
+ "learning_rate": 2.1535403256342298e-06,
586
+ "loss": 0.0305,
587
+ "step": 25500
588
+ },
589
+ {
590
+ "epoch": 4.92,
591
+ "learning_rate": 9.702764104505868e-07,
592
+ "loss": 0.032,
593
+ "step": 26000
594
+ },
595
+ {
596
+ "epoch": 5.0,
597
+ "eval_ACCOUNTNAME_f1": 0.998468606431853,
598
+ "eval_ACCOUNTNUMBER_f1": 0.9961977186311788,
599
+ "eval_AGE_f1": 0.9846860643185298,
600
+ "eval_AMOUNT_f1": 0.962239004886717,
601
+ "eval_BIC_f1": 0.9614243323442137,
602
+ "eval_BITCOINADDRESS_f1": 0.9738219895287958,
603
+ "eval_BUILDINGNUMBER_f1": 0.9268645908761767,
604
+ "eval_CITY_f1": 0.9431438127090301,
605
+ "eval_COMPANYNAME_f1": 0.9782433521353747,
606
+ "eval_COUNTY_f1": 0.9748520710059172,
607
+ "eval_CREDITCARDCVV_f1": 0.9707602339181286,
608
+ "eval_CREDITCARDISSUER_f1": 0.9949238578680203,
609
+ "eval_CREDITCARDNUMBER_f1": 0.8990384615384617,
610
+ "eval_CURRENCYCODE_f1": 0.84472049689441,
611
+ "eval_CURRENCYNAME_f1": 0.4615384615384615,
612
+ "eval_CURRENCYSYMBOL_f1": 0.9646209386281589,
613
+ "eval_CURRENCY_f1": 0.7116022099447514,
614
+ "eval_DATE_f1": 0.8296430185268866,
615
+ "eval_DOB_f1": 0.7234678624813154,
616
+ "eval_EMAIL_f1": 0.9965792474344356,
617
+ "eval_ETHEREUMADDRESS_f1": 0.9946666666666667,
618
+ "eval_EYECOLOR_f1": 0.9853479853479853,
619
+ "eval_FIRSTNAME_f1": 0.9671702498547355,
620
+ "eval_GENDER_f1": 0.9928741092636578,
621
+ "eval_HEIGHT_f1": 0.9932279909706545,
622
+ "eval_IBAN_f1": 0.9919028340080971,
623
+ "eval_IPV4_f1": 0.7689946277820414,
624
+ "eval_IPV6_f1": 0.6836027713625865,
625
+ "eval_IP_f1": 0.37057728119180633,
626
+ "eval_JOBAREA_f1": 0.9837587006960556,
627
+ "eval_JOBTITLE_f1": 0.9940564635958394,
628
+ "eval_JOBTYPE_f1": 0.9788566953797964,
629
+ "eval_LASTNAME_f1": 0.9251577998196574,
630
+ "eval_LITECOINADDRESS_f1": 0.8875739644970415,
631
+ "eval_MAC_f1": 0.995967741935484,
632
+ "eval_MASKEDNUMBER_f1": 0.8848580441640378,
633
+ "eval_MIDDLENAME_f1": 0.9171511627906977,
634
+ "eval_NEARBYGPSCOORDINATE_f1": 1.0,
635
+ "eval_ORDINALDIRECTION_f1": 0.9885807504078303,
636
+ "eval_PASSWORD_f1": 0.9846650524616627,
637
+ "eval_PHONEIMEI_f1": 0.9957894736842106,
638
+ "eval_PHONENUMBER_f1": 0.9924686192468619,
639
+ "eval_PIN_f1": 0.9483282674772036,
640
+ "eval_PREFIX_f1": 0.96996336996337,
641
+ "eval_SECONDARYADDRESS_f1": 0.9911504424778762,
642
+ "eval_SEX_f1": 1.0,
643
+ "eval_SSN_f1": 0.9944444444444445,
644
+ "eval_STATE_f1": 0.975609756097561,
645
+ "eval_STREET_f1": 0.9467939972714872,
646
+ "eval_TIME_f1": 0.99,
647
+ "eval_URL_f1": 0.9983766233766234,
648
+ "eval_USERAGENT_f1": 0.994661921708185,
649
+ "eval_USERNAME_f1": 0.9806451612903225,
650
+ "eval_VEHICLEVIN_f1": 0.9939024390243903,
651
+ "eval_VEHICLEVRM_f1": 1.0,
652
+ "eval_ZIPCODE_f1": 0.9107692307692307,
653
+ "eval_loss": 0.09979617595672607,
654
+ "eval_overall_accuracy": 0.974122838328931,
655
+ "eval_overall_f1": 0.935134654170127,
656
+ "eval_overall_precision": 0.9210118891128444,
657
+ "eval_overall_recall": 0.9496972800385554,
658
+ "eval_runtime": 86.467,
659
+ "eval_samples_per_second": 122.174,
660
+ "eval_steps_per_second": 15.278,
661
+ "step": 26410
662
+ },
663
+ {
664
+ "epoch": 5.0,
665
+ "step": 26410,
666
+ "total_flos": 8429647356614820.0,
667
+ "train_loss": 0.19417928484794272,
668
+ "train_runtime": 3867.2299,
669
+ "train_samples_per_second": 54.63,
670
+ "train_steps_per_second": 6.829
671
+ },
672
+ {
673
+ "epoch": 5.0,
674
+ "eval_ACCOUNTNAME_f1": 0.998468606431853,
675
+ "eval_ACCOUNTNUMBER_f1": 0.9848714069591529,
676
+ "eval_AGE_f1": 0.9791505791505791,
677
+ "eval_AMOUNT_f1": 0.9386854874283194,
678
+ "eval_BIC_f1": 0.964071856287425,
679
+ "eval_BITCOINADDRESS_f1": 0.9637305699481865,
680
+ "eval_BUILDINGNUMBER_f1": 0.9010676156583629,
681
+ "eval_CITY_f1": 0.9259574468085108,
682
+ "eval_COMPANYNAME_f1": 0.9782082324455207,
683
+ "eval_COUNTY_f1": 0.977810650887574,
684
+ "eval_CREDITCARDCVV_f1": 0.9542857142857143,
685
+ "eval_CREDITCARDISSUER_f1": 1.0,
686
+ "eval_CREDITCARDNUMBER_f1": 0.8796223446105429,
687
+ "eval_CURRENCYCODE_f1": 0.8328267477203648,
688
+ "eval_CURRENCYNAME_f1": 0.34657039711191334,
689
+ "eval_CURRENCYSYMBOL_f1": 0.9420289855072463,
690
+ "eval_CURRENCY_f1": 0.7027027027027027,
691
+ "eval_DATE_f1": 0.8156424581005587,
692
+ "eval_DOB_f1": 0.6575121163166397,
693
+ "eval_EMAIL_f1": 0.9971477467199088,
694
+ "eval_ETHEREUMADDRESS_f1": 0.9946524064171123,
695
+ "eval_EYECOLOR_f1": 0.9833024118738404,
696
+ "eval_FIRSTNAME_f1": 0.9613659383591375,
697
+ "eval_GENDER_f1": 0.9881235154394298,
698
+ "eval_HEIGHT_f1": 0.9841986455981941,
699
+ "eval_IBAN_f1": 0.9818548387096774,
700
+ "eval_IPV4_f1": 0.6631419939577039,
701
+ "eval_IPV6_f1": 0.7243163340724317,
702
+ "eval_IP_f1": 0.20231822971549,
703
+ "eval_JOBAREA_f1": 0.9722222222222222,
704
+ "eval_JOBTITLE_f1": 0.9903774981495189,
705
+ "eval_JOBTYPE_f1": 0.9725058915946583,
706
+ "eval_LASTNAME_f1": 0.9185051778478163,
707
+ "eval_LITECOINADDRESS_f1": 0.8545454545454546,
708
+ "eval_MAC_f1": 0.9780439121756487,
709
+ "eval_MASKEDNUMBER_f1": 0.8365079365079364,
710
+ "eval_MIDDLENAME_f1": 0.915574963609898,
711
+ "eval_NEARBYGPSCOORDINATE_f1": 1.0,
712
+ "eval_ORDINALDIRECTION_f1": 0.9853181076672104,
713
+ "eval_PASSWORD_f1": 0.9782433521353747,
714
+ "eval_PHONEIMEI_f1": 0.9947312961011593,
715
+ "eval_PHONENUMBER_f1": 0.9882747068676717,
716
+ "eval_PIN_f1": 0.918918918918919,
717
+ "eval_PREFIX_f1": 0.9593727726300785,
718
+ "eval_SECONDARYADDRESS_f1": 0.9831053901850363,
719
+ "eval_SEX_f1": 0.9992790194664743,
720
+ "eval_SSN_f1": 0.9898242368177612,
721
+ "eval_STATE_f1": 0.973913043478261,
722
+ "eval_STREET_f1": 0.9355281207133058,
723
+ "eval_TIME_f1": 0.9764453961456102,
724
+ "eval_URL_f1": 0.9983766233766234,
725
+ "eval_USERAGENT_f1": 0.9884853852967228,
726
+ "eval_USERNAME_f1": 0.9797898140662894,
727
+ "eval_VEHICLEVIN_f1": 0.9614243323442138,
728
+ "eval_VEHICLEVRM_f1": 1.0,
729
+ "eval_ZIPCODE_f1": 0.909952606635071,
730
+ "eval_loss": 0.08207416534423828,
731
+ "eval_overall_accuracy": 0.9679481731535213,
732
+ "eval_overall_f1": 0.9230016748432613,
733
+ "eval_overall_precision": 0.9085789320105048,
734
+ "eval_overall_recall": 0.9378896954727552,
735
+ "eval_runtime": 89.4277,
736
+ "eval_samples_per_second": 118.129,
737
+ "eval_steps_per_second": 14.772,
738
+ "step": 26410
739
+ }
740
+ ],
741
+ "logging_steps": 500,
742
+ "max_steps": 26410,
743
+ "num_train_epochs": 5,
744
+ "save_steps": 500,
745
+ "total_flos": 8429647356614820.0,
746
+ "trial_name": null,
747
+ "trial_params": null
748
+ }