Isotonic commited on
Commit
011f54c
·
verified ·
1 Parent(s): c08e6c9

Isotonic/ai4privacy200k_adapter_en

Browse files
README.md ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-multilingual-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: ai4privacy_v2_adapter_en
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
+ # ai4privacy_v2_adapter_en
15
+
16
+ This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.1079
19
+ - Overall Precision: 0.8136
20
+ - Overall Recall: 0.8836
21
+ - Overall F1: 0.8472
22
+ - Overall Accuracy: 0.9560
23
+ - Accountname F1: 0.9712
24
+ - Accountnumber F1: 0.9677
25
+ - Age F1: 0.8432
26
+ - Amount F1: 0.7929
27
+ - Bic F1: 0.9689
28
+ - Bitcoinaddress F1: 0.9343
29
+ - Buildingnumber F1: 0.8405
30
+ - City F1: 0.8139
31
+ - Companyname F1: 0.9310
32
+ - County F1: 0.8406
33
+ - Creditcardcvv F1: 0.8889
34
+ - Creditcardissuer F1: 0.9661
35
+ - Creditcardnumber F1: 0.8404
36
+ - Currency F1: 0.5968
37
+ - Currencycode F1: 0.6556
38
+ - Currencyname F1: 0.0182
39
+ - Currencysymbol F1: 0.8176
40
+ - Date F1: 0.7858
41
+ - Dob F1: 0.4636
42
+ - Email F1: 0.9928
43
+ - Ethereumaddress F1: 0.9941
44
+ - Eyecolor F1: 0.7859
45
+ - Firstname F1: 0.8699
46
+ - Gender F1: 0.8945
47
+ - Height F1: 0.9227
48
+ - Iban F1: 0.9730
49
+ - Ip F1: 0.0497
50
+ - Ipv4 F1: 0.8345
51
+ - Ipv6 F1: 0.4659
52
+ - Jobarea F1: 0.9131
53
+ - Jobtitle F1: 0.9599
54
+ - Jobtype F1: 0.9303
55
+ - Lastname F1: 0.8016
56
+ - Litecoinaddress F1: 0.8483
57
+ - Mac F1: 0.9817
58
+ - Maskednumber F1: 0.7049
59
+ - Middlename F1: 0.5006
60
+ - Nearbygpscoordinate F1: 0.9969
61
+ - Ordinaldirection F1: 0.9519
62
+ - Password F1: 0.9780
63
+ - Phoneimei F1: 0.9928
64
+ - Phonenumber F1: 0.9752
65
+ - Pin F1: 0.7525
66
+ - Prefix F1: 0.9121
67
+ - Secondaryaddress F1: 0.9474
68
+ - Sex F1: 0.9770
69
+ - Ssn F1: 0.9771
70
+ - State F1: 0.8680
71
+ - Street F1: 0.8677
72
+ - Time F1: 0.9516
73
+ - Url F1: 0.9975
74
+ - Useragent F1: 0.9844
75
+ - Username F1: 0.9669
76
+ - Vehiclevin F1: 0.9775
77
+ - Vehiclevrm F1: 0.9888
78
+ - Zipcode F1: 0.8203
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: 32
99
+ - eval_batch_size: 32
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: 6
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
+ | 0.9109 | 1.0 | 1088 | 0.5093 | 0.2688 | 0.3282 | 0.2956 | 0.8499 | 0.2034 | 0.3040 | 0.0752 | 0.1147 | 0.0935 | 0.5972 | 0.0673 | 0.0 | 0.0024 | 0.0 | 0.0 | 0.0 | 0.1141 | 0.0 | 0.0 | 0.0 | 0.0112 | 0.7137 | 0.0 | 0.9095 | 0.9119 | 0.0 | 0.3152 | 0.0 | 0.0 | 0.8248 | 0.0 | 0.6785 | 0.4199 | 0.0 | 0.0475 | 0.0 | 0.0167 | 0.0907 | 0.6333 | 0.0011 | 0.0 | 0.9525 | 0.0 | 0.6438 | 0.3918 | 0.2703 | 0.0 | 0.0099 | 0.2395 | 0.0 | 0.0220 | 0.0 | 0.0276 | 0.5557 | 0.9658 | 0.8157 | 0.0415 | 0.3955 | 0.0106 | 0.0181 |
111
+ | 0.2793 | 2.0 | 2176 | 0.1903 | 0.6974 | 0.7582 | 0.7265 | 0.9309 | 0.9684 | 0.8789 | 0.7561 | 0.3604 | 0.7609 | 0.8715 | 0.6492 | 0.4956 | 0.8028 | 0.5558 | 0.7756 | 0.6575 | 0.5363 | 0.4671 | 0.128 | 0.0 | 0.5910 | 0.7731 | 0.0186 | 0.9838 | 0.9465 | 0.4482 | 0.7689 | 0.5160 | 0.7446 | 0.9234 | 0.0 | 0.8226 | 0.8007 | 0.5589 | 0.8712 | 0.6553 | 0.6634 | 0.7056 | 0.9315 | 0.0382 | 0.0661 | 0.9954 | 0.8828 | 0.9270 | 0.9693 | 0.8621 | 0.1481 | 0.8783 | 0.9120 | 0.9262 | 0.8707 | 0.6693 | 0.7378 | 0.9152 | 0.9886 | 0.9524 | 0.8859 | 0.8352 | 0.8976 | 0.6466 |
112
+ | 0.1707 | 3.0 | 3264 | 0.1388 | 0.7704 | 0.8319 | 0.8000 | 0.9467 | 0.9702 | 0.9396 | 0.8120 | 0.6102 | 0.9298 | 0.9034 | 0.7409 | 0.6205 | 0.8922 | 0.7128 | 0.8446 | 0.9218 | 0.6983 | 0.5504 | 0.5380 | 0.0106 | 0.6877 | 0.6125 | 0.3259 | 0.9892 | 0.9956 | 0.6647 | 0.8358 | 0.7540 | 0.8859 | 0.9430 | 0.0 | 0.8313 | 0.7993 | 0.8235 | 0.9241 | 0.8191 | 0.7504 | 0.7882 | 0.9412 | 0.5129 | 0.4005 | 0.9969 | 0.9452 | 0.9618 | 0.9900 | 0.9452 | 0.5018 | 0.8959 | 0.9348 | 0.9406 | 0.9524 | 0.7643 | 0.7747 | 0.9497 | 0.9943 | 0.9714 | 0.9274 | 0.9048 | 0.9646 | 0.7387 |
113
+ | 0.1373 | 4.0 | 4352 | 0.1197 | 0.7751 | 0.8645 | 0.8174 | 0.9509 | 0.9651 | 0.9510 | 0.8263 | 0.7169 | 0.9592 | 0.9254 | 0.8151 | 0.7795 | 0.9148 | 0.8060 | 0.8808 | 0.9524 | 0.8007 | 0.5676 | 0.5656 | 0.0249 | 0.8000 | 0.7858 | 0.3425 | 0.9910 | 0.9869 | 0.7552 | 0.8609 | 0.8397 | 0.8981 | 0.9779 | 0.0278 | 0.8309 | 0.3179 | 0.8643 | 0.9475 | 0.9000 | 0.7812 | 0.8415 | 0.9749 | 0.6191 | 0.4617 | 0.9969 | 0.9519 | 0.9711 | 0.9914 | 0.9700 | 0.6733 | 0.9088 | 0.9421 | 0.9732 | 0.9671 | 0.8360 | 0.8494 | 0.9442 | 0.9943 | 0.9618 | 0.9487 | 0.9838 | 0.9672 | 0.8093 |
114
+ | 0.1202 | 5.0 | 5440 | 0.1106 | 0.8264 | 0.8796 | 0.8522 | 0.9564 | 0.9720 | 0.9634 | 0.8360 | 0.7423 | 0.9756 | 0.9327 | 0.8268 | 0.8031 | 0.9134 | 0.8404 | 0.8792 | 0.9660 | 0.7957 | 0.5723 | 0.6159 | 0.0167 | 0.8132 | 0.7914 | 0.4301 | 0.9928 | 0.9941 | 0.7544 | 0.8659 | 0.8871 | 0.9121 | 0.9695 | 0.0137 | 0.8361 | 0.7008 | 0.9108 | 0.9623 | 0.9126 | 0.7783 | 0.8459 | 0.9749 | 0.6770 | 0.4944 | 0.9985 | 0.9519 | 0.9754 | 0.9900 | 0.9673 | 0.7647 | 0.9115 | 0.9484 | 0.9760 | 0.9771 | 0.8588 | 0.8590 | 0.9526 | 0.9975 | 0.9820 | 0.9547 | 0.9871 | 0.9916 | 0.8133 |
115
+ | 0.1065 | 6.0 | 6528 | 0.1079 | 0.8136 | 0.8836 | 0.8472 | 0.9560 | 0.9712 | 0.9677 | 0.8432 | 0.7929 | 0.9689 | 0.9343 | 0.8405 | 0.8139 | 0.9310 | 0.8406 | 0.8889 | 0.9661 | 0.8404 | 0.5968 | 0.6556 | 0.0182 | 0.8176 | 0.7858 | 0.4636 | 0.9928 | 0.9941 | 0.7859 | 0.8699 | 0.8945 | 0.9227 | 0.9730 | 0.0497 | 0.8345 | 0.4659 | 0.9131 | 0.9599 | 0.9303 | 0.8016 | 0.8483 | 0.9817 | 0.7049 | 0.5006 | 0.9969 | 0.9519 | 0.9780 | 0.9928 | 0.9752 | 0.7525 | 0.9121 | 0.9474 | 0.9770 | 0.9771 | 0.8680 | 0.8677 | 0.9516 | 0.9975 | 0.9844 | 0.9669 | 0.9775 | 0.9888 | 0.8203 |
116
+
117
+
118
+ ### Framework versions
119
+
120
+ - Transformers 4.35.2
121
+ - Pytorch 2.1.0+cu121
122
+ - Datasets 2.17.0
123
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
+ "bias": "all",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 384,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 320,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_lin",
23
+ "v_lin",
24
+ "k_lin",
25
+ "out_lin"
26
+ ],
27
+ "task_type": "TOKEN_CLS",
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baac2df7a49b163ddd40f6cecb646cef4b6f766fa59376ad9826aa1ecdb4f368
3
+ size 47760508
all_results.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_ACCOUNTNAME_f1": 0.9712230215827338,
4
+ "eval_ACCOUNTNUMBER_f1": 0.967741935483871,
5
+ "eval_AGE_f1": 0.8432203389830508,
6
+ "eval_AMOUNT_f1": 0.7929342492639844,
7
+ "eval_BIC_f1": 0.9688581314878892,
8
+ "eval_BITCOINADDRESS_f1": 0.9342915811088296,
9
+ "eval_BUILDINGNUMBER_f1": 0.8405253283302063,
10
+ "eval_CITY_f1": 0.8139337298215804,
11
+ "eval_COMPANYNAME_f1": 0.9310344827586207,
12
+ "eval_COUNTY_f1": 0.8406304728546411,
13
+ "eval_CREDITCARDCVV_f1": 0.8888888888888888,
14
+ "eval_CREDITCARDISSUER_f1": 0.9660743134087239,
15
+ "eval_CREDITCARDNUMBER_f1": 0.8403967538322814,
16
+ "eval_CURRENCYCODE_f1": 0.6556291390728476,
17
+ "eval_CURRENCYNAME_f1": 0.01818181818181818,
18
+ "eval_CURRENCYSYMBOL_f1": 0.8175985334555453,
19
+ "eval_CURRENCY_f1": 0.5967741935483872,
20
+ "eval_DATE_f1": 0.7857793983591613,
21
+ "eval_DOB_f1": 0.46357615894039733,
22
+ "eval_EMAIL_f1": 0.9927710843373494,
23
+ "eval_ETHEREUMADDRESS_f1": 0.9941348973607038,
24
+ "eval_EYECOLOR_f1": 0.7859237536656891,
25
+ "eval_FIRSTNAME_f1": 0.8699042892591281,
26
+ "eval_GENDER_f1": 0.8945233265720081,
27
+ "eval_HEIGHT_f1": 0.9226519337016574,
28
+ "eval_IBAN_f1": 0.972972972972973,
29
+ "eval_IPV4_f1": 0.8345323741007193,
30
+ "eval_IPV6_f1": 0.4659231722428749,
31
+ "eval_IP_f1": 0.049665711556829036,
32
+ "eval_JOBAREA_f1": 0.9130801687763713,
33
+ "eval_JOBTITLE_f1": 0.9599345870809485,
34
+ "eval_JOBTYPE_f1": 0.930316742081448,
35
+ "eval_LASTNAME_f1": 0.8015833745670461,
36
+ "eval_LITECOINADDRESS_f1": 0.848314606741573,
37
+ "eval_MAC_f1": 0.9817351598173517,
38
+ "eval_MASKEDNUMBER_f1": 0.7049180327868851,
39
+ "eval_MIDDLENAME_f1": 0.5005847953216374,
40
+ "eval_NEARBYGPSCOORDINATE_f1": 0.9969418960244648,
41
+ "eval_ORDINALDIRECTION_f1": 0.9519450800915331,
42
+ "eval_PASSWORD_f1": 0.9780123131046614,
43
+ "eval_PHONEIMEI_f1": 0.9928469241773962,
44
+ "eval_PHONENUMBER_f1": 0.9751552795031055,
45
+ "eval_PIN_f1": 0.7524752475247525,
46
+ "eval_PREFIX_f1": 0.9120879120879122,
47
+ "eval_SECONDARYADDRESS_f1": 0.9473684210526315,
48
+ "eval_SEX_f1": 0.976976976976977,
49
+ "eval_SSN_f1": 0.9770992366412213,
50
+ "eval_STATE_f1": 0.8680445151033387,
51
+ "eval_STREET_f1": 0.8676748582230623,
52
+ "eval_TIME_f1": 0.951627088830255,
53
+ "eval_URL_f1": 0.9975429975429976,
54
+ "eval_USERAGENT_f1": 0.9843937575030013,
55
+ "eval_USERNAME_f1": 0.9669291338582677,
56
+ "eval_VEHICLEVIN_f1": 0.977491961414791,
57
+ "eval_VEHICLEVRM_f1": 0.9888268156424581,
58
+ "eval_ZIPCODE_f1": 0.8203045685279189,
59
+ "eval_loss": 0.10785039514303207,
60
+ "eval_overall_accuracy": 0.9559518404054311,
61
+ "eval_overall_f1": 0.8471647350993378,
62
+ "eval_overall_precision": 0.8135744807711418,
63
+ "eval_overall_recall": 0.8836481381543443,
64
+ "eval_runtime": 95.1945,
65
+ "eval_samples": 8701,
66
+ "eval_samples_per_second": 91.402,
67
+ "eval_steps_per_second": 2.857,
68
+ "total_flos": 1.458680878857888e+16,
69
+ "train_loss": 0.4378688358427847,
70
+ "train_runtime": 4446.6577,
71
+ "train_samples": 34800,
72
+ "train_samples_per_second": 46.957,
73
+ "train_steps_per_second": 1.468
74
+ }
eval_results.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_ACCOUNTNAME_f1": 0.9712230215827338,
4
+ "eval_ACCOUNTNUMBER_f1": 0.967741935483871,
5
+ "eval_AGE_f1": 0.8432203389830508,
6
+ "eval_AMOUNT_f1": 0.7929342492639844,
7
+ "eval_BIC_f1": 0.9688581314878892,
8
+ "eval_BITCOINADDRESS_f1": 0.9342915811088296,
9
+ "eval_BUILDINGNUMBER_f1": 0.8405253283302063,
10
+ "eval_CITY_f1": 0.8139337298215804,
11
+ "eval_COMPANYNAME_f1": 0.9310344827586207,
12
+ "eval_COUNTY_f1": 0.8406304728546411,
13
+ "eval_CREDITCARDCVV_f1": 0.8888888888888888,
14
+ "eval_CREDITCARDISSUER_f1": 0.9660743134087239,
15
+ "eval_CREDITCARDNUMBER_f1": 0.8403967538322814,
16
+ "eval_CURRENCYCODE_f1": 0.6556291390728476,
17
+ "eval_CURRENCYNAME_f1": 0.01818181818181818,
18
+ "eval_CURRENCYSYMBOL_f1": 0.8175985334555453,
19
+ "eval_CURRENCY_f1": 0.5967741935483872,
20
+ "eval_DATE_f1": 0.7857793983591613,
21
+ "eval_DOB_f1": 0.46357615894039733,
22
+ "eval_EMAIL_f1": 0.9927710843373494,
23
+ "eval_ETHEREUMADDRESS_f1": 0.9941348973607038,
24
+ "eval_EYECOLOR_f1": 0.7859237536656891,
25
+ "eval_FIRSTNAME_f1": 0.8699042892591281,
26
+ "eval_GENDER_f1": 0.8945233265720081,
27
+ "eval_HEIGHT_f1": 0.9226519337016574,
28
+ "eval_IBAN_f1": 0.972972972972973,
29
+ "eval_IPV4_f1": 0.8345323741007193,
30
+ "eval_IPV6_f1": 0.4659231722428749,
31
+ "eval_IP_f1": 0.049665711556829036,
32
+ "eval_JOBAREA_f1": 0.9130801687763713,
33
+ "eval_JOBTITLE_f1": 0.9599345870809485,
34
+ "eval_JOBTYPE_f1": 0.930316742081448,
35
+ "eval_LASTNAME_f1": 0.8015833745670461,
36
+ "eval_LITECOINADDRESS_f1": 0.848314606741573,
37
+ "eval_MAC_f1": 0.9817351598173517,
38
+ "eval_MASKEDNUMBER_f1": 0.7049180327868851,
39
+ "eval_MIDDLENAME_f1": 0.5005847953216374,
40
+ "eval_NEARBYGPSCOORDINATE_f1": 0.9969418960244648,
41
+ "eval_ORDINALDIRECTION_f1": 0.9519450800915331,
42
+ "eval_PASSWORD_f1": 0.9780123131046614,
43
+ "eval_PHONEIMEI_f1": 0.9928469241773962,
44
+ "eval_PHONENUMBER_f1": 0.9751552795031055,
45
+ "eval_PIN_f1": 0.7524752475247525,
46
+ "eval_PREFIX_f1": 0.9120879120879122,
47
+ "eval_SECONDARYADDRESS_f1": 0.9473684210526315,
48
+ "eval_SEX_f1": 0.976976976976977,
49
+ "eval_SSN_f1": 0.9770992366412213,
50
+ "eval_STATE_f1": 0.8680445151033387,
51
+ "eval_STREET_f1": 0.8676748582230623,
52
+ "eval_TIME_f1": 0.951627088830255,
53
+ "eval_URL_f1": 0.9975429975429976,
54
+ "eval_USERAGENT_f1": 0.9843937575030013,
55
+ "eval_USERNAME_f1": 0.9669291338582677,
56
+ "eval_VEHICLEVIN_f1": 0.977491961414791,
57
+ "eval_VEHICLEVRM_f1": 0.9888268156424581,
58
+ "eval_ZIPCODE_f1": 0.8203045685279189,
59
+ "eval_loss": 0.10785039514303207,
60
+ "eval_overall_accuracy": 0.9559518404054311,
61
+ "eval_overall_f1": 0.8471647350993378,
62
+ "eval_overall_precision": 0.8135744807711418,
63
+ "eval_overall_recall": 0.8836481381543443,
64
+ "eval_runtime": 95.1945,
65
+ "eval_samples": 8701,
66
+ "eval_samples_per_second": 91.402,
67
+ "eval_steps_per_second": 2.857
68
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "total_flos": 1.458680878857888e+16,
4
+ "train_loss": 0.4378688358427847,
5
+ "train_runtime": 4446.6577,
6
+ "train_samples": 34800,
7
+ "train_samples_per_second": 46.957,
8
+ "train_steps_per_second": 1.468
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,582 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.10785039514303207,
3
+ "best_model_checkpoint": "ai4privacy_v2_adapter_en/checkpoint-6528",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6528,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.46,
13
+ "learning_rate": 1.9142419601837675e-05,
14
+ "loss": 2.8226,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.92,
19
+ "learning_rate": 3.828483920367535e-05,
20
+ "loss": 0.9109,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_ACCOUNTNAME_f1": 0.20342205323193913,
26
+ "eval_ACCOUNTNUMBER_f1": 0.3039927404718693,
27
+ "eval_AGE_f1": 0.07516339869281047,
28
+ "eval_AMOUNT_f1": 0.11468695143358691,
29
+ "eval_BIC_f1": 0.09345794392523366,
30
+ "eval_BITCOINADDRESS_f1": 0.5972108285479902,
31
+ "eval_BUILDINGNUMBER_f1": 0.06732117812061712,
32
+ "eval_CITY_f1": 0.0,
33
+ "eval_COMPANYNAME_f1": 0.0024301336573511545,
34
+ "eval_COUNTY_f1": 0.0,
35
+ "eval_CREDITCARDCVV_f1": 0.0,
36
+ "eval_CREDITCARDISSUER_f1": 0.0,
37
+ "eval_CREDITCARDNUMBER_f1": 0.11406096361848575,
38
+ "eval_CURRENCYCODE_f1": 0.0,
39
+ "eval_CURRENCYNAME_f1": 0.0,
40
+ "eval_CURRENCYSYMBOL_f1": 0.011152416356877323,
41
+ "eval_CURRENCY_f1": 0.0,
42
+ "eval_DATE_f1": 0.7136667979519495,
43
+ "eval_DOB_f1": 0.0,
44
+ "eval_EMAIL_f1": 0.9095074455899198,
45
+ "eval_ETHEREUMADDRESS_f1": 0.9118881118881119,
46
+ "eval_EYECOLOR_f1": 0.0,
47
+ "eval_FIRSTNAME_f1": 0.3152098037694873,
48
+ "eval_GENDER_f1": 0.0,
49
+ "eval_HEIGHT_f1": 0.0,
50
+ "eval_IBAN_f1": 0.8248337028824834,
51
+ "eval_IPV4_f1": 0.6785225718194254,
52
+ "eval_IPV6_f1": 0.419889502762431,
53
+ "eval_IP_f1": 0.0,
54
+ "eval_JOBAREA_f1": 0.0,
55
+ "eval_JOBTITLE_f1": 0.04747320061255742,
56
+ "eval_JOBTYPE_f1": 0.0,
57
+ "eval_LASTNAME_f1": 0.0167427701674277,
58
+ "eval_LITECOINADDRESS_f1": 0.09073724007561437,
59
+ "eval_MAC_f1": 0.6333333333333333,
60
+ "eval_MASKEDNUMBER_f1": 0.0011037527593818985,
61
+ "eval_MIDDLENAME_f1": 0.0,
62
+ "eval_NEARBYGPSCOORDINATE_f1": 0.9525222551928784,
63
+ "eval_ORDINALDIRECTION_f1": 0.0,
64
+ "eval_PASSWORD_f1": 0.6438152011922503,
65
+ "eval_PHONEIMEI_f1": 0.3917525773195876,
66
+ "eval_PHONENUMBER_f1": 0.2703045685279188,
67
+ "eval_PIN_f1": 0.0,
68
+ "eval_PREFIX_f1": 0.009852216748768471,
69
+ "eval_SECONDARYADDRESS_f1": 0.239450441609421,
70
+ "eval_SEX_f1": 0.0,
71
+ "eval_SSN_f1": 0.02197802197802198,
72
+ "eval_STATE_f1": 0.0,
73
+ "eval_STREET_f1": 0.027568922305764413,
74
+ "eval_TIME_f1": 0.555667001003009,
75
+ "eval_URL_f1": 0.9657980456026058,
76
+ "eval_USERAGENT_f1": 0.815668202764977,
77
+ "eval_USERNAME_f1": 0.04152712659075687,
78
+ "eval_VEHICLEVIN_f1": 0.39554317548746515,
79
+ "eval_VEHICLEVRM_f1": 0.010582010582010581,
80
+ "eval_ZIPCODE_f1": 0.018083182640144666,
81
+ "eval_loss": 0.5092686414718628,
82
+ "eval_overall_accuracy": 0.8498586556911224,
83
+ "eval_overall_f1": 0.2955823032934277,
84
+ "eval_overall_precision": 0.26884540578770555,
85
+ "eval_overall_recall": 0.3282245008094981,
86
+ "eval_runtime": 97.2896,
87
+ "eval_samples_per_second": 89.434,
88
+ "eval_steps_per_second": 2.796,
89
+ "step": 1088
90
+ },
91
+ {
92
+ "epoch": 1.38,
93
+ "learning_rate": 4.814247414783608e-05,
94
+ "loss": 0.4619,
95
+ "step": 1500
96
+ },
97
+ {
98
+ "epoch": 1.84,
99
+ "learning_rate": 4.3355036384527004e-05,
100
+ "loss": 0.2793,
101
+ "step": 2000
102
+ },
103
+ {
104
+ "epoch": 2.0,
105
+ "eval_ACCOUNTNAME_f1": 0.9684400360685302,
106
+ "eval_ACCOUNTNUMBER_f1": 0.87893864013267,
107
+ "eval_AGE_f1": 0.7560718057022174,
108
+ "eval_AMOUNT_f1": 0.3604240282685512,
109
+ "eval_BIC_f1": 0.7609427609427608,
110
+ "eval_BITCOINADDRESS_f1": 0.8715415019762845,
111
+ "eval_BUILDINGNUMBER_f1": 0.649155722326454,
112
+ "eval_CITY_f1": 0.4956011730205278,
113
+ "eval_COMPANYNAME_f1": 0.8028045574057844,
114
+ "eval_COUNTY_f1": 0.5558397271952259,
115
+ "eval_CREDITCARDCVV_f1": 0.775623268698061,
116
+ "eval_CREDITCARDISSUER_f1": 0.6575342465753425,
117
+ "eval_CREDITCARDNUMBER_f1": 0.5363469761759315,
118
+ "eval_CURRENCYCODE_f1": 0.128,
119
+ "eval_CURRENCYNAME_f1": 0.0,
120
+ "eval_CURRENCYSYMBOL_f1": 0.590990990990991,
121
+ "eval_CURRENCY_f1": 0.46710526315789475,
122
+ "eval_DATE_f1": 0.7730881738403678,
123
+ "eval_DOB_f1": 0.01858736059479554,
124
+ "eval_EMAIL_f1": 0.9838226482923906,
125
+ "eval_ETHEREUMADDRESS_f1": 0.9464788732394367,
126
+ "eval_EYECOLOR_f1": 0.4481605351170569,
127
+ "eval_FIRSTNAME_f1": 0.7689129052765417,
128
+ "eval_GENDER_f1": 0.5160075329566854,
129
+ "eval_HEIGHT_f1": 0.7445652173913043,
130
+ "eval_IBAN_f1": 0.923444976076555,
131
+ "eval_IPV4_f1": 0.822593476531424,
132
+ "eval_IPV6_f1": 0.8006644518272426,
133
+ "eval_IP_f1": 0.0,
134
+ "eval_JOBAREA_f1": 0.5588516746411483,
135
+ "eval_JOBTITLE_f1": 0.8711755233494364,
136
+ "eval_JOBTYPE_f1": 0.6552567237163814,
137
+ "eval_LASTNAME_f1": 0.6633663366336633,
138
+ "eval_LITECOINADDRESS_f1": 0.7055837563451777,
139
+ "eval_MAC_f1": 0.9315068493150684,
140
+ "eval_MASKEDNUMBER_f1": 0.038159371492704826,
141
+ "eval_MIDDLENAME_f1": 0.06608695652173913,
142
+ "eval_NEARBYGPSCOORDINATE_f1": 0.9954058192955589,
143
+ "eval_ORDINALDIRECTION_f1": 0.8827930174563591,
144
+ "eval_PASSWORD_f1": 0.9269949066213922,
145
+ "eval_PHONEIMEI_f1": 0.9692737430167597,
146
+ "eval_PHONENUMBER_f1": 0.8621399176954733,
147
+ "eval_PIN_f1": 0.14814814814814814,
148
+ "eval_PREFIX_f1": 0.8783216783216783,
149
+ "eval_SECONDARYADDRESS_f1": 0.9119830328738069,
150
+ "eval_SEX_f1": 0.9261744966442953,
151
+ "eval_SSN_f1": 0.8706998813760379,
152
+ "eval_STATE_f1": 0.6692975532754538,
153
+ "eval_STREET_f1": 0.7378455672068636,
154
+ "eval_TIME_f1": 0.9151943462897527,
155
+ "eval_URL_f1": 0.9885807504078303,
156
+ "eval_USERAGENT_f1": 0.9523809523809524,
157
+ "eval_USERNAME_f1": 0.8858654572940287,
158
+ "eval_VEHICLEVIN_f1": 0.8352272727272727,
159
+ "eval_VEHICLEVRM_f1": 0.8976377952755905,
160
+ "eval_ZIPCODE_f1": 0.6465661641541037,
161
+ "eval_loss": 0.19034649431705475,
162
+ "eval_overall_accuracy": 0.9308965476835646,
163
+ "eval_overall_f1": 0.7265048610632282,
164
+ "eval_overall_precision": 0.6973888870503359,
165
+ "eval_overall_recall": 0.7581579420759129,
166
+ "eval_runtime": 94.5565,
167
+ "eval_samples_per_second": 92.019,
168
+ "eval_steps_per_second": 2.877,
169
+ "step": 2176
170
+ },
171
+ {
172
+ "epoch": 2.3,
173
+ "learning_rate": 3.856759862121793e-05,
174
+ "loss": 0.2076,
175
+ "step": 2500
176
+ },
177
+ {
178
+ "epoch": 2.76,
179
+ "learning_rate": 3.3780160857908846e-05,
180
+ "loss": 0.1707,
181
+ "step": 3000
182
+ },
183
+ {
184
+ "epoch": 3.0,
185
+ "eval_ACCOUNTNAME_f1": 0.9702434625788998,
186
+ "eval_ACCOUNTNUMBER_f1": 0.9396325459317585,
187
+ "eval_AGE_f1": 0.8119658119658119,
188
+ "eval_AMOUNT_f1": 0.6101694915254238,
189
+ "eval_BIC_f1": 0.9297658862876254,
190
+ "eval_BITCOINADDRESS_f1": 0.9033570701932858,
191
+ "eval_BUILDINGNUMBER_f1": 0.7408726625111309,
192
+ "eval_CITY_f1": 0.6204772902232486,
193
+ "eval_COMPANYNAME_f1": 0.892193308550186,
194
+ "eval_COUNTY_f1": 0.7127659574468086,
195
+ "eval_CREDITCARDCVV_f1": 0.844559585492228,
196
+ "eval_CREDITCARDISSUER_f1": 0.9217970049916806,
197
+ "eval_CREDITCARDNUMBER_f1": 0.6982829108748978,
198
+ "eval_CURRENCYCODE_f1": 0.5379746835443038,
199
+ "eval_CURRENCYNAME_f1": 0.010582010582010581,
200
+ "eval_CURRENCYSYMBOL_f1": 0.6876737720111215,
201
+ "eval_CURRENCY_f1": 0.5504032258064515,
202
+ "eval_DATE_f1": 0.6125166444740345,
203
+ "eval_DOB_f1": 0.32593856655290104,
204
+ "eval_EMAIL_f1": 0.9891566265060241,
205
+ "eval_ETHEREUMADDRESS_f1": 0.9955947136563876,
206
+ "eval_EYECOLOR_f1": 0.6646884272997032,
207
+ "eval_FIRSTNAME_f1": 0.8357781753130591,
208
+ "eval_GENDER_f1": 0.753959873284055,
209
+ "eval_HEIGHT_f1": 0.8858695652173912,
210
+ "eval_IBAN_f1": 0.9430303030303031,
211
+ "eval_IPV4_f1": 0.8313349320543564,
212
+ "eval_IPV6_f1": 0.7993311036789298,
213
+ "eval_IP_f1": 0.0,
214
+ "eval_JOBAREA_f1": 0.8235294117647058,
215
+ "eval_JOBTITLE_f1": 0.9240506329113924,
216
+ "eval_JOBTYPE_f1": 0.8191304347826087,
217
+ "eval_LASTNAME_f1": 0.7503539405379895,
218
+ "eval_LITECOINADDRESS_f1": 0.7882037533512065,
219
+ "eval_MAC_f1": 0.9411764705882352,
220
+ "eval_MASKEDNUMBER_f1": 0.5129310344827586,
221
+ "eval_MIDDLENAME_f1": 0.4005102040816327,
222
+ "eval_NEARBYGPSCOORDINATE_f1": 0.9969418960244648,
223
+ "eval_ORDINALDIRECTION_f1": 0.9452054794520549,
224
+ "eval_PASSWORD_f1": 0.9618055555555555,
225
+ "eval_PHONEIMEI_f1": 0.9900142653352354,
226
+ "eval_PHONENUMBER_f1": 0.9451913133402274,
227
+ "eval_PIN_f1": 0.5017921146953406,
228
+ "eval_PREFIX_f1": 0.8958904109589041,
229
+ "eval_SECONDARYADDRESS_f1": 0.9347593582887699,
230
+ "eval_SEX_f1": 0.9406130268199233,
231
+ "eval_SSN_f1": 0.9523809523809523,
232
+ "eval_STATE_f1": 0.7643097643097643,
233
+ "eval_STREET_f1": 0.7746835443037975,
234
+ "eval_TIME_f1": 0.9496910856134158,
235
+ "eval_URL_f1": 0.9942857142857143,
236
+ "eval_USERAGENT_f1": 0.9713603818615751,
237
+ "eval_USERNAME_f1": 0.9273570324574962,
238
+ "eval_VEHICLEVIN_f1": 0.9047619047619049,
239
+ "eval_VEHICLEVRM_f1": 0.9645776566757492,
240
+ "eval_ZIPCODE_f1": 0.7386888273314866,
241
+ "eval_loss": 0.13880883157253265,
242
+ "eval_overall_accuracy": 0.9467036749520308,
243
+ "eval_overall_f1": 0.8000138386756387,
244
+ "eval_overall_precision": 0.7704404611181449,
245
+ "eval_overall_recall": 0.831948192120885,
246
+ "eval_runtime": 94.4623,
247
+ "eval_samples_per_second": 92.111,
248
+ "eval_steps_per_second": 2.879,
249
+ "step": 3264
250
+ },
251
+ {
252
+ "epoch": 3.22,
253
+ "learning_rate": 2.899272309459977e-05,
254
+ "loss": 0.1498,
255
+ "step": 3500
256
+ },
257
+ {
258
+ "epoch": 3.68,
259
+ "learning_rate": 2.4205285331290695e-05,
260
+ "loss": 0.1373,
261
+ "step": 4000
262
+ },
263
+ {
264
+ "epoch": 4.0,
265
+ "eval_ACCOUNTNAME_f1": 0.965085049239033,
266
+ "eval_ACCOUNTNUMBER_f1": 0.9510240427426536,
267
+ "eval_AGE_f1": 0.826271186440678,
268
+ "eval_AMOUNT_f1": 0.7169042769857433,
269
+ "eval_BIC_f1": 0.9591836734693878,
270
+ "eval_BITCOINADDRESS_f1": 0.9254341164453525,
271
+ "eval_BUILDINGNUMBER_f1": 0.8150873965041399,
272
+ "eval_CITY_f1": 0.7794612794612793,
273
+ "eval_COMPANYNAME_f1": 0.9147727272727273,
274
+ "eval_COUNTY_f1": 0.8059701492537313,
275
+ "eval_CREDITCARDCVV_f1": 0.8807785888077859,
276
+ "eval_CREDITCARDISSUER_f1": 0.9523809523809524,
277
+ "eval_CREDITCARDNUMBER_f1": 0.8006785411365565,
278
+ "eval_CURRENCYCODE_f1": 0.5655976676384841,
279
+ "eval_CURRENCYNAME_f1": 0.024896265560165973,
280
+ "eval_CURRENCYSYMBOL_f1": 0.7999999999999998,
281
+ "eval_CURRENCY_f1": 0.5676229508196721,
282
+ "eval_DATE_f1": 0.7858391608391608,
283
+ "eval_DOB_f1": 0.34248366013071896,
284
+ "eval_EMAIL_f1": 0.9909801563439566,
285
+ "eval_ETHEREUMADDRESS_f1": 0.9868613138686132,
286
+ "eval_EYECOLOR_f1": 0.7551622418879056,
287
+ "eval_FIRSTNAME_f1": 0.8609062170706007,
288
+ "eval_GENDER_f1": 0.8396793587174348,
289
+ "eval_HEIGHT_f1": 0.8980716253443526,
290
+ "eval_IBAN_f1": 0.977886977886978,
291
+ "eval_IPV4_f1": 0.8309409888357256,
292
+ "eval_IPV6_f1": 0.31789473684210523,
293
+ "eval_IP_f1": 0.027777777777777773,
294
+ "eval_JOBAREA_f1": 0.864297253634895,
295
+ "eval_JOBTITLE_f1": 0.9474535165723524,
296
+ "eval_JOBTYPE_f1": 0.8999999999999999,
297
+ "eval_LASTNAME_f1": 0.7812499999999999,
298
+ "eval_LITECOINADDRESS_f1": 0.8414985590778098,
299
+ "eval_MAC_f1": 0.9749430523917996,
300
+ "eval_MASKEDNUMBER_f1": 0.619105199516324,
301
+ "eval_MIDDLENAME_f1": 0.46172248803827753,
302
+ "eval_NEARBYGPSCOORDINATE_f1": 0.9969418960244648,
303
+ "eval_ORDINALDIRECTION_f1": 0.9519450800915331,
304
+ "eval_PASSWORD_f1": 0.9710780017528484,
305
+ "eval_PHONEIMEI_f1": 0.9914285714285714,
306
+ "eval_PHONENUMBER_f1": 0.9700103412616339,
307
+ "eval_PIN_f1": 0.6733333333333333,
308
+ "eval_PREFIX_f1": 0.9088416723783415,
309
+ "eval_SECONDARYADDRESS_f1": 0.9420600858369098,
310
+ "eval_SEX_f1": 0.9732408325074331,
311
+ "eval_SSN_f1": 0.9670886075949368,
312
+ "eval_STATE_f1": 0.83596214511041,
313
+ "eval_STREET_f1": 0.8493919550982227,
314
+ "eval_TIME_f1": 0.944153577661431,
315
+ "eval_URL_f1": 0.9942763695829927,
316
+ "eval_USERAGENT_f1": 0.9618138424821001,
317
+ "eval_USERNAME_f1": 0.9486780715396579,
318
+ "eval_VEHICLEVIN_f1": 0.9838187702265372,
319
+ "eval_VEHICLEVRM_f1": 0.9672131147540984,
320
+ "eval_ZIPCODE_f1": 0.8092835519677094,
321
+ "eval_loss": 0.11968772113323212,
322
+ "eval_overall_accuracy": 0.9509308218475825,
323
+ "eval_overall_f1": 0.8173824304787822,
324
+ "eval_overall_precision": 0.7751290322580645,
325
+ "eval_overall_recall": 0.8645080050368771,
326
+ "eval_runtime": 95.4105,
327
+ "eval_samples_per_second": 91.195,
328
+ "eval_steps_per_second": 2.851,
329
+ "step": 4352
330
+ },
331
+ {
332
+ "epoch": 4.14,
333
+ "learning_rate": 1.9417847567981616e-05,
334
+ "loss": 0.1263,
335
+ "step": 4500
336
+ },
337
+ {
338
+ "epoch": 4.6,
339
+ "learning_rate": 1.4630409804672541e-05,
340
+ "loss": 0.1202,
341
+ "step": 5000
342
+ },
343
+ {
344
+ "epoch": 5.0,
345
+ "eval_ACCOUNTNAME_f1": 0.9720468890892696,
346
+ "eval_ACCOUNTNUMBER_f1": 0.9634255129348795,
347
+ "eval_AGE_f1": 0.835978835978836,
348
+ "eval_AMOUNT_f1": 0.74234573716439,
349
+ "eval_BIC_f1": 0.975609756097561,
350
+ "eval_BITCOINADDRESS_f1": 0.9326530612244899,
351
+ "eval_BUILDINGNUMBER_f1": 0.8267942583732059,
352
+ "eval_CITY_f1": 0.8031088082901555,
353
+ "eval_COMPANYNAME_f1": 0.9134157944814462,
354
+ "eval_COUNTY_f1": 0.8403508771929824,
355
+ "eval_CREDITCARDCVV_f1": 0.8792270531400966,
356
+ "eval_CREDITCARDISSUER_f1": 0.9659643435980552,
357
+ "eval_CREDITCARDNUMBER_f1": 0.7957181088314006,
358
+ "eval_CURRENCYCODE_f1": 0.6158536585365854,
359
+ "eval_CURRENCYNAME_f1": 0.016736401673640166,
360
+ "eval_CURRENCYSYMBOL_f1": 0.8131868131868132,
361
+ "eval_CURRENCY_f1": 0.5723076923076923,
362
+ "eval_DATE_f1": 0.7913669064748201,
363
+ "eval_DOB_f1": 0.4300822561692127,
364
+ "eval_EMAIL_f1": 0.9927710843373494,
365
+ "eval_ETHEREUMADDRESS_f1": 0.9941348973607038,
366
+ "eval_EYECOLOR_f1": 0.7543859649122807,
367
+ "eval_FIRSTNAME_f1": 0.8658600736454498,
368
+ "eval_GENDER_f1": 0.8870803662258392,
369
+ "eval_HEIGHT_f1": 0.9120879120879121,
370
+ "eval_IBAN_f1": 0.9694749694749695,
371
+ "eval_IPV4_f1": 0.8361310951239009,
372
+ "eval_IPV6_f1": 0.7007633587786259,
373
+ "eval_IP_f1": 0.013675213675213675,
374
+ "eval_JOBAREA_f1": 0.9108061749571184,
375
+ "eval_JOBTITLE_f1": 0.962295081967213,
376
+ "eval_JOBTYPE_f1": 0.9125683060109289,
377
+ "eval_LASTNAME_f1": 0.7782898105478752,
378
+ "eval_LITECOINADDRESS_f1": 0.84593837535014,
379
+ "eval_MAC_f1": 0.9749430523917996,
380
+ "eval_MASKEDNUMBER_f1": 0.676957001102536,
381
+ "eval_MIDDLENAME_f1": 0.49435665914221216,
382
+ "eval_NEARBYGPSCOORDINATE_f1": 0.9984686064318529,
383
+ "eval_ORDINALDIRECTION_f1": 0.9519450800915331,
384
+ "eval_PASSWORD_f1": 0.9753521126760563,
385
+ "eval_PHONEIMEI_f1": 0.9899856938483547,
386
+ "eval_PHONENUMBER_f1": 0.967280163599182,
387
+ "eval_PIN_f1": 0.7647058823529412,
388
+ "eval_PREFIX_f1": 0.911461908030199,
389
+ "eval_SECONDARYADDRESS_f1": 0.9483870967741935,
390
+ "eval_SEX_f1": 0.9759999999999999,
391
+ "eval_SSN_f1": 0.9770992366412213,
392
+ "eval_STATE_f1": 0.8587570621468926,
393
+ "eval_STREET_f1": 0.8590102707749767,
394
+ "eval_TIME_f1": 0.9526315789473685,
395
+ "eval_URL_f1": 0.9975429975429976,
396
+ "eval_USERAGENT_f1": 0.9820359281437125,
397
+ "eval_USERNAME_f1": 0.9546875000000001,
398
+ "eval_VEHICLEVIN_f1": 0.9870967741935484,
399
+ "eval_VEHICLEVRM_f1": 0.9916434540389973,
400
+ "eval_ZIPCODE_f1": 0.8132530120481928,
401
+ "eval_loss": 0.11061251908540726,
402
+ "eval_overall_accuracy": 0.9564102939668683,
403
+ "eval_overall_f1": 0.8521733068423438,
404
+ "eval_overall_precision": 0.82642057938681,
405
+ "eval_overall_recall": 0.879582658751574,
406
+ "eval_runtime": 94.212,
407
+ "eval_samples_per_second": 92.356,
408
+ "eval_steps_per_second": 2.887,
409
+ "step": 5440
410
+ },
411
+ {
412
+ "epoch": 5.06,
413
+ "learning_rate": 9.842972041363464e-06,
414
+ "loss": 0.113,
415
+ "step": 5500
416
+ },
417
+ {
418
+ "epoch": 5.51,
419
+ "learning_rate": 5.055534278054386e-06,
420
+ "loss": 0.1049,
421
+ "step": 6000
422
+ },
423
+ {
424
+ "epoch": 5.97,
425
+ "learning_rate": 2.6809651474530835e-07,
426
+ "loss": 0.1065,
427
+ "step": 6500
428
+ },
429
+ {
430
+ "epoch": 6.0,
431
+ "eval_ACCOUNTNAME_f1": 0.9712230215827338,
432
+ "eval_ACCOUNTNUMBER_f1": 0.967741935483871,
433
+ "eval_AGE_f1": 0.8432203389830508,
434
+ "eval_AMOUNT_f1": 0.7929342492639844,
435
+ "eval_BIC_f1": 0.9688581314878892,
436
+ "eval_BITCOINADDRESS_f1": 0.9342915811088296,
437
+ "eval_BUILDINGNUMBER_f1": 0.8405253283302063,
438
+ "eval_CITY_f1": 0.8139337298215804,
439
+ "eval_COMPANYNAME_f1": 0.9310344827586207,
440
+ "eval_COUNTY_f1": 0.8406304728546411,
441
+ "eval_CREDITCARDCVV_f1": 0.8888888888888888,
442
+ "eval_CREDITCARDISSUER_f1": 0.9660743134087239,
443
+ "eval_CREDITCARDNUMBER_f1": 0.8403967538322814,
444
+ "eval_CURRENCYCODE_f1": 0.6556291390728476,
445
+ "eval_CURRENCYNAME_f1": 0.01818181818181818,
446
+ "eval_CURRENCYSYMBOL_f1": 0.8175985334555453,
447
+ "eval_CURRENCY_f1": 0.5967741935483872,
448
+ "eval_DATE_f1": 0.7857793983591613,
449
+ "eval_DOB_f1": 0.46357615894039733,
450
+ "eval_EMAIL_f1": 0.9927710843373494,
451
+ "eval_ETHEREUMADDRESS_f1": 0.9941348973607038,
452
+ "eval_EYECOLOR_f1": 0.7859237536656891,
453
+ "eval_FIRSTNAME_f1": 0.8699042892591281,
454
+ "eval_GENDER_f1": 0.8945233265720081,
455
+ "eval_HEIGHT_f1": 0.9226519337016574,
456
+ "eval_IBAN_f1": 0.972972972972973,
457
+ "eval_IPV4_f1": 0.8345323741007193,
458
+ "eval_IPV6_f1": 0.4659231722428749,
459
+ "eval_IP_f1": 0.049665711556829036,
460
+ "eval_JOBAREA_f1": 0.9130801687763713,
461
+ "eval_JOBTITLE_f1": 0.9599345870809485,
462
+ "eval_JOBTYPE_f1": 0.930316742081448,
463
+ "eval_LASTNAME_f1": 0.8015833745670461,
464
+ "eval_LITECOINADDRESS_f1": 0.848314606741573,
465
+ "eval_MAC_f1": 0.9817351598173517,
466
+ "eval_MASKEDNUMBER_f1": 0.7049180327868851,
467
+ "eval_MIDDLENAME_f1": 0.5005847953216374,
468
+ "eval_NEARBYGPSCOORDINATE_f1": 0.9969418960244648,
469
+ "eval_ORDINALDIRECTION_f1": 0.9519450800915331,
470
+ "eval_PASSWORD_f1": 0.9780123131046614,
471
+ "eval_PHONEIMEI_f1": 0.9928469241773962,
472
+ "eval_PHONENUMBER_f1": 0.9751552795031055,
473
+ "eval_PIN_f1": 0.7524752475247525,
474
+ "eval_PREFIX_f1": 0.9120879120879122,
475
+ "eval_SECONDARYADDRESS_f1": 0.9473684210526315,
476
+ "eval_SEX_f1": 0.976976976976977,
477
+ "eval_SSN_f1": 0.9770992366412213,
478
+ "eval_STATE_f1": 0.8680445151033387,
479
+ "eval_STREET_f1": 0.8676748582230623,
480
+ "eval_TIME_f1": 0.951627088830255,
481
+ "eval_URL_f1": 0.9975429975429976,
482
+ "eval_USERAGENT_f1": 0.9843937575030013,
483
+ "eval_USERNAME_f1": 0.9669291338582677,
484
+ "eval_VEHICLEVIN_f1": 0.977491961414791,
485
+ "eval_VEHICLEVRM_f1": 0.9888268156424581,
486
+ "eval_ZIPCODE_f1": 0.8203045685279189,
487
+ "eval_loss": 0.10785039514303207,
488
+ "eval_overall_accuracy": 0.9559518404054311,
489
+ "eval_overall_f1": 0.8471647350993378,
490
+ "eval_overall_precision": 0.8135744807711418,
491
+ "eval_overall_recall": 0.8836481381543443,
492
+ "eval_runtime": 94.7688,
493
+ "eval_samples_per_second": 91.813,
494
+ "eval_steps_per_second": 2.87,
495
+ "step": 6528
496
+ },
497
+ {
498
+ "epoch": 6.0,
499
+ "step": 6528,
500
+ "total_flos": 1.458680878857888e+16,
501
+ "train_loss": 0.4378688358427847,
502
+ "train_runtime": 4446.6577,
503
+ "train_samples_per_second": 46.957,
504
+ "train_steps_per_second": 1.468
505
+ },
506
+ {
507
+ "epoch": 6.0,
508
+ "eval_ACCOUNTNAME_f1": 0.9712230215827338,
509
+ "eval_ACCOUNTNUMBER_f1": 0.967741935483871,
510
+ "eval_AGE_f1": 0.8432203389830508,
511
+ "eval_AMOUNT_f1": 0.7929342492639844,
512
+ "eval_BIC_f1": 0.9688581314878892,
513
+ "eval_BITCOINADDRESS_f1": 0.9342915811088296,
514
+ "eval_BUILDINGNUMBER_f1": 0.8405253283302063,
515
+ "eval_CITY_f1": 0.8139337298215804,
516
+ "eval_COMPANYNAME_f1": 0.9310344827586207,
517
+ "eval_COUNTY_f1": 0.8406304728546411,
518
+ "eval_CREDITCARDCVV_f1": 0.8888888888888888,
519
+ "eval_CREDITCARDISSUER_f1": 0.9660743134087239,
520
+ "eval_CREDITCARDNUMBER_f1": 0.8403967538322814,
521
+ "eval_CURRENCYCODE_f1": 0.6556291390728476,
522
+ "eval_CURRENCYNAME_f1": 0.01818181818181818,
523
+ "eval_CURRENCYSYMBOL_f1": 0.8175985334555453,
524
+ "eval_CURRENCY_f1": 0.5967741935483872,
525
+ "eval_DATE_f1": 0.7857793983591613,
526
+ "eval_DOB_f1": 0.46357615894039733,
527
+ "eval_EMAIL_f1": 0.9927710843373494,
528
+ "eval_ETHEREUMADDRESS_f1": 0.9941348973607038,
529
+ "eval_EYECOLOR_f1": 0.7859237536656891,
530
+ "eval_FIRSTNAME_f1": 0.8699042892591281,
531
+ "eval_GENDER_f1": 0.8945233265720081,
532
+ "eval_HEIGHT_f1": 0.9226519337016574,
533
+ "eval_IBAN_f1": 0.972972972972973,
534
+ "eval_IPV4_f1": 0.8345323741007193,
535
+ "eval_IPV6_f1": 0.4659231722428749,
536
+ "eval_IP_f1": 0.049665711556829036,
537
+ "eval_JOBAREA_f1": 0.9130801687763713,
538
+ "eval_JOBTITLE_f1": 0.9599345870809485,
539
+ "eval_JOBTYPE_f1": 0.930316742081448,
540
+ "eval_LASTNAME_f1": 0.8015833745670461,
541
+ "eval_LITECOINADDRESS_f1": 0.848314606741573,
542
+ "eval_MAC_f1": 0.9817351598173517,
543
+ "eval_MASKEDNUMBER_f1": 0.7049180327868851,
544
+ "eval_MIDDLENAME_f1": 0.5005847953216374,
545
+ "eval_NEARBYGPSCOORDINATE_f1": 0.9969418960244648,
546
+ "eval_ORDINALDIRECTION_f1": 0.9519450800915331,
547
+ "eval_PASSWORD_f1": 0.9780123131046614,
548
+ "eval_PHONEIMEI_f1": 0.9928469241773962,
549
+ "eval_PHONENUMBER_f1": 0.9751552795031055,
550
+ "eval_PIN_f1": 0.7524752475247525,
551
+ "eval_PREFIX_f1": 0.9120879120879122,
552
+ "eval_SECONDARYADDRESS_f1": 0.9473684210526315,
553
+ "eval_SEX_f1": 0.976976976976977,
554
+ "eval_SSN_f1": 0.9770992366412213,
555
+ "eval_STATE_f1": 0.8680445151033387,
556
+ "eval_STREET_f1": 0.8676748582230623,
557
+ "eval_TIME_f1": 0.951627088830255,
558
+ "eval_URL_f1": 0.9975429975429976,
559
+ "eval_USERAGENT_f1": 0.9843937575030013,
560
+ "eval_USERNAME_f1": 0.9669291338582677,
561
+ "eval_VEHICLEVIN_f1": 0.977491961414791,
562
+ "eval_VEHICLEVRM_f1": 0.9888268156424581,
563
+ "eval_ZIPCODE_f1": 0.8203045685279189,
564
+ "eval_loss": 0.10785039514303207,
565
+ "eval_overall_accuracy": 0.9559518404054311,
566
+ "eval_overall_f1": 0.8471647350993378,
567
+ "eval_overall_precision": 0.8135744807711418,
568
+ "eval_overall_recall": 0.8836481381543443,
569
+ "eval_runtime": 95.1945,
570
+ "eval_samples_per_second": 91.402,
571
+ "eval_steps_per_second": 2.857,
572
+ "step": 6528
573
+ }
574
+ ],
575
+ "logging_steps": 500,
576
+ "max_steps": 6528,
577
+ "num_train_epochs": 6,
578
+ "save_steps": 500,
579
+ "total_flos": 1.458680878857888e+16,
580
+ "trial_name": null,
581
+ "trial_params": null
582
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96293739ce12e11cfb175e109cbadceee8fe44bf16f202fc0cf231b2368a1f25
3
+ size 4664
vocab.txt ADDED
The diff for this file is too large to render. See raw diff