Upload 8 files
Browse files- .gitattributes +1 -0
- config.json +101 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- validation_results +67 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "B-AGE",
|
| 14 |
+
"1": "B-BUILDINGNUM",
|
| 15 |
+
"2": "B-CITY",
|
| 16 |
+
"3": "B-CREDITCARDNUMBER",
|
| 17 |
+
"4": "B-DATE",
|
| 18 |
+
"5": "B-DRIVERLICENSENUM",
|
| 19 |
+
"6": "B-EMAIL",
|
| 20 |
+
"7": "B-GENDER",
|
| 21 |
+
"8": "B-GIVENNAME",
|
| 22 |
+
"9": "B-IDCARDNUM",
|
| 23 |
+
"10": "B-PASSPORTNUM",
|
| 24 |
+
"11": "B-SEX",
|
| 25 |
+
"12": "B-SOCIALNUM",
|
| 26 |
+
"13": "B-STREET",
|
| 27 |
+
"14": "B-SURNAME",
|
| 28 |
+
"15": "B-TAXNUM",
|
| 29 |
+
"16": "B-TELEPHONENUM",
|
| 30 |
+
"17": "B-TIME",
|
| 31 |
+
"18": "B-TITLE",
|
| 32 |
+
"19": "B-ZIPCODE",
|
| 33 |
+
"20": "I-BUILDINGNUM",
|
| 34 |
+
"21": "I-CITY",
|
| 35 |
+
"22": "I-DATE",
|
| 36 |
+
"23": "I-DRIVERLICENSENUM",
|
| 37 |
+
"24": "I-EMAIL",
|
| 38 |
+
"25": "I-GIVENNAME",
|
| 39 |
+
"26": "I-SOCIALNUM",
|
| 40 |
+
"27": "I-STREET",
|
| 41 |
+
"28": "I-SURNAME",
|
| 42 |
+
"29": "I-TAXNUM",
|
| 43 |
+
"30": "I-TELEPHONENUM",
|
| 44 |
+
"31": "I-TIME",
|
| 45 |
+
"32": "I-TITLE",
|
| 46 |
+
"33": "I-ZIPCODE",
|
| 47 |
+
"34": "O"
|
| 48 |
+
},
|
| 49 |
+
"initializer_range": 0.02,
|
| 50 |
+
"intermediate_size": 3072,
|
| 51 |
+
"label2id": {
|
| 52 |
+
"B-AGE": 0,
|
| 53 |
+
"B-BUILDINGNUM": 1,
|
| 54 |
+
"B-CITY": 2,
|
| 55 |
+
"B-CREDITCARDNUMBER": 3,
|
| 56 |
+
"B-DATE": 4,
|
| 57 |
+
"B-DRIVERLICENSENUM": 5,
|
| 58 |
+
"B-EMAIL": 6,
|
| 59 |
+
"B-GENDER": 7,
|
| 60 |
+
"B-GIVENNAME": 8,
|
| 61 |
+
"B-IDCARDNUM": 9,
|
| 62 |
+
"B-PASSPORTNUM": 10,
|
| 63 |
+
"B-SEX": 11,
|
| 64 |
+
"B-SOCIALNUM": 12,
|
| 65 |
+
"B-STREET": 13,
|
| 66 |
+
"B-SURNAME": 14,
|
| 67 |
+
"B-TAXNUM": 15,
|
| 68 |
+
"B-TELEPHONENUM": 16,
|
| 69 |
+
"B-TIME": 17,
|
| 70 |
+
"B-TITLE": 18,
|
| 71 |
+
"B-ZIPCODE": 19,
|
| 72 |
+
"I-BUILDINGNUM": 20,
|
| 73 |
+
"I-CITY": 21,
|
| 74 |
+
"I-DATE": 22,
|
| 75 |
+
"I-DRIVERLICENSENUM": 23,
|
| 76 |
+
"I-EMAIL": 24,
|
| 77 |
+
"I-GIVENNAME": 25,
|
| 78 |
+
"I-SOCIALNUM": 26,
|
| 79 |
+
"I-STREET": 27,
|
| 80 |
+
"I-SURNAME": 28,
|
| 81 |
+
"I-TAXNUM": 29,
|
| 82 |
+
"I-TELEPHONENUM": 30,
|
| 83 |
+
"I-TIME": 31,
|
| 84 |
+
"I-TITLE": 32,
|
| 85 |
+
"I-ZIPCODE": 33,
|
| 86 |
+
"O": 34
|
| 87 |
+
},
|
| 88 |
+
"layer_norm_eps": 1e-05,
|
| 89 |
+
"max_position_embeddings": 514,
|
| 90 |
+
"model_type": "xlm-roberta",
|
| 91 |
+
"num_attention_heads": 12,
|
| 92 |
+
"num_hidden_layers": 12,
|
| 93 |
+
"output_past": true,
|
| 94 |
+
"pad_token_id": 1,
|
| 95 |
+
"position_embedding_type": "absolute",
|
| 96 |
+
"torch_dtype": "float32",
|
| 97 |
+
"transformers_version": "4.55.2",
|
| 98 |
+
"type_vocab_size": 1,
|
| 99 |
+
"use_cache": true,
|
| 100 |
+
"vocab_size": 250002
|
| 101 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2cbf91cb9f92094c06ea0bd5eb1c86897e95f3285431b230d80fc6e153623aa
|
| 3 |
+
size 1109943940
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
|
| 3 |
+
size 17082832
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e91f1ed6691f27df72bf4ba20fefb2691742dddc41bc8d8243a22463632e0aa6
|
| 3 |
+
size 5713
|
validation_results
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
precision recall f1-score support
|
| 2 |
+
|
| 3 |
+
AGE 0.9670 0.9870 0.9769 4217
|
| 4 |
+
BUILDINGNUM 0.9791 0.9738 0.9764 7830
|
| 5 |
+
CITY 0.9618 0.9715 0.9666 13260
|
| 6 |
+
CREDITCARDNUMBER 0.9795 0.9869 0.9832 1837
|
| 7 |
+
DATE 0.9993 0.9996 0.9995 10101
|
| 8 |
+
DRIVERLICENSENUM 0.9109 0.8052 0.8548 1663
|
| 9 |
+
EMAIL 0.9998 0.9998 0.9998 9994
|
| 10 |
+
GENDER 0.7854 0.8763 0.8284 1520
|
| 11 |
+
GIVENNAME 0.9593 0.9740 0.9666 62085
|
| 12 |
+
IDCARDNUM 0.8943 0.9426 0.9178 6782
|
| 13 |
+
PASSPORTNUM 0.9042 0.8525 0.8776 3133
|
| 14 |
+
SEX 0.8840 0.8004 0.8401 1904
|
| 15 |
+
SOCIALNUM 0.8714 0.9442 0.9063 1737
|
| 16 |
+
STREET 0.9814 0.9708 0.9761 8866
|
| 17 |
+
SURNAME 0.8609 0.8308 0.8456 24001
|
| 18 |
+
TAXNUM 0.9768 0.9118 0.9432 2121
|
| 19 |
+
TELEPHONENUM 0.9969 0.9978 0.9973 13355
|
| 20 |
+
TIME 0.9993 0.9999 0.9996 10637
|
| 21 |
+
TITLE 0.9877 0.9936 0.9906 7019
|
| 22 |
+
ZIPCODE 0.9678 0.9719 0.9698 3243
|
| 23 |
+
|
| 24 |
+
micro avg 0.9536 0.9550 0.9543 195305
|
| 25 |
+
macro avg 0.9433 0.9395 0.9408 195305
|
| 26 |
+
weighted avg 0.9533 0.9550 0.9540 195305
|
| 27 |
+
|
| 28 |
+
precision recall f1-score support
|
| 29 |
+
|
| 30 |
+
B-AGE 0.9670 0.9870 0.9769 4217
|
| 31 |
+
B-BUILDINGNUM 0.9792 0.9739 0.9766 7830
|
| 32 |
+
B-CITY 0.9644 0.9741 0.9692 13260
|
| 33 |
+
B-CREDITCARDNUMBER 0.9795 0.9869 0.9832 1837
|
| 34 |
+
B-DATE 0.9994 0.9997 0.9996 10101
|
| 35 |
+
B-DRIVERLICENSENUM 0.9116 0.8058 0.8554 1663
|
| 36 |
+
B-EMAIL 0.9998 0.9998 0.9998 9994
|
| 37 |
+
B-GENDER 0.7854 0.8763 0.8284 1520
|
| 38 |
+
B-GIVENNAME 0.9745 0.9894 0.9819 62085
|
| 39 |
+
B-IDCARDNUM 0.8943 0.9426 0.9178 6782
|
| 40 |
+
B-PASSPORTNUM 0.9042 0.8525 0.8776 3133
|
| 41 |
+
B-SEX 0.8840 0.8004 0.8401 1904
|
| 42 |
+
B-SOCIALNUM 0.8730 0.9459 0.9080 1737
|
| 43 |
+
B-STREET 0.9840 0.9734 0.9787 8866
|
| 44 |
+
B-SURNAME 0.8622 0.8322 0.8469 24001
|
| 45 |
+
B-TAXNUM 0.9773 0.9123 0.9437 2121
|
| 46 |
+
B-TELEPHONENUM 0.9983 0.9991 0.9987 13355
|
| 47 |
+
B-TIME 0.9993 0.9999 0.9996 10637
|
| 48 |
+
B-TITLE 0.9877 0.9936 0.9906 7019
|
| 49 |
+
B-ZIPCODE 0.9681 0.9722 0.9702 3243
|
| 50 |
+
I-BUILDINGNUM 0.7500 1.0000 0.8571 12
|
| 51 |
+
I-CITY 0.9730 0.9803 0.9766 2386
|
| 52 |
+
I-DATE 0.9997 0.9993 0.9995 3072
|
| 53 |
+
I-DRIVERLICENSENUM 0.9936 0.9873 0.9905 158
|
| 54 |
+
I-EMAIL 1.0000 1.0000 1.0000 42
|
| 55 |
+
I-GIVENNAME 0.9207 0.9517 0.9359 7951
|
| 56 |
+
I-SOCIALNUM 1.0000 0.9719 0.9858 285
|
| 57 |
+
I-STREET 0.9777 0.9806 0.9791 2418
|
| 58 |
+
I-SURNAME 0.9303 0.8746 0.9016 5009
|
| 59 |
+
I-TAXNUM 0.9832 0.9915 0.9873 236
|
| 60 |
+
I-TELEPHONENUM 0.9946 0.9985 0.9966 5363
|
| 61 |
+
I-TIME 0.9964 1.0000 0.9982 546
|
| 62 |
+
I-ZIPCODE 0.9570 1.0000 0.9780 178
|
| 63 |
+
O 0.9983 0.9981 0.9982 1255145
|
| 64 |
+
|
| 65 |
+
accuracy 0.9924 1478106
|
| 66 |
+
macro avg 0.9520 0.9574 0.9537 1478106
|
| 67 |
+
weighted avg 0.9924 0.9924 0.9923 1478106
|