Training in progress, step 1000
Browse files- config.json +143 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,143 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "I-BOD",
|
13 |
+
"1": "I-BUILDING",
|
14 |
+
"2": "I-CARDISSUER",
|
15 |
+
"3": "I-CITY",
|
16 |
+
"4": "I-COUNTRY",
|
17 |
+
"5": "I-DATE",
|
18 |
+
"6": "I-DRIVERLICENSE",
|
19 |
+
"7": "I-EMAIL",
|
20 |
+
"8": "I-GEOCOORD",
|
21 |
+
"9": "I-GIVENNAME1",
|
22 |
+
"10": "I-GIVENNAME2",
|
23 |
+
"11": "I-IDCARD",
|
24 |
+
"12": "I-IP",
|
25 |
+
"13": "I-LASTNAME1",
|
26 |
+
"14": "I-LASTNAME2",
|
27 |
+
"15": "I-LASTNAME3",
|
28 |
+
"16": "I-PASS",
|
29 |
+
"17": "I-PASSPORT",
|
30 |
+
"18": "I-POSTCODE",
|
31 |
+
"19": "I-SECADDRESS",
|
32 |
+
"20": "I-SEX",
|
33 |
+
"21": "I-SOCIALNUMBER",
|
34 |
+
"22": "I-STATE",
|
35 |
+
"23": "I-STREET",
|
36 |
+
"24": "I-TEL",
|
37 |
+
"25": "I-TIME",
|
38 |
+
"26": "I-TITLE",
|
39 |
+
"27": "I-USERNAME",
|
40 |
+
"28": "B-BOD",
|
41 |
+
"29": "B-BUILDING",
|
42 |
+
"30": "B-CARDISSUER",
|
43 |
+
"31": "B-CITY",
|
44 |
+
"32": "B-COUNTRY",
|
45 |
+
"33": "B-DATE",
|
46 |
+
"34": "B-DRIVERLICENSE",
|
47 |
+
"35": "B-EMAIL",
|
48 |
+
"36": "B-GEOCOORD",
|
49 |
+
"37": "B-GIVENNAME1",
|
50 |
+
"38": "B-GIVENNAME2",
|
51 |
+
"39": "B-IDCARD",
|
52 |
+
"40": "B-IP",
|
53 |
+
"41": "B-LASTNAME1",
|
54 |
+
"42": "B-LASTNAME2",
|
55 |
+
"43": "B-LASTNAME3",
|
56 |
+
"44": "B-PASS",
|
57 |
+
"45": "B-PASSPORT",
|
58 |
+
"46": "B-POSTCODE",
|
59 |
+
"47": "B-SECADDRESS",
|
60 |
+
"48": "B-SEX",
|
61 |
+
"49": "B-SOCIALNUMBER",
|
62 |
+
"50": "B-STATE",
|
63 |
+
"51": "B-STREET",
|
64 |
+
"52": "B-TEL",
|
65 |
+
"53": "B-TIME",
|
66 |
+
"54": "B-TITLE",
|
67 |
+
"55": "B-USERNAME",
|
68 |
+
"56": "O"
|
69 |
+
},
|
70 |
+
"initializer_range": 0.02,
|
71 |
+
"label2id": {
|
72 |
+
"LABEL_0": 0,
|
73 |
+
"LABEL_1": 1,
|
74 |
+
"LABEL_10": 10,
|
75 |
+
"LABEL_11": 11,
|
76 |
+
"LABEL_12": 12,
|
77 |
+
"LABEL_13": 13,
|
78 |
+
"LABEL_14": 14,
|
79 |
+
"LABEL_15": 15,
|
80 |
+
"LABEL_16": 16,
|
81 |
+
"LABEL_17": 17,
|
82 |
+
"LABEL_18": 18,
|
83 |
+
"LABEL_19": 19,
|
84 |
+
"LABEL_2": 2,
|
85 |
+
"LABEL_20": 20,
|
86 |
+
"LABEL_21": 21,
|
87 |
+
"LABEL_22": 22,
|
88 |
+
"LABEL_23": 23,
|
89 |
+
"LABEL_24": 24,
|
90 |
+
"LABEL_25": 25,
|
91 |
+
"LABEL_26": 26,
|
92 |
+
"LABEL_27": 27,
|
93 |
+
"LABEL_28": 28,
|
94 |
+
"LABEL_29": 29,
|
95 |
+
"LABEL_3": 3,
|
96 |
+
"LABEL_30": 30,
|
97 |
+
"LABEL_31": 31,
|
98 |
+
"LABEL_32": 32,
|
99 |
+
"LABEL_33": 33,
|
100 |
+
"LABEL_34": 34,
|
101 |
+
"LABEL_35": 35,
|
102 |
+
"LABEL_36": 36,
|
103 |
+
"LABEL_37": 37,
|
104 |
+
"LABEL_38": 38,
|
105 |
+
"LABEL_39": 39,
|
106 |
+
"LABEL_4": 4,
|
107 |
+
"LABEL_40": 40,
|
108 |
+
"LABEL_41": 41,
|
109 |
+
"LABEL_42": 42,
|
110 |
+
"LABEL_43": 43,
|
111 |
+
"LABEL_44": 44,
|
112 |
+
"LABEL_45": 45,
|
113 |
+
"LABEL_46": 46,
|
114 |
+
"LABEL_47": 47,
|
115 |
+
"LABEL_48": 48,
|
116 |
+
"LABEL_49": 49,
|
117 |
+
"LABEL_5": 5,
|
118 |
+
"LABEL_50": 50,
|
119 |
+
"LABEL_51": 51,
|
120 |
+
"LABEL_52": 52,
|
121 |
+
"LABEL_53": 53,
|
122 |
+
"LABEL_54": 54,
|
123 |
+
"LABEL_55": 55,
|
124 |
+
"LABEL_56": 56,
|
125 |
+
"LABEL_6": 6,
|
126 |
+
"LABEL_7": 7,
|
127 |
+
"LABEL_8": 8,
|
128 |
+
"LABEL_9": 9
|
129 |
+
},
|
130 |
+
"max_position_embeddings": 512,
|
131 |
+
"model_type": "distilbert",
|
132 |
+
"n_heads": 12,
|
133 |
+
"n_layers": 6,
|
134 |
+
"output_past": true,
|
135 |
+
"pad_token_id": 0,
|
136 |
+
"qa_dropout": 0.1,
|
137 |
+
"seq_classif_dropout": 0.2,
|
138 |
+
"sinusoidal_pos_embds": false,
|
139 |
+
"tie_weights_": true,
|
140 |
+
"torch_dtype": "float32",
|
141 |
+
"transformers_version": "4.41.2",
|
142 |
+
"vocab_size": 28996
|
143 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe6fca8cfad2c802406e83f0381cc14f526c16d5c4b3cd073b2f0c48fb5f5546
|
3 |
+
size 260951324
|
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 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3da5be453baee050a1bb96b811919ea59413f9860dbef6c611f886414351fba2
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|