Upload 11 files
Browse files- config.json +255 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +159 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,255 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-multilingual-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": "O",
|
13 |
+
"1": "B-ORDINALDIRECTION",
|
14 |
+
"2": "B-NEARBYGPSCOORDINATE",
|
15 |
+
"3": "I-NEARBYGPSCOORDINATE",
|
16 |
+
"4": "B-PREFIX",
|
17 |
+
"5": "I-PREFIX",
|
18 |
+
"6": "B-LASTNAME",
|
19 |
+
"7": "I-LASTNAME",
|
20 |
+
"8": "B-SECONDARYADDRESS",
|
21 |
+
"9": "I-SECONDARYADDRESS",
|
22 |
+
"10": "B-PHONENUMBER",
|
23 |
+
"11": "I-PHONENUMBER",
|
24 |
+
"12": "B-JOBTITLE",
|
25 |
+
"13": "I-JOBTITLE",
|
26 |
+
"14": "B-BIC",
|
27 |
+
"15": "I-BIC",
|
28 |
+
"16": "B-IBAN",
|
29 |
+
"17": "I-IBAN",
|
30 |
+
"18": "B-CURRENCYNAME",
|
31 |
+
"19": "I-CURRENCYNAME",
|
32 |
+
"20": "B-CURRENCYSYMBOL",
|
33 |
+
"21": "I-CURRENCYSYMBOL",
|
34 |
+
"22": "B-FIRSTNAME",
|
35 |
+
"23": "I-FIRSTNAME",
|
36 |
+
"24": "B-PHONEIMEI",
|
37 |
+
"25": "I-PHONEIMEI",
|
38 |
+
"26": "B-AMOUNT",
|
39 |
+
"27": "I-AMOUNT",
|
40 |
+
"28": "B-CREDITCARDISSUER",
|
41 |
+
"29": "I-CREDITCARDISSUER",
|
42 |
+
"30": "B-CREDITCARDNUMBER",
|
43 |
+
"31": "I-CREDITCARDNUMBER",
|
44 |
+
"32": "B-EMAIL",
|
45 |
+
"33": "I-EMAIL",
|
46 |
+
"34": "B-BITCOINADDRESS",
|
47 |
+
"35": "I-BITCOINADDRESS",
|
48 |
+
"36": "B-STATE",
|
49 |
+
"37": "I-STATE",
|
50 |
+
"38": "B-JOBTYPE",
|
51 |
+
"39": "B-MASKEDNUMBER",
|
52 |
+
"40": "I-MASKEDNUMBER",
|
53 |
+
"41": "B-PASSWORD",
|
54 |
+
"42": "I-PASSWORD",
|
55 |
+
"43": "B-MAC",
|
56 |
+
"44": "I-MAC",
|
57 |
+
"45": "B-JOBAREA",
|
58 |
+
"46": "I-JOBAREA",
|
59 |
+
"47": "B-EYECOLOR",
|
60 |
+
"48": "B-USERNAME",
|
61 |
+
"49": "I-USERNAME",
|
62 |
+
"50": "B-DOB",
|
63 |
+
"51": "I-DOB",
|
64 |
+
"52": "B-PIN",
|
65 |
+
"53": "I-PIN",
|
66 |
+
"54": "B-SEX",
|
67 |
+
"55": "B-TIME",
|
68 |
+
"56": "I-TIME",
|
69 |
+
"57": "B-ETHEREUMADDRESS",
|
70 |
+
"58": "I-ETHEREUMADDRESS",
|
71 |
+
"59": "B-COMPANYNAME",
|
72 |
+
"60": "I-COMPANYNAME",
|
73 |
+
"61": "B-IPV6",
|
74 |
+
"62": "I-IPV6",
|
75 |
+
"63": "B-GENDER",
|
76 |
+
"64": "I-GENDER",
|
77 |
+
"65": "B-CURRENCY",
|
78 |
+
"66": "I-CURRENCY",
|
79 |
+
"67": "B-USERAGENT",
|
80 |
+
"68": "I-USERAGENT",
|
81 |
+
"69": "B-IP",
|
82 |
+
"70": "I-IP",
|
83 |
+
"71": "B-BUILDINGNUMBER",
|
84 |
+
"72": "B-CITY",
|
85 |
+
"73": "I-CITY",
|
86 |
+
"74": "I-JOBTYPE",
|
87 |
+
"75": "B-IPV4",
|
88 |
+
"76": "I-IPV4",
|
89 |
+
"77": "B-COUNTY",
|
90 |
+
"78": "I-COUNTY",
|
91 |
+
"79": "B-CREDITCARDCVV",
|
92 |
+
"80": "B-CURRENCYCODE",
|
93 |
+
"81": "I-CURRENCYCODE",
|
94 |
+
"82": "B-VEHICLEVRM",
|
95 |
+
"83": "I-VEHICLEVRM",
|
96 |
+
"84": "B-STREET",
|
97 |
+
"85": "I-STREET",
|
98 |
+
"86": "B-URL",
|
99 |
+
"87": "I-URL",
|
100 |
+
"88": "B-DATE",
|
101 |
+
"89": "I-DATE",
|
102 |
+
"90": "I-BUILDINGNUMBER",
|
103 |
+
"91": "B-ZIPCODE",
|
104 |
+
"92": "I-ZIPCODE",
|
105 |
+
"93": "B-ACCOUNTNAME",
|
106 |
+
"94": "I-ACCOUNTNAME",
|
107 |
+
"95": "B-MIDDLENAME",
|
108 |
+
"96": "B-SSN",
|
109 |
+
"97": "I-SSN",
|
110 |
+
"98": "B-AGE",
|
111 |
+
"99": "I-AGE",
|
112 |
+
"100": "B-ACCOUNTNUMBER",
|
113 |
+
"101": "I-ACCOUNTNUMBER",
|
114 |
+
"102": "B-LITECOINADDRESS",
|
115 |
+
"103": "I-LITECOINADDRESS",
|
116 |
+
"104": "B-VEHICLEVIN",
|
117 |
+
"105": "I-VEHICLEVIN",
|
118 |
+
"106": "I-CREDITCARDCVV",
|
119 |
+
"107": "I-EYECOLOR",
|
120 |
+
"108": "I-MIDDLENAME",
|
121 |
+
"109": "B-HEIGHT",
|
122 |
+
"110": "I-HEIGHT",
|
123 |
+
"111": "I-ORDINALDIRECTION",
|
124 |
+
"112": "I-SEX"
|
125 |
+
},
|
126 |
+
"initializer_range": 0.02,
|
127 |
+
"label2id": {
|
128 |
+
"B-ACCOUNTNAME": 93,
|
129 |
+
"B-ACCOUNTNUMBER": 100,
|
130 |
+
"B-AGE": 98,
|
131 |
+
"B-AMOUNT": 26,
|
132 |
+
"B-BIC": 14,
|
133 |
+
"B-BITCOINADDRESS": 34,
|
134 |
+
"B-BUILDINGNUMBER": 71,
|
135 |
+
"B-CITY": 72,
|
136 |
+
"B-COMPANYNAME": 59,
|
137 |
+
"B-COUNTY": 77,
|
138 |
+
"B-CREDITCARDCVV": 79,
|
139 |
+
"B-CREDITCARDISSUER": 28,
|
140 |
+
"B-CREDITCARDNUMBER": 30,
|
141 |
+
"B-CURRENCY": 65,
|
142 |
+
"B-CURRENCYCODE": 80,
|
143 |
+
"B-CURRENCYNAME": 18,
|
144 |
+
"B-CURRENCYSYMBOL": 20,
|
145 |
+
"B-DATE": 88,
|
146 |
+
"B-DOB": 50,
|
147 |
+
"B-EMAIL": 32,
|
148 |
+
"B-ETHEREUMADDRESS": 57,
|
149 |
+
"B-EYECOLOR": 47,
|
150 |
+
"B-FIRSTNAME": 22,
|
151 |
+
"B-GENDER": 63,
|
152 |
+
"B-HEIGHT": 109,
|
153 |
+
"B-IBAN": 16,
|
154 |
+
"B-IP": 69,
|
155 |
+
"B-IPV4": 75,
|
156 |
+
"B-IPV6": 61,
|
157 |
+
"B-JOBAREA": 45,
|
158 |
+
"B-JOBTITLE": 12,
|
159 |
+
"B-JOBTYPE": 38,
|
160 |
+
"B-LASTNAME": 6,
|
161 |
+
"B-LITECOINADDRESS": 102,
|
162 |
+
"B-MAC": 43,
|
163 |
+
"B-MASKEDNUMBER": 39,
|
164 |
+
"B-MIDDLENAME": 95,
|
165 |
+
"B-NEARBYGPSCOORDINATE": 2,
|
166 |
+
"B-ORDINALDIRECTION": 1,
|
167 |
+
"B-PASSWORD": 41,
|
168 |
+
"B-PHONEIMEI": 24,
|
169 |
+
"B-PHONENUMBER": 10,
|
170 |
+
"B-PIN": 52,
|
171 |
+
"B-PREFIX": 4,
|
172 |
+
"B-SECONDARYADDRESS": 8,
|
173 |
+
"B-SEX": 54,
|
174 |
+
"B-SSN": 96,
|
175 |
+
"B-STATE": 36,
|
176 |
+
"B-STREET": 84,
|
177 |
+
"B-TIME": 55,
|
178 |
+
"B-URL": 86,
|
179 |
+
"B-USERAGENT": 67,
|
180 |
+
"B-USERNAME": 48,
|
181 |
+
"B-VEHICLEVIN": 104,
|
182 |
+
"B-VEHICLEVRM": 82,
|
183 |
+
"B-ZIPCODE": 91,
|
184 |
+
"I-ACCOUNTNAME": 94,
|
185 |
+
"I-ACCOUNTNUMBER": 101,
|
186 |
+
"I-AGE": 99,
|
187 |
+
"I-AMOUNT": 27,
|
188 |
+
"I-BIC": 15,
|
189 |
+
"I-BITCOINADDRESS": 35,
|
190 |
+
"I-BUILDINGNUMBER": 90,
|
191 |
+
"I-CITY": 73,
|
192 |
+
"I-COMPANYNAME": 60,
|
193 |
+
"I-COUNTY": 78,
|
194 |
+
"I-CREDITCARDCVV": 106,
|
195 |
+
"I-CREDITCARDISSUER": 29,
|
196 |
+
"I-CREDITCARDNUMBER": 31,
|
197 |
+
"I-CURRENCY": 66,
|
198 |
+
"I-CURRENCYCODE": 81,
|
199 |
+
"I-CURRENCYNAME": 19,
|
200 |
+
"I-CURRENCYSYMBOL": 21,
|
201 |
+
"I-DATE": 89,
|
202 |
+
"I-DOB": 51,
|
203 |
+
"I-EMAIL": 33,
|
204 |
+
"I-ETHEREUMADDRESS": 58,
|
205 |
+
"I-EYECOLOR": 107,
|
206 |
+
"I-FIRSTNAME": 23,
|
207 |
+
"I-GENDER": 64,
|
208 |
+
"I-HEIGHT": 110,
|
209 |
+
"I-IBAN": 17,
|
210 |
+
"I-IP": 70,
|
211 |
+
"I-IPV4": 76,
|
212 |
+
"I-IPV6": 62,
|
213 |
+
"I-JOBAREA": 46,
|
214 |
+
"I-JOBTITLE": 13,
|
215 |
+
"I-JOBTYPE": 74,
|
216 |
+
"I-LASTNAME": 7,
|
217 |
+
"I-LITECOINADDRESS": 103,
|
218 |
+
"I-MAC": 44,
|
219 |
+
"I-MASKEDNUMBER": 40,
|
220 |
+
"I-MIDDLENAME": 108,
|
221 |
+
"I-NEARBYGPSCOORDINATE": 3,
|
222 |
+
"I-ORDINALDIRECTION": 111,
|
223 |
+
"I-PASSWORD": 42,
|
224 |
+
"I-PHONEIMEI": 25,
|
225 |
+
"I-PHONENUMBER": 11,
|
226 |
+
"I-PIN": 53,
|
227 |
+
"I-PREFIX": 5,
|
228 |
+
"I-SECONDARYADDRESS": 9,
|
229 |
+
"I-SEX": 112,
|
230 |
+
"I-SSN": 97,
|
231 |
+
"I-STATE": 37,
|
232 |
+
"I-STREET": 85,
|
233 |
+
"I-TIME": 56,
|
234 |
+
"I-URL": 87,
|
235 |
+
"I-USERAGENT": 68,
|
236 |
+
"I-USERNAME": 49,
|
237 |
+
"I-VEHICLEVIN": 105,
|
238 |
+
"I-VEHICLEVRM": 83,
|
239 |
+
"I-ZIPCODE": 92,
|
240 |
+
"O": 0
|
241 |
+
},
|
242 |
+
"max_position_embeddings": 512,
|
243 |
+
"model_type": "distilbert",
|
244 |
+
"n_heads": 12,
|
245 |
+
"n_layers": 6,
|
246 |
+
"output_past": true,
|
247 |
+
"pad_token_id": 0,
|
248 |
+
"qa_dropout": 0.1,
|
249 |
+
"seq_classif_dropout": 0.2,
|
250 |
+
"sinusoidal_pos_embds": false,
|
251 |
+
"tie_weights_": true,
|
252 |
+
"torch_dtype": "float32",
|
253 |
+
"transformers_version": "4.40.1",
|
254 |
+
"vocab_size": 119547
|
255 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0c97d47b6d7f8bce7c45a3b884b568eb9371674b1e5571ff0868e345b1d5a5a
|
3 |
+
size 539296276
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df6d8224814605d5069fdc4d9f2b450dec1932b429ee3caa739b1ae975cd7303
|
3 |
+
size 1078650554
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9d40ffe8a23b5b4b46add1066a5f1f6a585ef4b56eebe6a0463f29293928c7a
|
3 |
+
size 13990
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8891a02935ba8d0705e6bfd10443ae3b5c21586e304fbc609b18671abaf315e
|
3 |
+
size 1064
|
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 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.07471394538879395,
|
3 |
+
"best_model_checkpoint": "distilbert-base-multilingual-cased-ai4p\\checkpoint-5282",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 5282,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.09466111321469141,
|
13 |
+
"grad_norm": 0.3661908209323883,
|
14 |
+
"learning_rate": 2.3651844843897824e-05,
|
15 |
+
"loss": 0.1236,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.18932222642938282,
|
20 |
+
"grad_norm": 0.6252937316894531,
|
21 |
+
"learning_rate": 4.730368968779565e-05,
|
22 |
+
"loss": 0.1067,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.28398333964407424,
|
27 |
+
"grad_norm": 9.51940631866455,
|
28 |
+
"learning_rate": 4.865589479133266e-05,
|
29 |
+
"loss": 0.118,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.37864445285876563,
|
34 |
+
"grad_norm": 18.169490814208984,
|
35 |
+
"learning_rate": 4.4101898108698986e-05,
|
36 |
+
"loss": 0.1236,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.47330556607345703,
|
41 |
+
"grad_norm": 0.15524064004421234,
|
42 |
+
"learning_rate": 3.693781703029716e-05,
|
43 |
+
"loss": 0.1252,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.5679666792881485,
|
48 |
+
"grad_norm": 5.280295372009277,
|
49 |
+
"learning_rate": 2.814255198405058e-05,
|
50 |
+
"loss": 0.1135,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.6626277925028399,
|
55 |
+
"grad_norm": 1.4628525972366333,
|
56 |
+
"learning_rate": 1.891788846390441e-05,
|
57 |
+
"loss": 0.1095,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.7572889057175313,
|
62 |
+
"grad_norm": 0.3247055113315582,
|
63 |
+
"learning_rate": 1.0524284994615455e-05,
|
64 |
+
"loss": 0.0889,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.8519500189322227,
|
69 |
+
"grad_norm": 15.866767883300781,
|
70 |
+
"learning_rate": 4.10864401042293e-06,
|
71 |
+
"loss": 0.0993,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.9466111321469141,
|
76 |
+
"grad_norm": 0.05221886187791824,
|
77 |
+
"learning_rate": 5.475990440994617e-07,
|
78 |
+
"loss": 0.1167,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.0,
|
83 |
+
"eval_ACCOUNTNAME_f1": 0.9860627177700348,
|
84 |
+
"eval_ACCOUNTNUMBER_f1": 0.9660766961651918,
|
85 |
+
"eval_AGE_f1": 0.9777117384843984,
|
86 |
+
"eval_AMOUNT_f1": 0.9308291342189646,
|
87 |
+
"eval_BIC_f1": 0.9647058823529411,
|
88 |
+
"eval_BITCOINADDRESS_f1": 0.9257575757575758,
|
89 |
+
"eval_BUILDINGNUMBER_f1": 0.9371345029239766,
|
90 |
+
"eval_CITY_f1": 0.936,
|
91 |
+
"eval_COMPANYNAME_f1": 0.9870550161812297,
|
92 |
+
"eval_COUNTY_f1": 0.9694189602446482,
|
93 |
+
"eval_CREDITCARDCVV_f1": 0.9424083769633508,
|
94 |
+
"eval_CREDITCARDISSUER_f1": 0.981294964028777,
|
95 |
+
"eval_CREDITCARDNUMBER_f1": 0.8649851632047477,
|
96 |
+
"eval_CURRENCYCODE_f1": 0.8132992327365729,
|
97 |
+
"eval_CURRENCYNAME_f1": 0.273015873015873,
|
98 |
+
"eval_CURRENCYSYMBOL_f1": 0.9074585635359117,
|
99 |
+
"eval_CURRENCY_f1": 0.6470588235294117,
|
100 |
+
"eval_DATE_f1": 0.8255208333333333,
|
101 |
+
"eval_DOB_f1": 0.6356720202874049,
|
102 |
+
"eval_EMAIL_f1": 0.9888765294771968,
|
103 |
+
"eval_ETHEREUMADDRESS_f1": 0.9641873278236914,
|
104 |
+
"eval_EYECOLOR_f1": 0.9613034623217922,
|
105 |
+
"eval_FIRSTNAME_f1": 0.9645473190741283,
|
106 |
+
"eval_GENDER_f1": 0.9882352941176471,
|
107 |
+
"eval_HEIGHT_f1": 0.9784735812133072,
|
108 |
+
"eval_IBAN_f1": 0.9593023255813953,
|
109 |
+
"eval_IPV4_f1": 0.8195592286501376,
|
110 |
+
"eval_IPV6_f1": 0.8110867979576952,
|
111 |
+
"eval_IP_f1": 0.007843137254901962,
|
112 |
+
"eval_JOBAREA_f1": 0.9797507788161994,
|
113 |
+
"eval_JOBTITLE_f1": 0.976923076923077,
|
114 |
+
"eval_JOBTYPE_f1": 0.9853587115666179,
|
115 |
+
"eval_LASTNAME_f1": 0.94026226323458,
|
116 |
+
"eval_LITECOINADDRESS_f1": 0.7431693989071039,
|
117 |
+
"eval_MAC_f1": 0.9878048780487805,
|
118 |
+
"eval_MASKEDNUMBER_f1": 0.8086580086580087,
|
119 |
+
"eval_MIDDLENAME_f1": 0.8847641144624903,
|
120 |
+
"eval_NEARBYGPSCOORDINATE_f1": 0.9919028340080971,
|
121 |
+
"eval_ORDINALDIRECTION_f1": 0.9969512195121951,
|
122 |
+
"eval_PASSWORD_f1": 0.9656823623304069,
|
123 |
+
"eval_PHONEIMEI_f1": 0.9664179104477612,
|
124 |
+
"eval_PHONENUMBER_f1": 0.9745693191140279,
|
125 |
+
"eval_PIN_f1": 0.9051987767584098,
|
126 |
+
"eval_PREFIX_f1": 0.9503239740820734,
|
127 |
+
"eval_SECONDARYADDRESS_f1": 0.9871589085072231,
|
128 |
+
"eval_SEX_f1": 0.9957507082152975,
|
129 |
+
"eval_SSN_f1": 0.9929929929929929,
|
130 |
+
"eval_STATE_f1": 0.9698412698412698,
|
131 |
+
"eval_STREET_f1": 0.9632598530394122,
|
132 |
+
"eval_TIME_f1": 0.9889763779527558,
|
133 |
+
"eval_URL_f1": 0.9935170178282009,
|
134 |
+
"eval_USERAGENT_f1": 0.9880843263061412,
|
135 |
+
"eval_USERNAME_f1": 0.969363707776905,
|
136 |
+
"eval_VEHICLEVIN_f1": 0.9942196531791907,
|
137 |
+
"eval_VEHICLEVRM_f1": 0.9915966386554622,
|
138 |
+
"eval_ZIPCODE_f1": 0.9448441247002398,
|
139 |
+
"eval_loss": 0.07471394538879395,
|
140 |
+
"eval_overall_accuracy": 0.974947997301672,
|
141 |
+
"eval_overall_f1": 0.9267119117275793,
|
142 |
+
"eval_overall_precision": 0.9186491579319279,
|
143 |
+
"eval_overall_recall": 0.9349174482365985,
|
144 |
+
"eval_runtime": 13665.2679,
|
145 |
+
"eval_samples_per_second": 0.773,
|
146 |
+
"eval_steps_per_second": 0.387,
|
147 |
+
"step": 5282
|
148 |
+
}
|
149 |
+
],
|
150 |
+
"logging_steps": 500,
|
151 |
+
"max_steps": 5282,
|
152 |
+
"num_input_tokens_seen": 0,
|
153 |
+
"num_train_epochs": 1,
|
154 |
+
"save_steps": 500,
|
155 |
+
"total_flos": 364456496974380.0,
|
156 |
+
"train_batch_size": 2,
|
157 |
+
"trial_name": null,
|
158 |
+
"trial_params": null
|
159 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:503d6ef183373f88a0cf26cfa679f3c54b6bcc720de2954be4324010fabe2089
|
3 |
+
size 5048
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|