Training in progress, epoch 0
Browse files- config.json +173 -0
- model.safetensors +3 -0
- runs/Aug15_23-32-49_T2P-CPU010/events.out.tfevents.1723739571.T2P-CPU010.4169456.0 +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 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-bookingNumber",
|
15 |
+
"2": "I-bookingNumber",
|
16 |
+
"3": "B-cardNumber",
|
17 |
+
"4": "I-cardNumber",
|
18 |
+
"5": "B-cardType",
|
19 |
+
"6": "I-cardType",
|
20 |
+
"7": "B-checkIn",
|
21 |
+
"8": "I-checkIn",
|
22 |
+
"9": "B-checkOut",
|
23 |
+
"10": "I-checkOut",
|
24 |
+
"11": "B-companyAddress",
|
25 |
+
"12": "I-companyAddress",
|
26 |
+
"13": "B-companyCity",
|
27 |
+
"14": "I-companyCity",
|
28 |
+
"15": "B-companyCountry",
|
29 |
+
"16": "I-companyCountry",
|
30 |
+
"17": "B-companyName",
|
31 |
+
"18": "I-companyName",
|
32 |
+
"19": "B-companyVATNumber",
|
33 |
+
"20": "I-companyVATNumber",
|
34 |
+
"21": "B-companyZipcode",
|
35 |
+
"22": "I-companyZipcode",
|
36 |
+
"23": "B-currencyCode",
|
37 |
+
"24": "I-currencyCode",
|
38 |
+
"25": "B-documentType",
|
39 |
+
"26": "I-documentType",
|
40 |
+
"27": "B-externalReservationNumber",
|
41 |
+
"28": "I-externalReservationNumber",
|
42 |
+
"29": "B-grossAmount",
|
43 |
+
"30": "I-grossAmount",
|
44 |
+
"31": "B-hotelAddress",
|
45 |
+
"32": "I-hotelAddress",
|
46 |
+
"33": "B-hotelBankAccount",
|
47 |
+
"34": "I-hotelBankAccount",
|
48 |
+
"35": "B-hotelCity",
|
49 |
+
"36": "I-hotelCity",
|
50 |
+
"37": "B-hotelCountry",
|
51 |
+
"38": "I-hotelCountry",
|
52 |
+
"39": "B-hotelEmail",
|
53 |
+
"40": "I-hotelEmail",
|
54 |
+
"41": "B-hotelFaxNumber",
|
55 |
+
"42": "I-hotelFaxNumber",
|
56 |
+
"43": "B-hotelName",
|
57 |
+
"44": "I-hotelName",
|
58 |
+
"45": "B-hotelPhoneNumber",
|
59 |
+
"46": "I-hotelPhoneNumber",
|
60 |
+
"47": "B-hotelTaxCode",
|
61 |
+
"48": "I-hotelTaxCode",
|
62 |
+
"49": "B-hotelVATNumber",
|
63 |
+
"50": "I-hotelVATNumber",
|
64 |
+
"51": "B-hotelZipCode",
|
65 |
+
"52": "I-hotelZipCode",
|
66 |
+
"53": "B-invoiceDate",
|
67 |
+
"54": "I-invoiceDate",
|
68 |
+
"55": "B-invoiceNumber",
|
69 |
+
"56": "I-invoiceNumber",
|
70 |
+
"57": "B-netAmount",
|
71 |
+
"58": "I-netAmount",
|
72 |
+
"59": "B-pageNumber",
|
73 |
+
"60": "I-pageNumber",
|
74 |
+
"61": "B-reservationNumber",
|
75 |
+
"62": "I-reservationNumber",
|
76 |
+
"63": "B-roomNo",
|
77 |
+
"64": "I-roomNo",
|
78 |
+
"65": "B-taxAmount",
|
79 |
+
"66": "I-taxAmount",
|
80 |
+
"67": "B-travellerName",
|
81 |
+
"68": "I-travellerName"
|
82 |
+
},
|
83 |
+
"initializer_range": 0.02,
|
84 |
+
"intermediate_size": 3072,
|
85 |
+
"label2id": {
|
86 |
+
"B-bookingNumber": 1,
|
87 |
+
"B-cardNumber": 3,
|
88 |
+
"B-cardType": 5,
|
89 |
+
"B-checkIn": 7,
|
90 |
+
"B-checkOut": 9,
|
91 |
+
"B-companyAddress": 11,
|
92 |
+
"B-companyCity": 13,
|
93 |
+
"B-companyCountry": 15,
|
94 |
+
"B-companyName": 17,
|
95 |
+
"B-companyVATNumber": 19,
|
96 |
+
"B-companyZipcode": 21,
|
97 |
+
"B-currencyCode": 23,
|
98 |
+
"B-documentType": 25,
|
99 |
+
"B-externalReservationNumber": 27,
|
100 |
+
"B-grossAmount": 29,
|
101 |
+
"B-hotelAddress": 31,
|
102 |
+
"B-hotelBankAccount": 33,
|
103 |
+
"B-hotelCity": 35,
|
104 |
+
"B-hotelCountry": 37,
|
105 |
+
"B-hotelEmail": 39,
|
106 |
+
"B-hotelFaxNumber": 41,
|
107 |
+
"B-hotelName": 43,
|
108 |
+
"B-hotelPhoneNumber": 45,
|
109 |
+
"B-hotelTaxCode": 47,
|
110 |
+
"B-hotelVATNumber": 49,
|
111 |
+
"B-hotelZipCode": 51,
|
112 |
+
"B-invoiceDate": 53,
|
113 |
+
"B-invoiceNumber": 55,
|
114 |
+
"B-netAmount": 57,
|
115 |
+
"B-pageNumber": 59,
|
116 |
+
"B-reservationNumber": 61,
|
117 |
+
"B-roomNo": 63,
|
118 |
+
"B-taxAmount": 65,
|
119 |
+
"B-travellerName": 67,
|
120 |
+
"I-bookingNumber": 2,
|
121 |
+
"I-cardNumber": 4,
|
122 |
+
"I-cardType": 6,
|
123 |
+
"I-checkIn": 8,
|
124 |
+
"I-checkOut": 10,
|
125 |
+
"I-companyAddress": 12,
|
126 |
+
"I-companyCity": 14,
|
127 |
+
"I-companyCountry": 16,
|
128 |
+
"I-companyName": 18,
|
129 |
+
"I-companyVATNumber": 20,
|
130 |
+
"I-companyZipcode": 22,
|
131 |
+
"I-currencyCode": 24,
|
132 |
+
"I-documentType": 26,
|
133 |
+
"I-externalReservationNumber": 28,
|
134 |
+
"I-grossAmount": 30,
|
135 |
+
"I-hotelAddress": 32,
|
136 |
+
"I-hotelBankAccount": 34,
|
137 |
+
"I-hotelCity": 36,
|
138 |
+
"I-hotelCountry": 38,
|
139 |
+
"I-hotelEmail": 40,
|
140 |
+
"I-hotelFaxNumber": 42,
|
141 |
+
"I-hotelName": 44,
|
142 |
+
"I-hotelPhoneNumber": 46,
|
143 |
+
"I-hotelTaxCode": 48,
|
144 |
+
"I-hotelVATNumber": 50,
|
145 |
+
"I-hotelZipCode": 52,
|
146 |
+
"I-invoiceDate": 54,
|
147 |
+
"I-invoiceNumber": 56,
|
148 |
+
"I-netAmount": 58,
|
149 |
+
"I-pageNumber": 60,
|
150 |
+
"I-reservationNumber": 62,
|
151 |
+
"I-roomNo": 64,
|
152 |
+
"I-taxAmount": 66,
|
153 |
+
"I-travellerName": 68,
|
154 |
+
"O": 0
|
155 |
+
},
|
156 |
+
"layer_norm_eps": 1e-12,
|
157 |
+
"max_position_embeddings": 512,
|
158 |
+
"model_type": "bert",
|
159 |
+
"num_attention_heads": 12,
|
160 |
+
"num_hidden_layers": 12,
|
161 |
+
"pad_token_id": 0,
|
162 |
+
"pooler_fc_size": 768,
|
163 |
+
"pooler_num_attention_heads": 12,
|
164 |
+
"pooler_num_fc_layers": 3,
|
165 |
+
"pooler_size_per_head": 128,
|
166 |
+
"pooler_type": "first_token_transform",
|
167 |
+
"position_embedding_type": "absolute",
|
168 |
+
"torch_dtype": "float32",
|
169 |
+
"transformers_version": "4.40.2",
|
170 |
+
"type_vocab_size": 2,
|
171 |
+
"use_cache": true,
|
172 |
+
"vocab_size": 119547
|
173 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c0d09d194a3cad5d1060f56ed8f7b6d7010e6df95b0c2ea3cc381b3b34e9ad7
|
3 |
+
size 709286996
|
runs/Aug15_23-32-49_T2P-CPU010/events.out.tfevents.1723739571.T2P-CPU010.4169456.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02fae680bfdef00a57844cee6108dea11950e8eb5fa50ee0cdef27e6b036633a
|
3 |
+
size 38635
|
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": "BertTokenizer",
|
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:d38e5c5df65431fe0d3b0a48340a727abdf8319dd02588de9e8db98d3c9a2ad3
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|