TomasFAV commited on
Commit
6a988c3
·
verified ·
1 Parent(s): c2226d2

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "dtype": "float32",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B_INVOICE_NUMBER",
15
+ "2": "I_INVOICE_NUMBER",
16
+ "3": "B_SUPPLIER_REGISTER_ID",
17
+ "4": "I_SUPPLIER_REGISTER_ID",
18
+ "5": "B_SUPPLIER_TAX_ID",
19
+ "6": "I_SUPPLIER_TAX_ID",
20
+ "7": "B_CUSTOMER_REGISTER_ID",
21
+ "8": "I_CUSTOMER_REGISTER_ID",
22
+ "9": "B_CUSTOMER_TAX_ID",
23
+ "10": "I_CUSTOMER_TAX_ID",
24
+ "11": "B_ISSUE_DATE",
25
+ "12": "I_ISSUE_DATE",
26
+ "13": "B_TAXABLE_SUPPLY_DATE",
27
+ "14": "I_TAXABLE_SUPPLY_DATE",
28
+ "15": "B_DUE_DATE",
29
+ "16": "I_DUE_DATE",
30
+ "17": "B_PAYMENT_TYPE",
31
+ "18": "I_PAYMENT_TYPE",
32
+ "19": "B_BANK_ACCOUNT_NUMBER",
33
+ "20": "I_BANK_ACCOUNT_NUMBER",
34
+ "21": "B_IBAN",
35
+ "22": "I_IBAN",
36
+ "23": "B_BIC",
37
+ "24": "I_BIC",
38
+ "25": "B_VARIABLE_SYMBOL",
39
+ "26": "I_VARIABLE_SYMBOL",
40
+ "27": "B_CONST_SYMBOL",
41
+ "28": "I_CONST_SYMBOL",
42
+ "29": "B_VAT_PERCENTAGE",
43
+ "30": "I_VAT_PERCENTAGE",
44
+ "31": "B_VAT_BASE",
45
+ "32": "I_VAT_BASE",
46
+ "33": "B_VAT",
47
+ "34": "I_VAT",
48
+ "35": "B_TOTAL",
49
+ "36": "I_TOTAL"
50
+ },
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 3072,
53
+ "label2id": {
54
+ "B_BANK_ACCOUNT_NUMBER": 19,
55
+ "B_BIC": 23,
56
+ "B_CONST_SYMBOL": 27,
57
+ "B_CUSTOMER_REGISTER_ID": 7,
58
+ "B_CUSTOMER_TAX_ID": 9,
59
+ "B_DUE_DATE": 15,
60
+ "B_IBAN": 21,
61
+ "B_INVOICE_NUMBER": 1,
62
+ "B_ISSUE_DATE": 11,
63
+ "B_PAYMENT_TYPE": 17,
64
+ "B_SUPPLIER_REGISTER_ID": 3,
65
+ "B_SUPPLIER_TAX_ID": 5,
66
+ "B_TAXABLE_SUPPLY_DATE": 13,
67
+ "B_TOTAL": 35,
68
+ "B_VARIABLE_SYMBOL": 25,
69
+ "B_VAT": 33,
70
+ "B_VAT_BASE": 31,
71
+ "B_VAT_PERCENTAGE": 29,
72
+ "I_BANK_ACCOUNT_NUMBER": 20,
73
+ "I_BIC": 24,
74
+ "I_CONST_SYMBOL": 28,
75
+ "I_CUSTOMER_REGISTER_ID": 8,
76
+ "I_CUSTOMER_TAX_ID": 10,
77
+ "I_DUE_DATE": 16,
78
+ "I_IBAN": 22,
79
+ "I_INVOICE_NUMBER": 2,
80
+ "I_ISSUE_DATE": 12,
81
+ "I_PAYMENT_TYPE": 18,
82
+ "I_SUPPLIER_REGISTER_ID": 4,
83
+ "I_SUPPLIER_TAX_ID": 6,
84
+ "I_TAXABLE_SUPPLY_DATE": 14,
85
+ "I_TOTAL": 36,
86
+ "I_VARIABLE_SYMBOL": 26,
87
+ "I_VAT": 34,
88
+ "I_VAT_BASE": 32,
89
+ "I_VAT_PERCENTAGE": 30,
90
+ "O": 0
91
+ },
92
+ "layer_norm_eps": 1e-12,
93
+ "max_position_embeddings": 512,
94
+ "model_type": "bert",
95
+ "num_attention_heads": 12,
96
+ "num_hidden_layers": 12,
97
+ "pad_token_id": 0,
98
+ "pooler_fc_size": 768,
99
+ "pooler_num_attention_heads": 12,
100
+ "pooler_num_fc_layers": 3,
101
+ "pooler_size_per_head": 128,
102
+ "pooler_type": "first_token_transform",
103
+ "position_embedding_type": "absolute",
104
+ "transformers_version": "4.57.6",
105
+ "type_vocab_size": 2,
106
+ "use_cache": true,
107
+ "vocab_size": 119547
108
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67077b415b31d46c17d3cbf8b5f0cde09bb3788776846b7c497b38ccd7e5792a
3
+ size 709188564
runs/Jan27_20-10-35_14895b91e4f5/events.out.tfevents.1769544641.14895b91e4f5.443.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:565406d2a3ea8a701b45b12b93841325caa68ff97bc30cfb4694e2139ae0f105
3
+ size 7661
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59bdecf4a16f59a93b55f3b144e1f4f1b877122dfb8a1578a485a0ee9e19977
3
+ size 5841
vocab.txt ADDED
The diff for this file is too large to render. See raw diff