Training in progress epoch 0
Browse files- config.json +72 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "B-Beneficiary Name",
|
14 |
+
"1": "B-Insurance Company",
|
15 |
+
"2": "B-Insurance Company Address",
|
16 |
+
"3": "B-Law Firm",
|
17 |
+
"4": "B-Law Office Address",
|
18 |
+
"5": "B-Payout",
|
19 |
+
"6": "B-Policy Holder Name",
|
20 |
+
"7": "B-Policy Number",
|
21 |
+
"8": "B-Required Action",
|
22 |
+
"9": "B-Sender",
|
23 |
+
"10": "B-UNASSIGNED",
|
24 |
+
"11": "I-Beneficiary Name",
|
25 |
+
"12": "I-Insurance Company",
|
26 |
+
"13": "I-Insurance Company Address",
|
27 |
+
"14": "I-Law Firm",
|
28 |
+
"15": "I-Law Office Address",
|
29 |
+
"16": "I-Policy Holder Name",
|
30 |
+
"17": "I-Required Action",
|
31 |
+
"18": "I-Sender",
|
32 |
+
"19": "I-UNASSIGNED",
|
33 |
+
"20": "O"
|
34 |
+
},
|
35 |
+
"initializer_range": 0.02,
|
36 |
+
"intermediate_size": 3072,
|
37 |
+
"label2id": {
|
38 |
+
"B-Beneficiary Name": 0,
|
39 |
+
"B-Insurance Company": 1,
|
40 |
+
"B-Insurance Company Address": 2,
|
41 |
+
"B-Law Firm": 3,
|
42 |
+
"B-Law Office Address": 4,
|
43 |
+
"B-Payout": 5,
|
44 |
+
"B-Policy Holder Name": 6,
|
45 |
+
"B-Policy Number": 7,
|
46 |
+
"B-Required Action": 8,
|
47 |
+
"B-Sender": 9,
|
48 |
+
"B-UNASSIGNED": 10,
|
49 |
+
"I-Beneficiary Name": 11,
|
50 |
+
"I-Insurance Company": 12,
|
51 |
+
"I-Insurance Company Address": 13,
|
52 |
+
"I-Law Firm": 14,
|
53 |
+
"I-Law Office Address": 15,
|
54 |
+
"I-Policy Holder Name": 16,
|
55 |
+
"I-Required Action": 17,
|
56 |
+
"I-Sender": 18,
|
57 |
+
"I-UNASSIGNED": 19,
|
58 |
+
"O": 20
|
59 |
+
},
|
60 |
+
"layer_norm_eps": 1e-12,
|
61 |
+
"max_position_embeddings": 512,
|
62 |
+
"model_type": "bert",
|
63 |
+
"num_attention_heads": 12,
|
64 |
+
"num_hidden_layers": 12,
|
65 |
+
"pad_token_id": 0,
|
66 |
+
"position_embedding_type": "absolute",
|
67 |
+
"torch_dtype": "float32",
|
68 |
+
"transformers_version": "4.36.1",
|
69 |
+
"type_vocab_size": 2,
|
70 |
+
"use_cache": true,
|
71 |
+
"vocab_size": 28996
|
72 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdc2efe03fa0c70e9490864f1769a2386b193e4c86d98a5f583e817718a6f54d
|
3 |
+
size 430966652
|
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 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|