Continue training 3 epochs from last checkpoint
Browse files- .gitignore +1 -0
- config.json +93 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Danielwei0214/bert-base-chinese-finetuned-ner",
|
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-position",
|
15 |
+
"10": "I-company",
|
16 |
+
"11": "B-book",
|
17 |
+
"12": "I-book",
|
18 |
+
"13": "B-address",
|
19 |
+
"14": "I-address",
|
20 |
+
"15": "B-scene",
|
21 |
+
"16": "I-scene",
|
22 |
+
"17": "B-mobile",
|
23 |
+
"18": "I-mobile",
|
24 |
+
"19": "B-email",
|
25 |
+
"2": "I-position",
|
26 |
+
"20": "I-email",
|
27 |
+
"21": "B-game",
|
28 |
+
"22": "I-game",
|
29 |
+
"23": "B-government",
|
30 |
+
"24": "I-government",
|
31 |
+
"25": "B-QQ",
|
32 |
+
"26": "I-QQ",
|
33 |
+
"27": "B-vx",
|
34 |
+
"28": "I-vx",
|
35 |
+
"3": "B-name",
|
36 |
+
"4": "I-name",
|
37 |
+
"5": "B-movie",
|
38 |
+
"6": "I-movie",
|
39 |
+
"7": "B-organization",
|
40 |
+
"8": "I-organization",
|
41 |
+
"9": "B-company"
|
42 |
+
},
|
43 |
+
"initializer_range": 0.02,
|
44 |
+
"intermediate_size": 3072,
|
45 |
+
"label2id": {
|
46 |
+
"B-QQ": "25",
|
47 |
+
"B-address": "13",
|
48 |
+
"B-book": "11",
|
49 |
+
"B-company": "9",
|
50 |
+
"B-email": "19",
|
51 |
+
"B-game": "21",
|
52 |
+
"B-government": "23",
|
53 |
+
"B-mobile": "17",
|
54 |
+
"B-movie": "5",
|
55 |
+
"B-name": "3",
|
56 |
+
"B-organization": "7",
|
57 |
+
"B-position": "1",
|
58 |
+
"B-scene": "15",
|
59 |
+
"B-vx": "27",
|
60 |
+
"I-QQ": "26",
|
61 |
+
"I-address": "14",
|
62 |
+
"I-book": "12",
|
63 |
+
"I-company": "10",
|
64 |
+
"I-email": "20",
|
65 |
+
"I-game": "22",
|
66 |
+
"I-government": "24",
|
67 |
+
"I-mobile": "18",
|
68 |
+
"I-movie": "6",
|
69 |
+
"I-name": "4",
|
70 |
+
"I-organization": "8",
|
71 |
+
"I-position": "2",
|
72 |
+
"I-scene": "16",
|
73 |
+
"I-vx": "28",
|
74 |
+
"O": "0"
|
75 |
+
},
|
76 |
+
"layer_norm_eps": 1e-12,
|
77 |
+
"max_position_embeddings": 512,
|
78 |
+
"model_type": "bert",
|
79 |
+
"num_attention_heads": 12,
|
80 |
+
"num_hidden_layers": 12,
|
81 |
+
"pad_token_id": 0,
|
82 |
+
"pooler_fc_size": 768,
|
83 |
+
"pooler_num_attention_heads": 12,
|
84 |
+
"pooler_num_fc_layers": 3,
|
85 |
+
"pooler_size_per_head": 128,
|
86 |
+
"pooler_type": "first_token_transform",
|
87 |
+
"position_embedding_type": "absolute",
|
88 |
+
"torch_dtype": "float32",
|
89 |
+
"transformers_version": "4.27.3",
|
90 |
+
"type_vocab_size": 2,
|
91 |
+
"use_cache": true,
|
92 |
+
"vocab_size": 21128
|
93 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab1ddc99805650d44ee8aa6e59b2262ab22659ee44f6cb9d873b338308a37c88
|
3 |
+
size 406869549
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"ignore_mismatched_sizes": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"pad_token": "[PAD]",
|
9 |
+
"sep_token": "[SEP]",
|
10 |
+
"special_tokens_map_file": "/home/yirguo/.cache/huggingface/hub/models--Danielwei0214--bert-base-chinese-finetuned-ner/snapshots/d92ce014f4e5fcc30fb111f5f57ce014400614ca/special_tokens_map.json",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8662543b334563402fd847833281a20b0b1204795fad28d2416a80fa2ac59c37
|
3 |
+
size 3579
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|