Commit
•
12a395b
1
Parent(s):
b61977c
Training in progress, epoch 1
Browse files- config.json +106 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
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": "B-CRD",
|
13 |
+
"1": "B-DAT",
|
14 |
+
"2": "B-EVT",
|
15 |
+
"3": "B-FAC",
|
16 |
+
"4": "B-GPE",
|
17 |
+
"5": "B-LAN",
|
18 |
+
"6": "B-LAW",
|
19 |
+
"7": "B-LOC",
|
20 |
+
"8": "B-MON",
|
21 |
+
"9": "B-NOR",
|
22 |
+
"10": "B-ORD",
|
23 |
+
"11": "B-ORG",
|
24 |
+
"12": "B-PER",
|
25 |
+
"13": "B-PRC",
|
26 |
+
"14": "B-PRD",
|
27 |
+
"15": "B-QTY",
|
28 |
+
"16": "B-REG",
|
29 |
+
"17": "B-TIM",
|
30 |
+
"18": "B-WOA",
|
31 |
+
"19": "I-CRD",
|
32 |
+
"20": "I-DAT",
|
33 |
+
"21": "I-EVT",
|
34 |
+
"22": "I-FAC",
|
35 |
+
"23": "I-GPE",
|
36 |
+
"24": "I-LAN",
|
37 |
+
"25": "I-LAW",
|
38 |
+
"26": "I-LOC",
|
39 |
+
"27": "I-MON",
|
40 |
+
"28": "I-NOR",
|
41 |
+
"29": "I-ORD",
|
42 |
+
"30": "I-ORG",
|
43 |
+
"31": "I-PER",
|
44 |
+
"32": "I-PRC",
|
45 |
+
"33": "I-PRD",
|
46 |
+
"34": "I-QTY",
|
47 |
+
"35": "I-REG",
|
48 |
+
"36": "I-TIM",
|
49 |
+
"37": "I-WOA",
|
50 |
+
"38": "O"
|
51 |
+
},
|
52 |
+
"initializer_range": 0.02,
|
53 |
+
"label2id": {
|
54 |
+
"B-CRD": 0,
|
55 |
+
"B-DAT": 1,
|
56 |
+
"B-EVT": 2,
|
57 |
+
"B-FAC": 3,
|
58 |
+
"B-GPE": 4,
|
59 |
+
"B-LAN": 5,
|
60 |
+
"B-LAW": 6,
|
61 |
+
"B-LOC": 7,
|
62 |
+
"B-MON": 8,
|
63 |
+
"B-NOR": 9,
|
64 |
+
"B-ORD": 10,
|
65 |
+
"B-ORG": 11,
|
66 |
+
"B-PER": 12,
|
67 |
+
"B-PRC": 13,
|
68 |
+
"B-PRD": 14,
|
69 |
+
"B-QTY": 15,
|
70 |
+
"B-REG": 16,
|
71 |
+
"B-TIM": 17,
|
72 |
+
"B-WOA": 18,
|
73 |
+
"I-CRD": 19,
|
74 |
+
"I-DAT": 20,
|
75 |
+
"I-EVT": 21,
|
76 |
+
"I-FAC": 22,
|
77 |
+
"I-GPE": 23,
|
78 |
+
"I-LAN": 24,
|
79 |
+
"I-LAW": 25,
|
80 |
+
"I-LOC": 26,
|
81 |
+
"I-MON": 27,
|
82 |
+
"I-NOR": 28,
|
83 |
+
"I-ORD": 29,
|
84 |
+
"I-ORG": 30,
|
85 |
+
"I-PER": 31,
|
86 |
+
"I-PRC": 32,
|
87 |
+
"I-PRD": 33,
|
88 |
+
"I-QTY": 34,
|
89 |
+
"I-REG": 35,
|
90 |
+
"I-TIM": 36,
|
91 |
+
"I-WOA": 37,
|
92 |
+
"O": 38
|
93 |
+
},
|
94 |
+
"max_position_embeddings": 512,
|
95 |
+
"model_type": "distilbert",
|
96 |
+
"n_heads": 12,
|
97 |
+
"n_layers": 6,
|
98 |
+
"pad_token_id": 0,
|
99 |
+
"qa_dropout": 0.1,
|
100 |
+
"seq_classif_dropout": 0.2,
|
101 |
+
"sinusoidal_pos_embds": false,
|
102 |
+
"tie_weights_": true,
|
103 |
+
"torch_dtype": "float32",
|
104 |
+
"transformers_version": "4.33.2",
|
105 |
+
"vocab_size": 30522
|
106 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:beac142db699103344a1a94366b2cf9ae48c5c101ae180349156e88e727ec4b3
|
3 |
+
size 265606309
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "DistilBertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecd5ab198c55dd1e7728993f1548c0976e9772a1c786b33f20eb47d19afc0eee
|
3 |
+
size 4091
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|