Training in progress, epoch 1
Browse files- config.json +93 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForTokenClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"ctc_zero_infinity": true,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "B-DATE",
|
14 |
+
"1": "I-DATE",
|
15 |
+
"2": "L-DATE",
|
16 |
+
"3": "U-DATE",
|
17 |
+
"4": "B-GOVT_ID",
|
18 |
+
"5": "I-GOVT_ID",
|
19 |
+
"6": "L-GOVT_ID",
|
20 |
+
"7": "U-GOVT_ID",
|
21 |
+
"8": "B-LOCATION",
|
22 |
+
"9": "I-LOCATION",
|
23 |
+
"10": "L-LOCATION",
|
24 |
+
"11": "U-LOCATION",
|
25 |
+
"12": "B-NORP",
|
26 |
+
"13": "I-NORP",
|
27 |
+
"14": "L-NORP",
|
28 |
+
"15": "U-NORP",
|
29 |
+
"16": "B-ORG",
|
30 |
+
"17": "I-ORG",
|
31 |
+
"18": "L-ORG",
|
32 |
+
"19": "U-ORG",
|
33 |
+
"20": "B-PERSON",
|
34 |
+
"21": "I-PERSON",
|
35 |
+
"22": "L-PERSON",
|
36 |
+
"23": "U-PERSON",
|
37 |
+
"24": "B-USERID",
|
38 |
+
"25": "I-USERID",
|
39 |
+
"26": "L-USERID",
|
40 |
+
"27": "U-USERID",
|
41 |
+
"28": "O"
|
42 |
+
},
|
43 |
+
"initializer_range": 0.02,
|
44 |
+
"intermediate_size": 3072,
|
45 |
+
"label2id": {
|
46 |
+
"B-DATE": 0,
|
47 |
+
"B-GOVT_ID": 4,
|
48 |
+
"B-LOCATION": 8,
|
49 |
+
"B-NORP": 12,
|
50 |
+
"B-ORG": 16,
|
51 |
+
"B-PERSON": 20,
|
52 |
+
"B-USERID": 24,
|
53 |
+
"I-DATE": 1,
|
54 |
+
"I-GOVT_ID": 5,
|
55 |
+
"I-LOCATION": 9,
|
56 |
+
"I-NORP": 13,
|
57 |
+
"I-ORG": 17,
|
58 |
+
"I-PERSON": 21,
|
59 |
+
"I-USERID": 25,
|
60 |
+
"L-DATE": 2,
|
61 |
+
"L-GOVT_ID": 6,
|
62 |
+
"L-LOCATION": 10,
|
63 |
+
"L-NORP": 14,
|
64 |
+
"L-ORG": 18,
|
65 |
+
"L-PERSON": 22,
|
66 |
+
"L-USERID": 26,
|
67 |
+
"O": 28,
|
68 |
+
"U-DATE": 3,
|
69 |
+
"U-GOVT_ID": 7,
|
70 |
+
"U-LOCATION": 11,
|
71 |
+
"U-NORP": 15,
|
72 |
+
"U-ORG": 19,
|
73 |
+
"U-PERSON": 23,
|
74 |
+
"U-USERID": 27
|
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": "4.55.4",
|
90 |
+
"type_vocab_size": 2,
|
91 |
+
"use_cache": true,
|
92 |
+
"vocab_size": 119547
|
93 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c3b036c4671645c533d2dd92ceea9975a2b27c399cde9840760a91acb7fddcb
|
3 |
+
size 709163956
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "[PAD]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"100": {
|
13 |
+
"content": "[UNK]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"101": {
|
21 |
+
"content": "[CLS]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"102": {
|
29 |
+
"content": "[SEP]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"103": {
|
37 |
+
"content": "[MASK]",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"clean_up_tokenization_spaces": false,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": false,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77bafff99dee7bc0cb5b6998e7b169d9a128d08c9f1b835bc1d0bbad44dabc58
|
3 |
+
size 5841
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|