Hugging Face's logo

hewonty
/
bert-ner-finetuned-pii-long-sequences

Token Classification
Transformers
TensorBoard
Safetensors
bert
Inference Endpoints
Model card Files Metrics Community
hewonty commited on
Commit
33a1bb0
•
1 Parent(s): 89ca6d4

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +57 -0
  2. model.safetensors +3 -0
  3. runs/Feb19_11-56-12_ca8025cf0f18/events.out.tfevents.1708343779.ca8025cf0f18.34.0 +3 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +63 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hewonty/bert-ner-finetuned-pii",
3
+ "_num_labels": 9,
4
+ "architectures": [
5
+ "BertForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "B-EMAIL",
14
+ "1": "B-ID_NUM",
15
+ "2": "B-NAME_STUDENT",
16
+ "3": "B-PHONE_NUM",
17
+ "4": "B-STREET_ADDRESS",
18
+ "5": "B-URL_PERSONAL",
19
+ "6": "B-USERNAME",
20
+ "7": "I-ID_NUM",
21
+ "8": "I-NAME_STUDENT",
22
+ "9": "I-PHONE_NUM",
23
+ "10": "I-STREET_ADDRESS",
24
+ "11": "I-URL_PERSONAL",
25
+ "12": "O"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "B-EMAIL": 0,
31
+ "B-ID_NUM": 1,
32
+ "B-NAME_STUDENT": 2,
33
+ "B-PHONE_NUM": 3,
34
+ "B-STREET_ADDRESS": 4,
35
+ "B-URL_PERSONAL": 5,
36
+ "B-USERNAME": 6,
37
+ "I-ID_NUM": 7,
38
+ "I-NAME_STUDENT": 8,
39
+ "I-PHONE_NUM": 9,
40
+ "I-STREET_ADDRESS": 10,
41
+ "I-URL_PERSONAL": 11,
42
+ "O": 12
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "max_position_embeddings": 512,
46
+ "model_type": "bert",
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 12,
49
+ "output_past": true,
50
+ "pad_token_id": 0,
51
+ "position_embedding_type": "absolute",
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.37.0",
54
+ "type_vocab_size": 2,
55
+ "use_cache": true,
56
+ "vocab_size": 28996
57
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dead9b1dcb8f5bb1cda50f4249b3975a21efeab9daed66cd28aa5a95fb09e4cf
3
+ size 430942044
runs/Feb19_11-56-12_ca8025cf0f18/events.out.tfevents.1708343779.ca8025cf0f18.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:886fec159c7ead6e2c4ed16aacf7289228b4e343084bbb8d4aa2a3ffc118a52d
3
+ size 24012
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
+ "mask_token": "[MASK]",
50
+ "max_len": 512,
51
+ "max_length": 512,
52
+ "model_max_length": 512,
53
+ "never_split": null,
54
+ "pad_token": "[PAD]",
55
+ "sep_token": "[SEP]",
56
+ "stride": 0,
57
+ "strip_accents": null,
58
+ "tokenize_chinese_chars": true,
59
+ "tokenizer_class": "BertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "[UNK]"
63
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef99383524a4677d8612a040f3517e829fc7a353412f996b640744b3d8367fad
3
+ size 4792
vocab.txt ADDED
The diff for this file is too large to render. See raw diff