Hugging Face's logo

shubhamgantayat
/
my_pii_model_bert_large_uncased_2_v2

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
shubhamgantayat commited on
Commit
67d79f5
·
verified ·
1 Parent(s): 0138896

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +56 -0
  2. model.safetensors +3 -0
  3. runs/Apr03_08-16-35_a19c399409d4/events.out.tfevents.1712132197.a19c399409d4.276.0 +3 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +59 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "shubhamgantayat/my_pii_model_bert_large_uncased_2",
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": 1024,
12
+ "id2label": {
13
+ "0": "I-STREET_ADDRESS",
14
+ "1": "I-ID_NUM",
15
+ "2": "I-NAME_STUDENT",
16
+ "3": "B-PHONE_NUM",
17
+ "4": "B-USERNAME",
18
+ "5": "B-EMAIL",
19
+ "6": "I-PHONE_NUM",
20
+ "7": "O",
21
+ "8": "B-STREET_ADDRESS",
22
+ "9": "B-URL_PERSONAL",
23
+ "10": "I-URL_PERSONAL",
24
+ "11": "B-ID_NUM",
25
+ "12": "B-NAME_STUDENT"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 4096,
29
+ "label2id": {
30
+ "B-EMAIL": 5,
31
+ "B-ID_NUM": 11,
32
+ "B-NAME_STUDENT": 12,
33
+ "B-PHONE_NUM": 3,
34
+ "B-STREET_ADDRESS": 8,
35
+ "B-URL_PERSONAL": 9,
36
+ "B-USERNAME": 4,
37
+ "I-ID_NUM": 1,
38
+ "I-NAME_STUDENT": 2,
39
+ "I-PHONE_NUM": 6,
40
+ "I-STREET_ADDRESS": 0,
41
+ "I-URL_PERSONAL": 10,
42
+ "O": 7
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "max_position_embeddings": 512,
46
+ "model_type": "bert",
47
+ "num_attention_heads": 16,
48
+ "num_hidden_layers": 24,
49
+ "pad_token_id": 0,
50
+ "position_embedding_type": "absolute",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.38.2",
53
+ "type_vocab_size": 2,
54
+ "use_cache": true,
55
+ "vocab_size": 30522
56
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a7d1c81f1c08470b737595abeb6cd634e27ff58a80bcdf0b5ab6885881fe4f
3
+ size 1336469268
runs/Apr03_08-16-35_a19c399409d4/events.out.tfevents.1712132197.a19c399409d4.276.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00ef18fc80fa79ee1cabd7cda20b9666c4af0904af79017ef428d280aac4cd95
3
+ size 6869
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 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 512,
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "stride": 0,
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "truncation_side": "right",
57
+ "truncation_strategy": "longest_first",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed296c996a73c92a4160da1e27a3a73d2e54a11354b36bfafa2f850f911afda9
3
+ size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff