Hugging Face's logo

Heyzz
/
wikineural-finetuned-ner

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Heyzz commited on
Commit
1fdd45d
•
1 Parent(s): 1b299ef

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +77 -0
  2. model.safetensors +3 -0
  3. runs/Jul04_11-44-38_be7e65f98b81/events.out.tfevents.1720093485.be7e65f98b81.154.0 +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 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Babelscape/wikineural-multilingual-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": "I-SND",
15
+ "2": "B-SND",
16
+ "3": "I-PHN",
17
+ "4": "B-PHN",
18
+ "5": "I-ORG",
19
+ "6": "B-ORG",
20
+ "7": "I-LOC",
21
+ "8": "B-LOC",
22
+ "9": "I-JT",
23
+ "10": "B-JT",
24
+ "11": "I-EXR",
25
+ "12": "B-EXR",
26
+ "13": "B-MN",
27
+ "14": "B-MAIL",
28
+ "15": "B-KPP",
29
+ "16": "B-INN",
30
+ "17": "I-DS",
31
+ "18": "B-DS",
32
+ "19": "I-ADR",
33
+ "20": "B-ADR"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "B-ADR": 20,
39
+ "B-DS": 18,
40
+ "B-EXR": 12,
41
+ "B-INN": 16,
42
+ "B-JT": 10,
43
+ "B-KPP": 15,
44
+ "B-LOC": 8,
45
+ "B-MAIL": 14,
46
+ "B-MN": 13,
47
+ "B-ORG": 6,
48
+ "B-PHN": 4,
49
+ "B-SND": 2,
50
+ "I-ADR": 19,
51
+ "I-DS": 17,
52
+ "I-EXR": 11,
53
+ "I-JT": 9,
54
+ "I-LOC": 7,
55
+ "I-ORG": 5,
56
+ "I-PHN": 3,
57
+ "I-SND": 1,
58
+ "O": 0
59
+ },
60
+ "layer_norm_eps": 1e-12,
61
+ "max_position_embeddings": 512,
62
+ "model_type": "bert",
63
+ "num_attention_heads": 12,
64
+ "num_hidden_layers": 12,
65
+ "pad_token_id": 0,
66
+ "pooler_fc_size": 768,
67
+ "pooler_num_attention_heads": 12,
68
+ "pooler_num_fc_layers": 3,
69
+ "pooler_size_per_head": 128,
70
+ "pooler_type": "first_token_transform",
71
+ "position_embedding_type": "absolute",
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.41.2",
74
+ "type_vocab_size": 2,
75
+ "use_cache": true,
76
+ "vocab_size": 119547
77
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e27a2eb274c088e619349d215cdbefd99061128903d17b81b8b460540dd00e
3
+ size 709139348
runs/Jul04_11-44-38_be7e65f98b81/events.out.tfevents.1720093485.be7e65f98b81.154.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2615f2a50e73345babed6c6b11f7571369b7b9ec87e4526a885b317ecd2ba57f
3
+ size 6263
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": false,
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 sha256:3ac0b7d74fff6960f9d0cd618bdcf0c7285599256d728ae835c51865380496f7
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff