BahAdoR0101 commited on
Commit
fb49580
1 Parent(s): 0e9da47

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dslim/bert-large-NER",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "eos_token_ids": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-MIS",
16
+ "2": "I-MIS",
17
+ "3": "B-PER",
18
+ "4": "I-PER",
19
+ "5": "B-ORG",
20
+ "6": "I-ORG",
21
+ "7": "B-LOC",
22
+ "8": "I-LOC",
23
+ "9": "B-JOB_TITLE",
24
+ "10": "I-JOB_TITLE"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 4096,
28
+ "label2id": {
29
+ "B-JOB_TITLE": 9,
30
+ "B-LOC": 7,
31
+ "B-MIS": 1,
32
+ "B-ORG": 5,
33
+ "B-PER": 3,
34
+ "I-JOB_TITLE": 10,
35
+ "I-LOC": 8,
36
+ "I-MIS": 2,
37
+ "I-ORG": 6,
38
+ "I-PER": 4,
39
+ "O": 0
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "max_position_embeddings": 512,
43
+ "model_type": "bert",
44
+ "num_attention_heads": 16,
45
+ "num_hidden_layers": 24,
46
+ "output_past": true,
47
+ "pad_token_id": 0,
48
+ "pooler_fc_size": 768,
49
+ "pooler_num_attention_heads": 12,
50
+ "pooler_num_fc_layers": 3,
51
+ "pooler_size_per_head": 128,
52
+ "pooler_type": "first_token_transform",
53
+ "position_embedding_type": "absolute",
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.34.1",
56
+ "type_vocab_size": 2,
57
+ "use_cache": true,
58
+ "vocab_size": 28996
59
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ac5f801b24885faf0bb610c72f04419dcc18486c4241bb65315c5395c12bb9a
3
+ size 1330292454
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afcbff85e413889ef82ada5b72e2a8a75a77e801d16baac59b86e35c7e8a7994
3
+ size 4536
vocab.txt ADDED
The diff for this file is too large to render. See raw diff