yoshivo commited on
Commit
7508d2d
1 Parent(s): 63328f0

Training completed!

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cl-tohoku/bert-base-japanese-whole-word-masking",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "B-COR": 3,
13
+ "B-EVT": 15,
14
+ "B-FCL": 11,
15
+ "B-LOC": 9,
16
+ "B-OTO": 7,
17
+ "B-PER": 1,
18
+ "B-POR": 5,
19
+ "B-PRD": 13,
20
+ "I-COR": 4,
21
+ "I-EVT": 16,
22
+ "I-FCL": 12,
23
+ "I-LOC": 10,
24
+ "I-OTO": 8,
25
+ "I-PER": 2,
26
+ "I-POR": 6,
27
+ "I-PRD": 14,
28
+ "O": 0
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "label2id": {
33
+ "0": "O",
34
+ "1": "B-PER",
35
+ "2": "I-PER",
36
+ "3": "B-COR",
37
+ "4": "I-COR",
38
+ "5": "B-POR",
39
+ "6": "I-POR",
40
+ "7": "B-OTO",
41
+ "8": "I-OTO",
42
+ "9": "B-LOC",
43
+ "10": "I-LOC",
44
+ "11": "B-FCL",
45
+ "12": "I-FCL",
46
+ "13": "B-PRD",
47
+ "14": "I-PRD",
48
+ "15": "B-EVT",
49
+ "16": "I-EVT"
50
+ },
51
+ "layer_norm_eps": 1e-12,
52
+ "max_position_embeddings": 512,
53
+ "model_type": "bert",
54
+ "num_attention_heads": 12,
55
+ "num_hidden_layers": 12,
56
+ "pad_token_id": 0,
57
+ "position_embedding_type": "absolute",
58
+ "tokenizer_class": "BertJapaneseTokenizer",
59
+ "torch_dtype": "float32",
60
+ "transformers_version": "4.29.2",
61
+ "type_vocab_size": 2,
62
+ "use_cache": true,
63
+ "vocab_size": 32000
64
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe8c7925473f0704951472f68b7d973ede7f09da714e88a0a245c0a3c405d88
3
+ size 440229745
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_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "do_subword_tokenize": true,
6
+ "do_word_tokenize": true,
7
+ "jumanpp_kwargs": null,
8
+ "mask_token": "[MASK]",
9
+ "mecab_kwargs": null,
10
+ "model_max_length": 512,
11
+ "never_split": null,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "subword_tokenizer_type": "wordpiece",
15
+ "sudachi_kwargs": null,
16
+ "tokenizer_class": "ner_tokenizer",
17
+ "unk_token": "[UNK]",
18
+ "word_tokenizer_type": "mecab"
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f532981016d4721a3d8610027b8fb0fe4a0798e1a5220d697d81c9ae154e6a9
3
+ size 3951
vocab.txt ADDED
The diff for this file is too large to render. See raw diff