Alnusjaponica commited on
Commit
78e1167
1 Parent(s): f9e4f57

Training in progress, epoch 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<pad>": 0,
3
+ "<unk>": 1,
4
+ "[CLS]": 2,
5
+ "[MASK]": 4,
6
+ "[SEP]": 3
7
+ }
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "line-corporation/line-distilbert-base-japanese",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "ToxicSentenceClassifier"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4,
28
+ "LABEL_5": 5,
29
+ "LABEL_6": 6,
30
+ "LABEL_7": 7
31
+ },
32
+ "max_position_embeddings": 512,
33
+ "model_type": "distilbert",
34
+ "n_heads": 12,
35
+ "n_layers": 6,
36
+ "output_hidden_states": true,
37
+ "pad_token_id": 0,
38
+ "problem_type": "multi_label_classification",
39
+ "qa_dropout": 0.1,
40
+ "seq_classif_dropout": 0.2,
41
+ "sinusoidal_pos_embds": true,
42
+ "tie_weights_": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.34.0",
45
+ "vocab_size": 32768
46
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96fbbe3e4f38d12b30597b8b181fe74c9fbf5cc0648a6af232837ab5aaeafeee
3
+ size 274772269
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "<unk>"
9
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfafc8c0662d9c8f39621a64c74260f2ad120310c8dd24886de2dddaf599b4e
3
+ size 439391
tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "auto_map": {
46
+ "AutoTokenizer": [
47
+ "line-corporation/line-distilbert-base-japanese--distilbert_japanese_tokenizer.DistilBertJapaneseTokenizer",
48
+ null
49
+ ]
50
+ },
51
+ "bos_token": "[CLS]",
52
+ "clean_up_tokenization_spaces": true,
53
+ "cls_token": "[CLS]",
54
+ "do_lower_case": true,
55
+ "do_subword_tokenize": true,
56
+ "do_word_tokenize": true,
57
+ "eos_token": "[SEP]",
58
+ "jumanpp_kwargs": null,
59
+ "keep_accents": true,
60
+ "mask_token": "[MASK]",
61
+ "mecab_kwargs": {
62
+ "mecab_dic": "unidic_lite"
63
+ },
64
+ "model_max_length": 1000000000000000019884624838656,
65
+ "never_split": null,
66
+ "pad_token": "<pad>",
67
+ "remove_space": true,
68
+ "sep_token": "[SEP]",
69
+ "subword_tokenizer_type": "sentencepiece",
70
+ "sudachi_kwargs": null,
71
+ "tokenize_chinese_chars": false,
72
+ "tokenizer_class": "BertJapaneseTokenizer",
73
+ "tokenizer_file": null,
74
+ "unk_token": "<unk>",
75
+ "word_tokenizer_type": "mecab"
76
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9efa8d8a077b31c0bbe7b836f2adfeee46de21c52d11372c3296a9105e17c8
3
+ size 4091