nasuka commited on
Commit
1b91a20
1 Parent(s): 3873c34

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cl-tohoku/bert-large-japanese",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "tokenizer_class": "BertJapaneseTokenizer",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.25.1",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 32768
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f5e71cf65c4c2dcf0d4f681e7eb1a6d91417c9d466d6b9de82f71c9d7fd3cfb
3
+ size 1349911341
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 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "do_subword_tokenize": true,
5
+ "do_word_tokenize": true,
6
+ "jumanpp_kwargs": null,
7
+ "mask_token": "[MASK]",
8
+ "mecab_kwargs": {
9
+ "mecab_dic": "unidic_lite"
10
+ },
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "name_or_path": "cl-tohoku/bert-large-japanese",
13
+ "never_split": null,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "special_tokens_map_file": null,
17
+ "subword_tokenizer_type": "wordpiece",
18
+ "sudachi_kwargs": null,
19
+ "tokenizer_class": "BertJapaneseTokenizer",
20
+ "unk_token": "[UNK]",
21
+ "word_tokenizer_type": "mecab"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6dac249dda0255978a864ce6e5380fd93c7cb55dd499e87f2f96caa6f297983
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff