Mizuiro-sakura commited on
Commit
8846a77
1 Parent(s): fddb86b

Upload 9 files

Browse files
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cl-tohoku/bert-large-japanese-v2",
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": 1024,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d",
14
+ "2": "I-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d",
15
+ "3": "B-\u6cd5\u4eba\u540d",
16
+ "4": "I-\u6cd5\u4eba\u540d",
17
+ "5": "B-\u5730\u540d",
18
+ "6": "I-\u5730\u540d",
19
+ "7": "B-\u4eba\u540d",
20
+ "8": "I-\u4eba\u540d",
21
+ "9": "B-\u65bd\u8a2d\u540d",
22
+ "10": "I-\u65bd\u8a2d\u540d",
23
+ "11": "B-\u30a4\u30d9\u30f3\u30c8\u540d",
24
+ "12": "I-\u30a4\u30d9\u30f3\u30c8\u540d",
25
+ "13": "B-\u653f\u6cbb\u7684\u7d44\u7e54\u540d",
26
+ "14": "I-\u653f\u6cbb\u7684\u7d44\u7e54\u540d",
27
+ "15": "B-\u88fd\u54c1\u540d",
28
+ "16": "I-\u88fd\u54c1\u540d"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "label2id": {
33
+ "B-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d": 1,
34
+ "B-\u30a4\u30d9\u30f3\u30c8\u540d": 11,
35
+ "B-\u4eba\u540d": 7,
36
+ "B-\u5730\u540d": 5,
37
+ "B-\u653f\u6cbb\u7684\u7d44\u7e54\u540d": 13,
38
+ "B-\u65bd\u8a2d\u540d": 9,
39
+ "B-\u6cd5\u4eba\u540d": 3,
40
+ "B-\u88fd\u54c1\u540d": 15,
41
+ "I-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d": 2,
42
+ "I-\u30a4\u30d9\u30f3\u30c8\u540d": 12,
43
+ "I-\u4eba\u540d": 8,
44
+ "I-\u5730\u540d": 6,
45
+ "I-\u653f\u6cbb\u7684\u7d44\u7e54\u540d": 14,
46
+ "I-\u65bd\u8a2d\u540d": 10,
47
+ "I-\u6cd5\u4eba\u540d": 4,
48
+ "I-\u88fd\u54c1\u540d": 16,
49
+ "O": 0
50
+ },
51
+ "layer_norm_eps": 1e-12,
52
+ "max_position_embeddings": 512,
53
+ "model_type": "bert",
54
+ "num_attention_heads": 16,
55
+ "num_hidden_layers": 24,
56
+ "pad_token_id": 0,
57
+ "position_embedding_type": "absolute",
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.29.2",
60
+ "type_vocab_size": 2,
61
+ "use_cache": true,
62
+ "vocab_size": 32768
63
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384ff7271c2fd4249fecd8eecffba46797a95cfdc1a47da7d882ee9d7720df83
3
+ size 1345776685
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dcb064bfe3b6ba4a36687831b2a945f9f51eefd2701885f31063aa3e4cb188b
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c93a8afa13e002c27a3f9412545210f299377c6974732d95a4148432c40a3139
3
+ size 627
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 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
10
+ "mecab_dic": "unidic_lite"
11
+ },
12
+ "model_max_length": 512,
13
+ "never_split": null,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "subword_tokenizer_type": "wordpiece",
17
+ "sudachi_kwargs": null,
18
+ "tokenizer_class": "BertJapaneseTokenizer",
19
+ "unk_token": "[UNK]",
20
+ "word_tokenizer_type": "mecab"
21
+ }
trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 1170,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.14,
12
+ "learning_rate": 3.130841121495327e-05,
13
+ "loss": 0.0728,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 4.27,
18
+ "learning_rate": 7.94392523364486e-06,
19
+ "loss": 0.004,
20
+ "step": 1000
21
+ }
22
+ ],
23
+ "max_steps": 1170,
24
+ "num_train_epochs": 5,
25
+ "total_flos": 8686173881157120.0,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbeafe3a577bfc240bf04648a9e09dd69f2c1ea4be753bcb443dcd900e29056c
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff