davidliu1110 commited on
Commit
8595201
1 Parent(s): 29d3ce2

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ckiplab/bert-base-chinese",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "0",
15
+ "1": "B-ITEM",
16
+ "2": "I-ITEM",
17
+ "3": "B-BRAND",
18
+ "4": "I-BRAND"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "0": 0,
24
+ "B-BRAND": 3,
25
+ "B-ITEM": 1,
26
+ "I-BRAND": 4,
27
+ "I-ITEM": 2
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "bert",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 0,
35
+ "pooler_fc_size": 768,
36
+ "pooler_num_attention_heads": 12,
37
+ "pooler_num_fc_layers": 3,
38
+ "pooler_size_per_head": 128,
39
+ "pooler_type": "first_token_transform",
40
+ "position_embedding_type": "absolute",
41
+ "tokenizer_class": "BertTokenizerFast",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.29.0.dev0",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 21128
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:330a663be15d18c625189fb4af7796decb8388ec0af6c67e19ab8f8ed43fbbce
3
+ size 406794033
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69f91dd249aede855f60514e353ceb4c26aff7265de132eb94433d0cf326558
3
+ size 3567
vocab.txt ADDED
The diff for this file is too large to render. See raw diff