Hugging Face's logo

jamesLeeeeeee
/
code-search-net-tokenizer

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
jamesLeeeeeee commited on
Commit
8cf2f76
·
verified ·
1 Parent(s): 1eee64d

Training in progress, epoch 3

Browse files
Files changed (7) hide show
  1. model.safetensors +1 -1
  2. runs/Mar11_10-36-12_73b178ce4b81/events.out.tfevents.1710153377.73b178ce4b81.1619.0 +3 -0
  3. special_tokens_map.json +5 -3
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +44 -8
  6. training_args.bin +3 -0
  7. vocab.txt +0 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a57fc5ad9f51c4b4a2a035572ce5df4d591a6c6c97a3d908960dba7a6c7de228
3
  size 430929740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178b7874aa8153f7a81526120f216030911a3db92c58dded9d8c0465e2b165aa
3
  size 430929740
runs/Mar11_10-36-12_73b178ce4b81/events.out.tfevents.1710153377.73b178ce4b81.1619.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9300dab5bdd3208ca30be16fc3de4963757bcf4b32b84722c5ef22d3d56ce9f
3
+ size 8818
special_tokens_map.json CHANGED
@@ -1,5 +1,7 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|endoftext|>"
 
 
5
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,19 +1,55 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<|endoftext|>",
6
  "lstrip": false,
7
- "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  }
12
  },
13
- "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": true,
15
- "eos_token": "<|endoftext|>",
16
- "model_max_length": 1024,
17
- "tokenizer_class": "GPT2Tokenizer",
18
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
19
  }
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
  }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad6319310a7132b1780ad108d76a0709fbef5f03ca21636fd87ffddc95e7c71
3
+ size 4920
vocab.txt ADDED
The diff for this file is too large to render. See raw diff