aimarsg commited on
Commit
baa0824
1 Parent(s): e3ea8f0

Training in progress, epoch 1

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd3d615b14d0b3cb048aa54be117dd0cc4eaa65a4ffd74c0099d572311733432
3
  size 498674357
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69667c2cd516ebd7a4d73fe85612c076211a41f7d315cffacd6e33192d9dec2
3
  size 498674357
special_tokens_map.json CHANGED
@@ -1,7 +1,51 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,15 +1,65 @@
1
  {
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": false,
6
- "mask_token": "[MASK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "model_max_length": 512,
8
- "never_split": null,
9
- "pad_token": "[PAD]",
10
- "sep_token": "[SEP]",
11
- "strip_accents": false,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
 
1
  {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
  "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "max_len": 512,
38
  "model_max_length": 512,
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff