rose-e-wang commited on
Commit
f323b73
·
verified ·
1 Parent(s): 386fe5e

Training in progress, epoch 1

Browse files
added_tokens.json CHANGED
@@ -3,5 +3,8 @@
3
  "<mask>": 50264,
4
  "<pad>": 1,
5
  "<s>": 0,
6
- "<unk>": 3
 
 
 
7
  }
 
3
  "<mask>": 50264,
4
  "<pad>": 1,
5
  "<s>": 0,
6
+ "<unk>": 3,
7
+ "[POSTTEXT]": 50266,
8
+ "[PRETEXT]": 50265,
9
+ "[TEXT]": 50267
10
  }
config.json CHANGED
@@ -32,5 +32,5 @@
32
  "transformers_version": "4.34.0",
33
  "type_vocab_size": 1,
34
  "use_cache": true,
35
- "vocab_size": 50265
36
  }
 
32
  "transformers_version": "4.34.0",
33
  "type_vocab_size": 1,
34
  "use_cache": true,
35
+ "vocab_size": 50268
36
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbe8d6f42cd020e0493ec0d442bcd8f8fcc99b3df1e6c14b0940e27767e7c15a
3
- size 1421582769
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5cbfd8578d879627b498c03c3337460b69c641e27096d3043f1c6de8ba262fd
3
+ size 1421595057
special_tokens_map.json CHANGED
@@ -1,4 +1,9 @@
1
  {
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
 
1
  {
2
+ "additional_special_tokens": [
3
+ "[PRETEXT]",
4
+ "[POSTTEXT]",
5
+ "[TEXT]"
6
+ ],
7
  "bos_token": "<s>",
8
  "cls_token": "<s>",
9
  "eos_token": "</s>",
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
@@ -47,6 +52,33 @@
47
  "rstrip": false,
48
  "normalized": false,
49
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  }
51
  ],
52
  "normalizer": null,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
52
  "rstrip": false,
53
  "normalized": false,
54
  "special": true
55
+ },
56
+ {
57
+ "id": 50265,
58
+ "content": "[PRETEXT]",
59
+ "single_word": false,
60
+ "lstrip": true,
61
+ "rstrip": true,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ {
66
+ "id": 50266,
67
+ "content": "[POSTTEXT]",
68
+ "single_word": false,
69
+ "lstrip": true,
70
+ "rstrip": true,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ {
75
+ "id": 50267,
76
+ "content": "[TEXT]",
77
+ "single_word": false,
78
+ "lstrip": true,
79
+ "rstrip": true,
80
+ "normalized": false,
81
+ "special": true
82
  }
83
  ],
84
  "normalizer": null,
tokenizer_config.json CHANGED
@@ -40,9 +40,37 @@
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  }
44
  },
45
- "additional_special_tokens": [],
 
 
 
 
46
  "bos_token": "<s>",
47
  "clean_up_tokenization_spaces": true,
48
  "cls_token": "<s>",
 
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
+ },
44
+ "50265": {
45
+ "content": "[PRETEXT]",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50266": {
53
+ "content": "[POSTTEXT]",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50267": {
61
+ "content": "[TEXT]",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
  }
68
  },
69
+ "additional_special_tokens": [
70
+ "[PRETEXT]",
71
+ "[POSTTEXT]",
72
+ "[TEXT]"
73
+ ],
74
  "bos_token": "<s>",
75
  "clean_up_tokenization_spaces": true,
76
  "cls_token": "<s>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:190cbca9eb73c807d96d7cd1096fb250b61cfa84d0f0039663d4eefeb32127de
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6d90fcedfe5a9ff1c47fc7a5705e980da0900a505c85137646b97fc3951498
3
  size 4091