dvitel commited on
Commit
a7882fb
1 Parent(s): 6ed630e

Training in progress, step 1600

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[Add]": 50311,
3
+ "[And]": 50291,
4
+ "[Assign]": 50286,
5
+ "[Attribute]": 50280,
6
+ "[AugAssign]": 50310,
7
+ "[BinOp]": 50299,
8
+ "[BoolOp]": 50290,
9
+ "[Break]": 50316,
10
+ "[CLS0]": 50261,
11
+ "[CLS1]": 50267,
12
+ "[CLS2]": 50258,
13
+ "[Call]": 50279,
14
+ "[ClassDef]": 50271,
15
+ "[Compare]": 50292,
16
+ "[Constant]": 50281,
17
+ "[Eq]": 50296,
18
+ "[Expr]": 50278,
19
+ "[For]": 50294,
20
+ "[FunctionDef]": 50275,
21
+ "[GtE]": 50297,
22
+ "[Gt]": 50303,
23
+ "[If]": 50302,
24
+ "[ImportFrom]": 50317,
25
+ "[In]": 50319,
26
+ "[Index]": 50307,
27
+ "[IsNot]": 50305,
28
+ "[Is]": 50301,
29
+ "[LST]": 50268,
30
+ "[Lambda]": 50295,
31
+ "[ListComp]": 50313,
32
+ "[List]": 50289,
33
+ "[Load]": 50274,
34
+ "[LtE]": 50304,
35
+ "[Lt]": 50293,
36
+ "[Module]": 50270,
37
+ "[NEND]": 50269,
38
+ "[Name]": 50273,
39
+ "[NoneType]": 50282,
40
+ "[NotEq]": 50298,
41
+ "[Not]": 50320,
42
+ "[Or]": 50312,
43
+ "[Return]": 50285,
44
+ "[Slice]": 50315,
45
+ "[Store]": 50287,
46
+ "[Sub]": 50300,
47
+ "[Subscript]": 50306,
48
+ "[Tuple]": 50321,
49
+ "[USub]": 50309,
50
+ "[UnaryOp]": 50308,
51
+ "[alias]": 50318,
52
+ "[arg]": 50277,
53
+ "[arguments]": 50276,
54
+ "[bool]": 50288,
55
+ "[comprehension]": 50314,
56
+ "[int]": 50283,
57
+ "[keyword]": 50284,
58
+ "[str]": 50272,
59
+ "[v0]": 50263,
60
+ "[v1]": 50262,
61
+ "[v2]": 50257,
62
+ "[v3]": 50266,
63
+ "[v4]": 50265,
64
+ "[v5]": 50259,
65
+ "[v6]": 50260,
66
+ "[v7]": 50264
67
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c52b3ca9df91ee2005299bc02340471e6f4ed7f69975e7c1bf37c613e6209bb8
3
+ size 334176057
special_tokens_map.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[v2]",
4
+ "[CLS2]",
5
+ "[v5]",
6
+ "[v6]",
7
+ "[CLS0]",
8
+ "[v1]",
9
+ "[v0]",
10
+ "[v7]",
11
+ "[v4]",
12
+ "[v3]",
13
+ "[CLS1]",
14
+ "[LST]",
15
+ "[NEND]",
16
+ "[Module]",
17
+ "[ClassDef]",
18
+ "[str]",
19
+ "[Name]",
20
+ "[Load]",
21
+ "[FunctionDef]",
22
+ "[arguments]",
23
+ "[arg]",
24
+ "[Expr]",
25
+ "[Call]",
26
+ "[Attribute]",
27
+ "[Constant]",
28
+ "[NoneType]",
29
+ "[int]",
30
+ "[keyword]",
31
+ "[Return]",
32
+ "[Assign]",
33
+ "[Store]",
34
+ "[bool]",
35
+ "[List]",
36
+ "[BoolOp]",
37
+ "[And]",
38
+ "[Compare]",
39
+ "[Lt]",
40
+ "[For]",
41
+ "[Lambda]",
42
+ "[Eq]",
43
+ "[GtE]",
44
+ "[NotEq]",
45
+ "[BinOp]",
46
+ "[Sub]",
47
+ "[Is]",
48
+ "[If]",
49
+ "[Gt]",
50
+ "[LtE]",
51
+ "[IsNot]",
52
+ "[Subscript]",
53
+ "[Index]",
54
+ "[UnaryOp]",
55
+ "[USub]",
56
+ "[AugAssign]",
57
+ "[Add]",
58
+ "[Or]",
59
+ "[ListComp]",
60
+ "[comprehension]",
61
+ "[Slice]",
62
+ "[Break]",
63
+ "[ImportFrom]",
64
+ "[alias]",
65
+ "[In]",
66
+ "[Not]",
67
+ "[Tuple]"
68
+ ],
69
+ "bos_token": "<|endoftext|>",
70
+ "eos_token": "<|endoftext|>",
71
+ "pad_token": "<|endoftext|>",
72
+ "unk_token": "<|endoftext|>"
73
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "distilgpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6569c0370c367e160d794b569f3babcb0081ebedb312726c05295765ce7644
3
+ size 3387
vocab.json ADDED
The diff for this file is too large to render. See raw diff