GiGi2044 commited on
Commit
71a0879
1 Parent(s): 2d0724e

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f18471f187709a1005c76fc4a7b4745dd7a68f5894452c466ae83326bf30b8bc
3
  size 295806292
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe58ca31c92a7d5fad3a3321b41d12373faf1e3b663a09cc19c812627730e8f
3
  size 295806292
special_tokens_map.json CHANGED
@@ -1,5 +1,9 @@
1
  {
2
- "eos_token": "</s>",
3
- "pad_token": "<pad>",
4
- "unk_token": "<unk>"
 
 
 
 
5
  }
 
1
  {
2
+ "pad_token": {
3
+ "content": "[PAD]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ }
9
  }
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "</s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,6 +9,22 @@
9
  "special": true
10
  },
11
  "1": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "content": "<unk>",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,8 +32,16 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "58100": {
20
- "content": "<pad>",
 
 
 
 
 
 
 
 
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -26,13 +50,7 @@
26
  }
27
  },
28
  "clean_up_tokenization_spaces": true,
29
- "eos_token": "</s>",
30
- "model_max_length": 512,
31
- "pad_token": "<pad>",
32
- "separate_vocabs": false,
33
- "source_lang": "en",
34
- "sp_model_kwargs": {},
35
- "target_lang": "de",
36
- "tokenizer_class": "MarianTokenizer",
37
- "unk_token": "<unk>"
38
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
  "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "124": {
44
+ "content": "[PAD]",
45
  "lstrip": false,
46
  "normalized": false,
47
  "rstrip": false,
 
50
  }
51
  },
52
  "clean_up_tokenization_spaces": true,
53
+ "model_max_length": 1000000000000000019884624838656,
54
+ "pad_token": "[PAD]",
55
+ "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
 
 
56
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0a8d4b9c1700b3ab2184fdc2983bb2a53f03c43ab71b36bee987ec75ce2fc30
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329d7eda4a248d2d56e7165cce673d7176fe9465aa790a1edd8d5a39084127ea
3
  size 5304