Hugging Face's logo

asafd60
/
LiltHeb_2.0

TensorBoard
Safetensors
layoutlmv3
Model card Files
xet
Metrics Community
asafd60 commited on
Commit
6598d93
·
verified ·
1 Parent(s): b02fbf0

Training in progress, step 200

Browse files
Files changed (8) hide show
  1. merges.txt +0 -0
  2. model.safetensors +1 -1
  3. runs/Aug15_13-11-33_39f7c6efe4df/events.out.tfevents.1723727494.39f7c6efe4df.1056.0 +3 -0
  4. special_tokens_map.json +7 -7
  5. tokenizer.json +2 -2
  6. tokenizer_config.json +16 -12
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f031e6ea0a3153d1473861de685d172bf756b8c737c62fa92b3355739a4260a
3
  size 1117294952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a465f2880a6e4a0914b1ee08c54b98d8366a3f99139a0557e3982cb679c7c3e7
3
  size 1117294952
runs/Aug15_13-11-33_39f7c6efe4df/events.out.tfevents.1723727494.39f7c6efe4df.1056.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0baa7e3850e01cf4b1cec657df1ec01cff3da9d6e154ffe20152dcd5d602cff9
3
+ size 6247
special_tokens_map.json CHANGED
@@ -2,49 +2,49 @@
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
- "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "cls_token": {
10
  "content": "<s>",
11
  "lstrip": false,
12
- "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "eos_token": {
17
  "content": "</s>",
18
  "lstrip": false,
19
- "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "mask_token": {
24
  "content": "<mask>",
25
  "lstrip": true,
26
- "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "pad_token": {
31
  "content": "<pad>",
32
  "lstrip": false,
33
- "normalized": false,
34
  "rstrip": false,
35
  "single_word": false
36
  },
37
  "sep_token": {
38
  "content": "</s>",
39
  "lstrip": false,
40
- "normalized": false,
41
  "rstrip": false,
42
  "single_word": false
43
  },
44
  "unk_token": {
45
  "content": "<unk>",
46
  "lstrip": false,
47
- "normalized": false,
48
  "rstrip": false,
49
  "single_word": false
50
  }
 
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
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
3
- size 17082999
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b642560e24dade6e668205a829def6a058668c45d63a12752160fd2b539d0417
3
+ size 2108905
tokenizer_config.json CHANGED
@@ -1,9 +1,10 @@
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<s>",
5
  "lstrip": false,
6
- "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
@@ -11,7 +12,7 @@
11
  "1": {
12
  "content": "<pad>",
13
  "lstrip": false,
14
- "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
@@ -19,7 +20,7 @@
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
- "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
@@ -27,15 +28,15 @@
27
  "3": {
28
  "content": "<unk>",
29
  "lstrip": false,
30
- "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "250001": {
36
  "content": "<mask>",
37
  "lstrip": true,
38
- "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
@@ -51,8 +52,10 @@
51
  0
52
  ],
53
  "eos_token": "</s>",
 
54
  "mask_token": "<mask>",
55
- "model_max_length": 1000000000000000019884624838656,
 
56
  "only_label_first_subword": true,
57
  "pad_token": "<pad>",
58
  "pad_token_box": [
@@ -64,11 +67,12 @@
64
  "pad_token_label": -100,
65
  "sep_token": "</s>",
66
  "sep_token_box": [
67
- 1000,
68
- 1000,
69
- 1000,
70
- 1000
71
  ],
72
- "tokenizer_class": "LayoutXLMTokenizer",
 
73
  "unk_token": "<unk>"
74
  }
 
1
  {
2
+ "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
  "content": "<s>",
6
  "lstrip": false,
7
+ "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
12
  "1": {
13
  "content": "<pad>",
14
  "lstrip": false,
15
+ "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
 
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
 
28
  "3": {
29
  "content": "<unk>",
30
  "lstrip": false,
31
+ "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "50264": {
37
  "content": "<mask>",
38
  "lstrip": true,
39
+ "normalized": true,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
 
52
  0
53
  ],
54
  "eos_token": "</s>",
55
+ "errors": "replace",
56
  "mask_token": "<mask>",
57
+ "max_len": 512,
58
+ "model_max_length": 512,
59
  "only_label_first_subword": true,
60
  "pad_token": "<pad>",
61
  "pad_token_box": [
 
67
  "pad_token_label": -100,
68
  "sep_token": "</s>",
69
  "sep_token_box": [
70
+ 0,
71
+ 0,
72
+ 0,
73
+ 0
74
  ],
75
+ "tokenizer_class": "LayoutLMv3Tokenizer",
76
+ "trim_offsets": true,
77
  "unk_token": "<unk>"
78
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64f2e4af66b35ba9983c138c4d55cda64b052231af0f29bdf6a124d67d675730
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96bbf34d013627c580d9c3e8d1443007aacbac9c0d0585eefcf4c824c39fc68e
3
  size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff