oussama commited on
Commit
a82e2f5
1 Parent(s): 109a292

Training in progress, step 500

Browse files
config.json CHANGED
@@ -61,7 +61,7 @@
61
  "shape_size": 128,
62
  "text_embed": true,
63
  "torch_dtype": "float32",
64
- "transformers_version": "4.21.0.dev0",
65
  "type_vocab_size": 1,
66
  "visual_embed": true,
67
  "vocab_size": 50265
61
  "shape_size": 128,
62
  "text_embed": true,
63
  "torch_dtype": "float32",
64
+ "transformers_version": "4.32.0.dev0",
65
  "type_vocab_size": 1,
66
  "visual_embed": true,
67
  "vocab_size": 50265
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ t
3
  Ġ a
4
  h e
1
+ #version: 0.2
2
  Ġ t
3
  Ġ a
4
  h e
preprocessor_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "apply_ocr": false,
3
  "do_normalize": true,
 
4
  "do_resize": true,
5
  "feature_extractor_type": "LayoutLMv3FeatureExtractor",
6
  "image_mean": [
@@ -8,6 +9,7 @@
8
  0.5,
9
  0.5
10
  ],
 
11
  "image_std": [
12
  0.5,
13
  0.5,
@@ -16,5 +18,10 @@
16
  "ocr_lang": null,
17
  "processor_class": "LayoutLMv3Processor",
18
  "resample": 2,
19
- "size": 224
 
 
 
 
 
20
  }
1
  {
2
  "apply_ocr": false,
3
  "do_normalize": true,
4
+ "do_rescale": true,
5
  "do_resize": true,
6
  "feature_extractor_type": "LayoutLMv3FeatureExtractor",
7
  "image_mean": [
9
  0.5,
10
  0.5
11
  ],
12
+ "image_processor_type": "LayoutLMv3ImageProcessor",
13
  "image_std": [
14
  0.5,
15
  0.5,
18
  "ocr_lang": null,
19
  "processor_class": "LayoutLMv3Processor",
20
  "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "height": 224,
24
+ "width": 224
25
+ },
26
+ "tesseract_config": ""
27
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d07782f3f5aa5a7dca90e92f435c4c76c9070dc8bc477156c12d5f1bca288d4
3
- size 503784271
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce35ddc64488d58f7b52563960bf91e5e566b170b1429176954ff7ed7154b90
3
+ size 503781677
tokenizer.json CHANGED
@@ -96,6 +96,7 @@
96
  "continuing_subword_prefix": "",
97
  "end_of_word_suffix": "",
98
  "fuse_unk": false,
 
99
  "vocab": {
100
  "<s>": 0,
101
  "<pad>": 1,
96
  "continuing_subword_prefix": "",
97
  "end_of_word_suffix": "",
98
  "fuse_unk": false,
99
+ "byte_fallback": false,
100
  "vocab": {
101
  "<s>": 0,
102
  "<pad>": 1,
tokenizer_config.json CHANGED
@@ -9,6 +9,7 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
 
12
  "cls_token": {
13
  "__type": "AddedToken",
14
  "content": "<s>",
@@ -41,7 +42,6 @@
41
  "single_word": false
42
  },
43
  "model_max_length": 512,
44
- "name_or_path": "microsoft/layoutlmv3-base",
45
  "only_label_first_subword": true,
46
  "pad_token": {
47
  "__type": "AddedToken",
@@ -73,7 +73,6 @@
73
  0,
74
  0
75
  ],
76
- "special_tokens_map_file": null,
77
  "tokenizer_class": "LayoutLMv3Tokenizer",
78
  "trim_offsets": true,
79
  "unk_token": {
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "clean_up_tokenization_spaces": true,
13
  "cls_token": {
14
  "__type": "AddedToken",
15
  "content": "<s>",
42
  "single_word": false
43
  },
44
  "model_max_length": 512,
 
45
  "only_label_first_subword": true,
46
  "pad_token": {
47
  "__type": "AddedToken",
73
  0,
74
  0
75
  ],
 
76
  "tokenizer_class": "LayoutLMv3Tokenizer",
77
  "trim_offsets": true,
78
  "unk_token": {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:906d3d77a7a1daa4b8b8913dd52265a86c71d76d3f3e77fe76cf3f87a6b5a5c3
3
- size 3375
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f567568bcf823adc54555537461a0da99bee2a24a787f432eab06b5a3eac40e
3
+ size 4091