felixtran commited on
Commit
a5e605e
·
1 Parent(s): fe9b768

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv3-base",
3
+ "architectures": [
4
+ "LayoutLMv3ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "coordinate_size": 128,
10
+ "eos_token_id": 2,
11
+ "has_relative_attention_bias": true,
12
+ "has_spatial_attention_bias": true,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "Allergen_Statement",
18
+ "1": "BRC_Audit",
19
+ "2": "BRC_Certification",
20
+ "3": "Bioengineer_Document",
21
+ "4": "Certificate_of_Analysis",
22
+ "5": "Certificate_of_Liability",
23
+ "6": "Certificate_of_Origin",
24
+ "7": "FDA_Related",
25
+ "8": "FSSC_Audit",
26
+ "9": "FSSC_Certification",
27
+ "10": "GMO_Statement",
28
+ "11": "HACCP_Plan",
29
+ "12": "Halal",
30
+ "13": "Kosher",
31
+ "14": "Letter_of_Guarantee",
32
+ "15": "Lot_Code",
33
+ "16": "Nutrition_Specification",
34
+ "17": "Organic",
35
+ "18": "Other",
36
+ "19": "Product_Specification",
37
+ "20": "Recall_Policy",
38
+ "21": "SQF_Audit",
39
+ "22": "SQF_Certification",
40
+ "23": "Safety_Data_Sheet"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "input_size": 224,
44
+ "intermediate_size": 3072,
45
+ "label2id": {
46
+ "Allergen_Statement": 0,
47
+ "BRC_Audit": 1,
48
+ "BRC_Certification": 2,
49
+ "Bioengineer_Document": 3,
50
+ "Certificate_of_Analysis": 4,
51
+ "Certificate_of_Liability": 5,
52
+ "Certificate_of_Origin": 6,
53
+ "FDA_Related": 7,
54
+ "FSSC_Audit": 8,
55
+ "FSSC_Certification": 9,
56
+ "GMO_Statement": 10,
57
+ "HACCP_Plan": 11,
58
+ "Halal": 12,
59
+ "Kosher": 13,
60
+ "Letter_of_Guarantee": 14,
61
+ "Lot_Code": 15,
62
+ "Nutrition_Specification": 16,
63
+ "Organic": 17,
64
+ "Other": 18,
65
+ "Product_Specification": 19,
66
+ "Recall_Policy": 20,
67
+ "SQF_Audit": 21,
68
+ "SQF_Certification": 22,
69
+ "Safety_Data_Sheet": 23
70
+ },
71
+ "layer_norm_eps": 1e-05,
72
+ "max_2d_position_embeddings": 1024,
73
+ "max_position_embeddings": 514,
74
+ "max_rel_2d_pos": 256,
75
+ "max_rel_pos": 128,
76
+ "model_type": "layoutlmv3",
77
+ "num_attention_heads": 12,
78
+ "num_channels": 3,
79
+ "num_hidden_layers": 12,
80
+ "pad_token_id": 1,
81
+ "patch_size": 16,
82
+ "problem_type": "single_label_classification",
83
+ "rel_2d_pos_bins": 64,
84
+ "rel_pos_bins": 32,
85
+ "second_input_size": 112,
86
+ "shape_size": 128,
87
+ "text_embed": true,
88
+ "torch_dtype": "float32",
89
+ "transformers_version": "4.28.0",
90
+ "type_vocab_size": 1,
91
+ "visual_embed": true,
92
+ "vocab_size": 50265
93
+ }
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 sha256:6b373ff04e1d09851404cef73035bcef7d4ff49afa2527f713a23a56e10ea2f0
3
+ size 503823089
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
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
+ }
51
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "cls_token_box": [
21
+ 0,
22
+ 0,
23
+ 0,
24
+ 0
25
+ ],
26
+ "eos_token": {
27
+ "__type": "AddedToken",
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "errors": "replace",
35
+ "mask_token": {
36
+ "__type": "AddedToken",
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ },
43
+ "model_max_length": 512,
44
+ "only_label_first_subword": true,
45
+ "pad_token": {
46
+ "__type": "AddedToken",
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token_box": [
54
+ 0,
55
+ 0,
56
+ 0,
57
+ 0
58
+ ],
59
+ "pad_token_label": -100,
60
+ "sep_token": {
61
+ "__type": "AddedToken",
62
+ "content": "</s>",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false
67
+ },
68
+ "sep_token_box": [
69
+ 0,
70
+ 0,
71
+ 0,
72
+ 0
73
+ ],
74
+ "tokenizer_class": "LayoutLMv3Tokenizer",
75
+ "tokenizer_file": null,
76
+ "unk_token": {
77
+ "__type": "AddedToken",
78
+ "content": "<unk>",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false
83
+ }
84
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1693e162d9923fc25491769d423e7f52058e78b714ea5369e134f3a2558b64e8
3
+ size 3643
vocab.json ADDED
The diff for this file is too large to render. See raw diff