Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +114 -0
- merges.txt +0 -0
- preprocessor_config.json +27 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +86 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/layoutlmv3-base",
|
3 |
+
"architectures": [
|
4 |
+
"LayoutLMv3ForTokenClassification"
|
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": "E-RECEIVERNAME",
|
18 |
+
"1": "E-RECEIVERADRESS",
|
19 |
+
"10": "B-RECEIVERADRESS",
|
20 |
+
"11": "B-EXPIRATIONDATE",
|
21 |
+
"12": "E-TOTALAMOUNT",
|
22 |
+
"13": "E-RECEIVERCITY",
|
23 |
+
"14": "E-SENDERADRESS",
|
24 |
+
"15": "E-VATAMOUNT",
|
25 |
+
"16": "I-RECEIVERNAME",
|
26 |
+
"17": "I-EXPIRATIONDATE",
|
27 |
+
"18": "E-RECEIVERZIPCODE",
|
28 |
+
"19": "I-SENDERADRESS",
|
29 |
+
"2": "I-SENDERNAME",
|
30 |
+
"20": "B-SENDERNAME",
|
31 |
+
"21": "I-INVOICEDATE",
|
32 |
+
"22": "B-TOTALAMOUNT",
|
33 |
+
"23": "E-EXPIRATIONDATE",
|
34 |
+
"24": "B-SENDERZIPCODE",
|
35 |
+
"25": "B-RECEIVERNAME",
|
36 |
+
"26": "E-SENDERNAME",
|
37 |
+
"27": "B-SENDERADRESS",
|
38 |
+
"28": "B-REFERENCE",
|
39 |
+
"29": "I-SENDERZIPCODE",
|
40 |
+
"3": "B-INVOICEDATE",
|
41 |
+
"30": "B-VATAMOUNT",
|
42 |
+
"31": "I-REFERENCE",
|
43 |
+
"32": "B-RECEIVERCITY",
|
44 |
+
"33": "B-RECEIVERZIPCODE",
|
45 |
+
"34": "I-SENDERCITY",
|
46 |
+
"4": "I-RECEIVERADRESS",
|
47 |
+
"5": "E-SENDERCITY",
|
48 |
+
"6": "E-INVOICEDATE",
|
49 |
+
"7": "E-SENDERZIPCODE",
|
50 |
+
"8": "B-SENDERCITY",
|
51 |
+
"9": "E-REFERENCE"
|
52 |
+
},
|
53 |
+
"initializer_range": 0.02,
|
54 |
+
"input_size": 224,
|
55 |
+
"intermediate_size": 3072,
|
56 |
+
"label2id": {
|
57 |
+
"B-EXPIRATIONDATE": 11,
|
58 |
+
"B-INVOICEDATE": 3,
|
59 |
+
"B-RECEIVERADRESS": 10,
|
60 |
+
"B-RECEIVERCITY": 32,
|
61 |
+
"B-RECEIVERNAME": 25,
|
62 |
+
"B-RECEIVERZIPCODE": 33,
|
63 |
+
"B-REFERENCE": 28,
|
64 |
+
"B-SENDERADRESS": 27,
|
65 |
+
"B-SENDERCITY": 8,
|
66 |
+
"B-SENDERNAME": 20,
|
67 |
+
"B-SENDERZIPCODE": 24,
|
68 |
+
"B-TOTALAMOUNT": 22,
|
69 |
+
"B-VATAMOUNT": 30,
|
70 |
+
"E-EXPIRATIONDATE": 23,
|
71 |
+
"E-INVOICEDATE": 6,
|
72 |
+
"E-RECEIVERADRESS": 1,
|
73 |
+
"E-RECEIVERCITY": 13,
|
74 |
+
"E-RECEIVERNAME": 0,
|
75 |
+
"E-RECEIVERZIPCODE": 18,
|
76 |
+
"E-REFERENCE": 9,
|
77 |
+
"E-SENDERADRESS": 14,
|
78 |
+
"E-SENDERCITY": 5,
|
79 |
+
"E-SENDERNAME": 26,
|
80 |
+
"E-SENDERZIPCODE": 7,
|
81 |
+
"E-TOTALAMOUNT": 12,
|
82 |
+
"E-VATAMOUNT": 15,
|
83 |
+
"I-EXPIRATIONDATE": 17,
|
84 |
+
"I-INVOICEDATE": 21,
|
85 |
+
"I-RECEIVERADRESS": 4,
|
86 |
+
"I-RECEIVERNAME": 16,
|
87 |
+
"I-REFERENCE": 31,
|
88 |
+
"I-SENDERADRESS": 19,
|
89 |
+
"I-SENDERCITY": 34,
|
90 |
+
"I-SENDERNAME": 2,
|
91 |
+
"I-SENDERZIPCODE": 29
|
92 |
+
},
|
93 |
+
"layer_norm_eps": 1e-05,
|
94 |
+
"max_2d_position_embeddings": 1024,
|
95 |
+
"max_position_embeddings": 514,
|
96 |
+
"max_rel_2d_pos": 256,
|
97 |
+
"max_rel_pos": 128,
|
98 |
+
"model_type": "layoutlmv3",
|
99 |
+
"num_attention_heads": 12,
|
100 |
+
"num_channels": 3,
|
101 |
+
"num_hidden_layers": 12,
|
102 |
+
"pad_token_id": 1,
|
103 |
+
"patch_size": 16,
|
104 |
+
"rel_2d_pos_bins": 64,
|
105 |
+
"rel_pos_bins": 32,
|
106 |
+
"second_input_size": 112,
|
107 |
+
"shape_size": 128,
|
108 |
+
"text_embed": true,
|
109 |
+
"torch_dtype": "float32",
|
110 |
+
"transformers_version": "4.30.0.dev0",
|
111 |
+
"type_vocab_size": 1,
|
112 |
+
"visual_embed": true,
|
113 |
+
"vocab_size": 50265
|
114 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": [
|
8 |
+
0.5,
|
9 |
+
0.5,
|
10 |
+
0.5
|
11 |
+
],
|
12 |
+
"image_processor_type": "LayoutLMv3ImageProcessor",
|
13 |
+
"image_std": [
|
14 |
+
0.5,
|
15 |
+
0.5,
|
16 |
+
0.5
|
17 |
+
],
|
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
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1401c50386727f3b1dfcf10395c23a444e02ee4afd201db36151bb39bd8870d
|
3 |
+
size 503857143
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"apply_ocr": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"cls_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"cls_token_box": [
|
22 |
+
0,
|
23 |
+
0,
|
24 |
+
0,
|
25 |
+
0
|
26 |
+
],
|
27 |
+
"eos_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "</s>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
},
|
35 |
+
"errors": "replace",
|
36 |
+
"mask_token": {
|
37 |
+
"__type": "AddedToken",
|
38 |
+
"content": "<mask>",
|
39 |
+
"lstrip": true,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"model_max_length": 512,
|
45 |
+
"only_label_first_subword": true,
|
46 |
+
"pad_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "<pad>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"pad_token_box": [
|
55 |
+
0,
|
56 |
+
0,
|
57 |
+
0,
|
58 |
+
0
|
59 |
+
],
|
60 |
+
"pad_token_label": -100,
|
61 |
+
"processor_class": "LayoutLMv3Processor",
|
62 |
+
"sep_token": {
|
63 |
+
"__type": "AddedToken",
|
64 |
+
"content": "</s>",
|
65 |
+
"lstrip": false,
|
66 |
+
"normalized": true,
|
67 |
+
"rstrip": false,
|
68 |
+
"single_word": false
|
69 |
+
},
|
70 |
+
"sep_token_box": [
|
71 |
+
0,
|
72 |
+
0,
|
73 |
+
0,
|
74 |
+
0
|
75 |
+
],
|
76 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
77 |
+
"trim_offsets": true,
|
78 |
+
"unk_token": {
|
79 |
+
"__type": "AddedToken",
|
80 |
+
"content": "<unk>",
|
81 |
+
"lstrip": false,
|
82 |
+
"normalized": true,
|
83 |
+
"rstrip": false,
|
84 |
+
"single_word": false
|
85 |
+
}
|
86 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbd59710f34851c9ddb077d5d665459ed8d239f122b6de53787302aa9ad9d33c
|
3 |
+
size 3951
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|