Training in progress, epoch 1
Browse files- config.json +62 -0
- logs/events.out.tfevents.1725958129.7ac140579d3b.36.0 +3 -0
- model.safetensors +3 -0
- preprocessor_config.json +13 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +80 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/layoutlm-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"LayoutLMForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "OTHER",
|
12 |
+
"1": "ssnOfEmployee",
|
13 |
+
"2": "einEmployerIdentificationNumber",
|
14 |
+
"3": "box1WagesTipsAndOtherCompensations",
|
15 |
+
"4": "box2FederalIncomeTaxWithheld",
|
16 |
+
"5": "employerName",
|
17 |
+
"6": "box3SocialSecurityWages",
|
18 |
+
"7": "box4SocialSecurityTaxWithheld",
|
19 |
+
"8": "employerAddressStreet_name",
|
20 |
+
"9": "employerAddressCity",
|
21 |
+
"10": "employerAddressState",
|
22 |
+
"11": "employerAddressZip",
|
23 |
+
"12": "employeeName",
|
24 |
+
"13": "taxYear",
|
25 |
+
"14": "box16StateWagesTips",
|
26 |
+
"15": "box17StateIncomeTax"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"label2id": {
|
31 |
+
"OTHER": 0,
|
32 |
+
"box16StateWagesTips": 14,
|
33 |
+
"box17StateIncomeTax": 15,
|
34 |
+
"box1WagesTipsAndOtherCompensations": 3,
|
35 |
+
"box2FederalIncomeTaxWithheld": 4,
|
36 |
+
"box3SocialSecurityWages": 6,
|
37 |
+
"box4SocialSecurityTaxWithheld": 7,
|
38 |
+
"einEmployerIdentificationNumber": 2,
|
39 |
+
"employeeName": 12,
|
40 |
+
"employerAddressCity": 9,
|
41 |
+
"employerAddressState": 10,
|
42 |
+
"employerAddressStreet_name": 8,
|
43 |
+
"employerAddressZip": 11,
|
44 |
+
"employerName": 5,
|
45 |
+
"ssnOfEmployee": 1,
|
46 |
+
"taxYear": 13
|
47 |
+
},
|
48 |
+
"layer_norm_eps": 1e-12,
|
49 |
+
"max_2d_position_embeddings": 1024,
|
50 |
+
"max_position_embeddings": 512,
|
51 |
+
"model_type": "layoutlm",
|
52 |
+
"num_attention_heads": 12,
|
53 |
+
"num_hidden_layers": 12,
|
54 |
+
"output_past": true,
|
55 |
+
"pad_token_id": 0,
|
56 |
+
"position_embedding_type": "absolute",
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.44.0",
|
59 |
+
"type_vocab_size": 2,
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 30522
|
62 |
+
}
|
logs/events.out.tfevents.1725958129.7ac140579d3b.36.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e917d5c4d4678cdef24ea614d707db3d3c7186b0e7ba34a6c690bb40f67c90e
|
3 |
+
size 6584
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ed57cafb1a87a9ec1c97fc2139ea3fc928ba2f7bacb24c8d285242a9058ebd3
|
3 |
+
size 450585896
|
preprocessor_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_ocr": true,
|
3 |
+
"do_resize": true,
|
4 |
+
"image_processor_type": "LayoutLMv2ImageProcessor",
|
5 |
+
"ocr_lang": null,
|
6 |
+
"processor_class": "LayoutLMv2Processor",
|
7 |
+
"resample": 2,
|
8 |
+
"size": {
|
9 |
+
"height": 224,
|
10 |
+
"width": 224
|
11 |
+
},
|
12 |
+
"tesseract_config": ""
|
13 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
+
"apply_ocr": false,
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "[CLS]",
|
48 |
+
"cls_token_box": [
|
49 |
+
0,
|
50 |
+
0,
|
51 |
+
0,
|
52 |
+
0
|
53 |
+
],
|
54 |
+
"do_basic_tokenize": true,
|
55 |
+
"do_lower_case": true,
|
56 |
+
"mask_token": "[MASK]",
|
57 |
+
"model_max_length": 512,
|
58 |
+
"never_split": null,
|
59 |
+
"only_label_first_subword": true,
|
60 |
+
"pad_token": "[PAD]",
|
61 |
+
"pad_token_box": [
|
62 |
+
0,
|
63 |
+
0,
|
64 |
+
0,
|
65 |
+
0
|
66 |
+
],
|
67 |
+
"pad_token_label": -100,
|
68 |
+
"processor_class": "LayoutLMv2Processor",
|
69 |
+
"sep_token": "[SEP]",
|
70 |
+
"sep_token_box": [
|
71 |
+
1000,
|
72 |
+
1000,
|
73 |
+
1000,
|
74 |
+
1000
|
75 |
+
],
|
76 |
+
"strip_accents": null,
|
77 |
+
"tokenize_chinese_chars": true,
|
78 |
+
"tokenizer_class": "LayoutLMv2Tokenizer",
|
79 |
+
"unk_token": "[UNK]"
|
80 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85cb6d89e9478acf7133d18c20c2adff399f968b8ef25151d4d4e13ce5273558
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|