jpino commited on
Commit
71cb65c
1 Parent(s): 2c57b6c

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "B-REG_CIV_BIRTHDATE",
18
+ "1": "B-REG_CIV_BLOOD",
19
+ "2": "B-REG_CIV_CITYBD",
20
+ "3": "B-REG_CIV_CLIN",
21
+ "4": "B-REG_CIV_COUNTRYBD",
22
+ "5": "B-REG_CIV_DAD_LASTNAME",
23
+ "6": "B-REG_CIV_DADLUGEXP",
24
+ "7": "B-REG_CIV_DADNAC",
25
+ "8": "B-REG_CIV_DADNAME",
26
+ "9": "B-REG_CIV_DADNUMDOC",
27
+ "10": "B-REG_CIV_DADOC",
28
+ "11": "B-REG_CIV_DEPBD",
29
+ "12": "B-REG_CIV_GENDER",
30
+ "13": "B-REG_CIV_LASTNAME1",
31
+ "14": "B-REG_CIV_LASTNAME2",
32
+ "15": "B-REG_CIV_MAMDOC",
33
+ "16": "B-REG_CIV_MAM_LASTNAME",
34
+ "17": "B-REG_CIV_MAMLUGEXP",
35
+ "18": "B-REG_CIV_MAMNAC",
36
+ "19": "B-REG_CIV_MAMNAME",
37
+ "20": "B-REG_CIV_MAMNUMDOC",
38
+ "21": "B-REG_CIV_NAME",
39
+ "22": "B-REG_CIV_NUIP",
40
+ "23": "B-REG_CIV_REGDATE",
41
+ "24": "B-REG_CIV_RH",
42
+ "25": "B-REG_CIV_SERIAL",
43
+ "26": "I-REG_CIV_BIRTHDATE",
44
+ "27": "I-REG_CIV_CITYBD",
45
+ "28": "I-REG_CIV_CLIN",
46
+ "29": "I-REG_CIV_DAD_LASTNAME",
47
+ "30": "I-REG_CIV_DADLUGEXP",
48
+ "31": "I-REG_CIV_DADNAME",
49
+ "32": "I-REG_CIV_DADOC",
50
+ "33": "I-REG_CIV_DEPBD",
51
+ "34": "I-REG_CIV_MAMDOC",
52
+ "35": "I-REG_CIV_MAM_LASTNAME",
53
+ "36": "I-REG_CIV_MAMLUGEXP",
54
+ "37": "I-REG_CIV_MAMNAME",
55
+ "38": "I-REG_CIV_NAME",
56
+ "39": "I-REG_CIV_REGDATE",
57
+ "40": "O"
58
+ },
59
+ "initializer_range": 0.02,
60
+ "input_size": 224,
61
+ "intermediate_size": 3072,
62
+ "label2id": {
63
+ "B-REG_CIV_BIRTHDATE": 0,
64
+ "B-REG_CIV_BLOOD": 1,
65
+ "B-REG_CIV_CITYBD": 2,
66
+ "B-REG_CIV_CLIN": 3,
67
+ "B-REG_CIV_COUNTRYBD": 4,
68
+ "B-REG_CIV_DADLUGEXP": 6,
69
+ "B-REG_CIV_DADNAC": 7,
70
+ "B-REG_CIV_DADNAME": 8,
71
+ "B-REG_CIV_DADNUMDOC": 9,
72
+ "B-REG_CIV_DADOC": 10,
73
+ "B-REG_CIV_DAD_LASTNAME": 5,
74
+ "B-REG_CIV_DEPBD": 11,
75
+ "B-REG_CIV_GENDER": 12,
76
+ "B-REG_CIV_LASTNAME1": 13,
77
+ "B-REG_CIV_LASTNAME2": 14,
78
+ "B-REG_CIV_MAMDOC": 15,
79
+ "B-REG_CIV_MAMLUGEXP": 17,
80
+ "B-REG_CIV_MAMNAC": 18,
81
+ "B-REG_CIV_MAMNAME": 19,
82
+ "B-REG_CIV_MAMNUMDOC": 20,
83
+ "B-REG_CIV_MAM_LASTNAME": 16,
84
+ "B-REG_CIV_NAME": 21,
85
+ "B-REG_CIV_NUIP": 22,
86
+ "B-REG_CIV_REGDATE": 23,
87
+ "B-REG_CIV_RH": 24,
88
+ "B-REG_CIV_SERIAL": 25,
89
+ "I-REG_CIV_BIRTHDATE": 26,
90
+ "I-REG_CIV_CITYBD": 27,
91
+ "I-REG_CIV_CLIN": 28,
92
+ "I-REG_CIV_DADLUGEXP": 30,
93
+ "I-REG_CIV_DADNAME": 31,
94
+ "I-REG_CIV_DADOC": 32,
95
+ "I-REG_CIV_DAD_LASTNAME": 29,
96
+ "I-REG_CIV_DEPBD": 33,
97
+ "I-REG_CIV_MAMDOC": 34,
98
+ "I-REG_CIV_MAMLUGEXP": 36,
99
+ "I-REG_CIV_MAMNAME": 37,
100
+ "I-REG_CIV_MAM_LASTNAME": 35,
101
+ "I-REG_CIV_NAME": 38,
102
+ "I-REG_CIV_REGDATE": 39,
103
+ "O": 40
104
+ },
105
+ "layer_norm_eps": 1e-05,
106
+ "max_2d_position_embeddings": 1024,
107
+ "max_position_embeddings": 514,
108
+ "max_rel_2d_pos": 256,
109
+ "max_rel_pos": 128,
110
+ "model_type": "layoutlmv3",
111
+ "num_attention_heads": 12,
112
+ "num_channels": 3,
113
+ "num_hidden_layers": 12,
114
+ "pad_token_id": 1,
115
+ "patch_size": 16,
116
+ "rel_2d_pos_bins": 64,
117
+ "rel_pos_bins": 32,
118
+ "second_input_size": 112,
119
+ "shape_size": 128,
120
+ "text_embed": true,
121
+ "torch_dtype": "float32",
122
+ "transformers_version": "4.29.2",
123
+ "type_vocab_size": 1,
124
+ "visual_embed": true,
125
+ "vocab_size": 50265
126
+ }
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 sha256:334fda8226d951d4c53fdb35173d1273dbe31f52fc9f9140b4e2da53d80eec0a
3
+ size 503875377
runs/May23_22-51-39_fe792b229d49/1684882321.0160167/events.out.tfevents.1684882321.fe792b229d49.311.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32fcd13a3004a77b240efca46ce0e39b40ae963e561e32f01370beda88242a76
3
+ size 6037
runs/May23_22-51-39_fe792b229d49/events.out.tfevents.1684882320.fe792b229d49.311.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451ff5bddc4105c57f4750ba87074a3024132b8e004b6d7533b52cf874ae0354
3
+ size 8022
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 sha256:946c686846ca3525efe41032229a9f2d59fd1879534474ddd336a39f3d655978
3
+ size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff