jpino commited on
Commit
82ec078
1 Parent(s): 696d93e

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-ID_BLOOD_TYPE",
18
+ "1": "B-ID_BORN_CITY",
19
+ "2": "B-ID_BORN_DATE",
20
+ "3": "B-ID_EXP_CITY",
21
+ "4": "B-ID_EXP_DATE",
22
+ "5": "B-ID_EXPIRATION_DATE",
23
+ "6": "B-ID_HEIGHT",
24
+ "7": "B-ID_LAST_NAME",
25
+ "8": "B-ID_NAME",
26
+ "9": "B-ID_NATIONALITY",
27
+ "10": "B-ID_NUM",
28
+ "11": "B-ID_SEX",
29
+ "12": "B-ID_TYPE",
30
+ "13": "B-INEMEX_AGE",
31
+ "14": "B-INEMEX_CURP",
32
+ "15": "B-INEMEX_EMI",
33
+ "16": "B-INEMEX_HOME",
34
+ "17": "B-INEMEX_INV",
35
+ "18": "B-INEMEX_KEY",
36
+ "19": "B-INEMEX_REGY",
37
+ "20": "B-INEMEX_VAL",
38
+ "21": "B-PASSP_CODC",
39
+ "22": "B-PASSP_NUM",
40
+ "23": "B-PASSP_TYP",
41
+ "24": "I-ID_BLOOD_TYPE",
42
+ "25": "I-ID_BORN_CITY",
43
+ "26": "I-ID_BORN_DATE",
44
+ "27": "I-ID_EXP_CITY",
45
+ "28": "I-ID_EXP_DATE",
46
+ "29": "I-ID_EXPIRATION_DATE",
47
+ "30": "I-ID_LAST_NAME",
48
+ "31": "I-ID_NAME",
49
+ "32": "I-ID_TYPE",
50
+ "33": "I-INEMEX_CURP",
51
+ "34": "I-INEMEX_HOME",
52
+ "35": "I-INEMEX_REGY",
53
+ "36": "I-INEMEX_VAL",
54
+ "37": "O"
55
+ },
56
+ "initializer_range": 0.02,
57
+ "input_size": 224,
58
+ "intermediate_size": 3072,
59
+ "label2id": {
60
+ "B-ID_BLOOD_TYPE": 0,
61
+ "B-ID_BORN_CITY": 1,
62
+ "B-ID_BORN_DATE": 2,
63
+ "B-ID_EXPIRATION_DATE": 5,
64
+ "B-ID_EXP_CITY": 3,
65
+ "B-ID_EXP_DATE": 4,
66
+ "B-ID_HEIGHT": 6,
67
+ "B-ID_LAST_NAME": 7,
68
+ "B-ID_NAME": 8,
69
+ "B-ID_NATIONALITY": 9,
70
+ "B-ID_NUM": 10,
71
+ "B-ID_SEX": 11,
72
+ "B-ID_TYPE": 12,
73
+ "B-INEMEX_AGE": 13,
74
+ "B-INEMEX_CURP": 14,
75
+ "B-INEMEX_EMI": 15,
76
+ "B-INEMEX_HOME": 16,
77
+ "B-INEMEX_INV": 17,
78
+ "B-INEMEX_KEY": 18,
79
+ "B-INEMEX_REGY": 19,
80
+ "B-INEMEX_VAL": 20,
81
+ "B-PASSP_CODC": 21,
82
+ "B-PASSP_NUM": 22,
83
+ "B-PASSP_TYP": 23,
84
+ "I-ID_BLOOD_TYPE": 24,
85
+ "I-ID_BORN_CITY": 25,
86
+ "I-ID_BORN_DATE": 26,
87
+ "I-ID_EXPIRATION_DATE": 29,
88
+ "I-ID_EXP_CITY": 27,
89
+ "I-ID_EXP_DATE": 28,
90
+ "I-ID_LAST_NAME": 30,
91
+ "I-ID_NAME": 31,
92
+ "I-ID_TYPE": 32,
93
+ "I-INEMEX_CURP": 33,
94
+ "I-INEMEX_HOME": 34,
95
+ "I-INEMEX_REGY": 35,
96
+ "I-INEMEX_VAL": 36,
97
+ "O": 37
98
+ },
99
+ "layer_norm_eps": 1e-05,
100
+ "max_2d_position_embeddings": 1024,
101
+ "max_position_embeddings": 514,
102
+ "max_rel_2d_pos": 256,
103
+ "max_rel_pos": 128,
104
+ "model_type": "layoutlmv3",
105
+ "num_attention_heads": 12,
106
+ "num_channels": 3,
107
+ "num_hidden_layers": 12,
108
+ "pad_token_id": 1,
109
+ "patch_size": 16,
110
+ "rel_2d_pos_bins": 64,
111
+ "rel_pos_bins": 32,
112
+ "second_input_size": 112,
113
+ "shape_size": 128,
114
+ "text_embed": true,
115
+ "torch_dtype": "float32",
116
+ "transformers_version": "4.29.2",
117
+ "type_vocab_size": 1,
118
+ "visual_embed": true,
119
+ "vocab_size": 50265
120
+ }
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 sha256:73b7352f2faeeb85f52e7cacb9865eb5cde46ed212ee80e2de6d6c7f2fcc77e6
3
+ size 503866161
runs/May29_21-01-37_981bda30a681/1685394109.8612416/events.out.tfevents.1685394109.981bda30a681.1010.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bf3a9e1be56973ab49afe3eaf743d35826cb0b79a51564fca8e62ac0b6e39ad
3
+ size 6022
runs/May29_21-01-37_981bda30a681/events.out.tfevents.1685394109.981bda30a681.1010.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01009cb66551596e5536294a5253e937ab727782e75b2130ca34663105919c84
3
+ size 6398
runs/May29_21-02-36_981bda30a681/1685394161.6341276/events.out.tfevents.1685394161.981bda30a681.1010.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94407b454e5f509c090c478194e9ce4af0981de8c3cc936be248669e7e92a2ea
3
+ size 6022
runs/May29_21-02-36_981bda30a681/events.out.tfevents.1685394161.981bda30a681.1010.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f07a0240d6ed3fe949967b1c619905148da027a013234d722b72bb6db632d4ed
3
+ size 7499
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 sha256:2a8e0b5fa9fe8a3f322f91d9e16d4cbd997058543d9900756be256d2e4b84830
3
+ size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff