prajwalJumde commited on
Commit
1f8a01b
1 Parent(s): 08402d0

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "other",
18
+ "1": "what is the DOS or D.O.S?",
19
+ "2": "what is the service date or date of service?",
20
+ "3": "what is the admit date or admission date?",
21
+ "4": "what is the visit date or date of visit?",
22
+ "5": "What is signature date or signed on date?",
23
+ "6": "what is the DOB or date of birth?",
24
+ "7": "What is the diagnosis or What is the disease?",
25
+ "8": "What is Doctor Name or Physician Name?",
26
+ "9": "What is the patient name?",
27
+ "10": "What is the facility name?",
28
+ "11": "What is the Date of Evaluation?",
29
+ "12": "What is the Date of operation?",
30
+ "13": "What is the Procedure Date?",
31
+ "14": "What is the Date of Exam or Examination date?",
32
+ "15": "What is the Date of Draw?",
33
+ "16": "What is the Date of collection?",
34
+ "17": "What is the Date of Consultation?",
35
+ "18": "What is the Date of Encounter or Enc Date?",
36
+ "19": "What is the Date of registration Reg Date?",
37
+ "20": "What is the Date of Daily Notes?",
38
+ "21": "What is the Date of Injury or DOI?",
39
+ "22": "What is the Date of Discharge?"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "input_size": 224,
43
+ "intermediate_size": 3072,
44
+ "label2id": {
45
+ "What is Doctor Name or Physician Name?": 8,
46
+ "What is signature date or signed on date?": 5,
47
+ "What is the Date of Consultation?": 17,
48
+ "What is the Date of Daily Notes?": 20,
49
+ "What is the Date of Discharge?": 22,
50
+ "What is the Date of Draw?": 15,
51
+ "What is the Date of Encounter or Enc Date?": 18,
52
+ "What is the Date of Evaluation?": 11,
53
+ "What is the Date of Exam or Examination date?": 14,
54
+ "What is the Date of Injury or DOI?": 21,
55
+ "What is the Date of collection?": 16,
56
+ "What is the Date of operation?": 12,
57
+ "What is the Date of registration Reg Date?": 19,
58
+ "What is the Procedure Date?": 13,
59
+ "What is the diagnosis or What is the disease?": 7,
60
+ "What is the facility name?": 10,
61
+ "What is the patient name?": 9,
62
+ "other": 0,
63
+ "what is the DOB or date of birth?": 6,
64
+ "what is the DOS or D.O.S?": 1,
65
+ "what is the admit date or admission date?": 3,
66
+ "what is the service date or date of service?": 2,
67
+ "what is the visit date or date of visit?": 4
68
+ },
69
+ "layer_norm_eps": 1e-05,
70
+ "max_2d_position_embeddings": 1024,
71
+ "max_position_embeddings": 514,
72
+ "max_rel_2d_pos": 256,
73
+ "max_rel_pos": 128,
74
+ "model_type": "layoutlmv3",
75
+ "num_attention_heads": 12,
76
+ "num_channels": 3,
77
+ "num_hidden_layers": 12,
78
+ "pad_token_id": 1,
79
+ "patch_size": 16,
80
+ "rel_2d_pos_bins": 64,
81
+ "rel_pos_bins": 32,
82
+ "second_input_size": 112,
83
+ "shape_size": 128,
84
+ "text_embed": true,
85
+ "torch_dtype": "float32",
86
+ "transformers_version": "4.34.0.dev0",
87
+ "type_vocab_size": 1,
88
+ "visual_embed": true,
89
+ "vocab_size": 50265
90
+ }
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 sha256:32a758a3f1863bfdde4b26ae66edca00cda93136e861317c1f5a5531fad9487f
3
+ size 503815533
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:ae6c07c331b89a720f7f4a23e7095c9cfd5a0e3a3c9c61a32d0715c795b06431
3
+ size 4091
vocab.json ADDED
The diff for this file is too large to render. See raw diff