Hugging Face's logo

Sebabrata
/
lmv2-g-rai-auth-02-14

Token Classification
Transformers
PyTorch
TensorBoard
layoutlmv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Sebabrata commited on
Commit
a875a14
•
1 Parent(s): 2e87aae

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. .gitignore +1 -0
  2. config.json +186 -0
  3. pytorch_model.bin +3 -0
  4. runs/Feb14_11-03-28_38010830aef8/1676372955.9861891/events.out.tfevents.1676372955.38010830aef8.622.1 +3 -0
  5. runs/Feb14_11-03-28_38010830aef8/events.out.tfevents.1676372955.38010830aef8.622.0 +3 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +36 -0
  9. training_args.bin +3 -0
  10. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv2-base-uncased",
3
+ "architectures": [
4
+ "LayoutLMv2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "convert_sync_batchnorm": true,
8
+ "coordinate_size": 128,
9
+ "detectron2_config_args": {
10
+ "MODEL.ANCHOR_GENERATOR.SIZES": [
11
+ [
12
+ 32
13
+ ],
14
+ [
15
+ 64
16
+ ],
17
+ [
18
+ 128
19
+ ],
20
+ [
21
+ 256
22
+ ],
23
+ [
24
+ 512
25
+ ]
26
+ ],
27
+ "MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
28
+ "MODEL.FPN.IN_FEATURES": [
29
+ "res2",
30
+ "res3",
31
+ "res4",
32
+ "res5"
33
+ ],
34
+ "MODEL.MASK_ON": true,
35
+ "MODEL.PIXEL_STD": [
36
+ 57.375,
37
+ 57.12,
38
+ 58.395
39
+ ],
40
+ "MODEL.POST_NMS_TOPK_TEST": 1000,
41
+ "MODEL.RESNETS.ASPECT_RATIOS": [
42
+ [
43
+ 0.5,
44
+ 1.0,
45
+ 2.0
46
+ ]
47
+ ],
48
+ "MODEL.RESNETS.DEPTH": 101,
49
+ "MODEL.RESNETS.NUM_GROUPS": 32,
50
+ "MODEL.RESNETS.OUT_FEATURES": [
51
+ "res2",
52
+ "res3",
53
+ "res4",
54
+ "res5"
55
+ ],
56
+ "MODEL.RESNETS.SIZES": [
57
+ [
58
+ 32
59
+ ],
60
+ [
61
+ 64
62
+ ],
63
+ [
64
+ 128
65
+ ],
66
+ [
67
+ 256
68
+ ],
69
+ [
70
+ 512
71
+ ]
72
+ ],
73
+ "MODEL.RESNETS.STRIDE_IN_1X1": false,
74
+ "MODEL.RESNETS.WIDTH_PER_GROUP": 8,
75
+ "MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
76
+ "MODEL.ROI_BOX_HEAD.NUM_FC": 2,
77
+ "MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
78
+ "MODEL.ROI_HEADS.IN_FEATURES": [
79
+ "p2",
80
+ "p3",
81
+ "p4",
82
+ "p5"
83
+ ],
84
+ "MODEL.ROI_HEADS.NAME": "StandardROIHeads",
85
+ "MODEL.ROI_HEADS.NUM_CLASSES": 5,
86
+ "MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
87
+ "MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
88
+ "MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
89
+ "MODEL.RPN.IN_FEATURES": [
90
+ "p2",
91
+ "p3",
92
+ "p4",
93
+ "p5",
94
+ "p6"
95
+ ],
96
+ "MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
97
+ "MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
98
+ "MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
99
+ },
100
+ "fast_qkv": true,
101
+ "gradient_checkpointing": false,
102
+ "has_relative_attention_bias": true,
103
+ "has_spatial_attention_bias": true,
104
+ "has_visual_segment_embedding": false,
105
+ "hidden_act": "gelu",
106
+ "hidden_dropout_prob": 0.1,
107
+ "hidden_size": 768,
108
+ "id2label": {
109
+ "0": "I-PATIENT_NAME_KEY",
110
+ "1": "I-PROVIDER_NAME_KEY",
111
+ "2": "S-DOB_KEY",
112
+ "3": "S-PATIENT_NAME_KEY",
113
+ "4": "B-PATIENT_NAME_KEY",
114
+ "5": "E-PROVIDER_NAME_VALUE",
115
+ "6": "I-PATIENT_NAME_VALUE",
116
+ "7": "E-DOB_VALUE",
117
+ "8": "B-PROVIDER_NAME_VALUE",
118
+ "9": "E-PATIENT_NAME_VALUE",
119
+ "10": "B-PROVIDER_NAME_KEY",
120
+ "11": "E-DOB_KEY",
121
+ "12": "S-PROVIDER_NAME_KEY",
122
+ "13": "B-DOB_KEY",
123
+ "14": "S-DOB_VALUE",
124
+ "15": "I-DOB_KEY",
125
+ "16": "E-PROVIDER_NAME_KEY",
126
+ "17": "I-DOB_VALUE",
127
+ "18": "B-PATIENT_NAME_VALUE",
128
+ "19": "I-PROVIDER_NAME_VALUE",
129
+ "20": "B-DOB_VALUE",
130
+ "21": "E-PATIENT_NAME_KEY",
131
+ "22": "S-PATIENT_NAME_VALUE",
132
+ "23": "S-PROVIDER_NAME_VALUE",
133
+ "24": "O"
134
+ },
135
+ "image_feature_pool_shape": [
136
+ 7,
137
+ 7,
138
+ 256
139
+ ],
140
+ "initializer_range": 0.02,
141
+ "intermediate_size": 3072,
142
+ "label2id": {
143
+ "B-DOB_KEY": 13,
144
+ "B-DOB_VALUE": 20,
145
+ "B-PATIENT_NAME_KEY": 4,
146
+ "B-PATIENT_NAME_VALUE": 18,
147
+ "B-PROVIDER_NAME_KEY": 10,
148
+ "B-PROVIDER_NAME_VALUE": 8,
149
+ "E-DOB_KEY": 11,
150
+ "E-DOB_VALUE": 7,
151
+ "E-PATIENT_NAME_KEY": 21,
152
+ "E-PATIENT_NAME_VALUE": 9,
153
+ "E-PROVIDER_NAME_KEY": 16,
154
+ "E-PROVIDER_NAME_VALUE": 5,
155
+ "I-DOB_KEY": 15,
156
+ "I-DOB_VALUE": 17,
157
+ "I-PATIENT_NAME_KEY": 0,
158
+ "I-PATIENT_NAME_VALUE": 6,
159
+ "I-PROVIDER_NAME_KEY": 1,
160
+ "I-PROVIDER_NAME_VALUE": 19,
161
+ "O": 24,
162
+ "S-DOB_KEY": 2,
163
+ "S-DOB_VALUE": 14,
164
+ "S-PATIENT_NAME_KEY": 3,
165
+ "S-PATIENT_NAME_VALUE": 22,
166
+ "S-PROVIDER_NAME_KEY": 12,
167
+ "S-PROVIDER_NAME_VALUE": 23
168
+ },
169
+ "layer_norm_eps": 1e-12,
170
+ "max_2d_position_embeddings": 1024,
171
+ "max_position_embeddings": 512,
172
+ "max_rel_2d_pos": 256,
173
+ "max_rel_pos": 128,
174
+ "model_type": "layoutlmv2",
175
+ "num_attention_heads": 12,
176
+ "num_hidden_layers": 12,
177
+ "output_past": true,
178
+ "pad_token_id": 0,
179
+ "rel_2d_pos_bins": 64,
180
+ "rel_pos_bins": 32,
181
+ "shape_size": 128,
182
+ "torch_dtype": "float32",
183
+ "transformers_version": "4.27.0.dev0",
184
+ "type_vocab_size": 2,
185
+ "vocab_size": 30522
186
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c01ade097dbad1d0396e3d93862a2c49786956ed3a86b3fabb0bb4f1a23cecf
3
+ size 802286393
runs/Feb14_11-03-28_38010830aef8/1676372955.9861891/events.out.tfevents.1676372955.38010830aef8.622.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d61326af96ffa06a59d201bd414f0a2b1d68149a63e6d9ca61f58f321d563d5d
3
+ size 5818
runs/Feb14_11-03-28_38010830aef8/events.out.tfevents.1676372955.38010830aef8.622.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d999d3b85fd7c54846b46b0de6caaba2ddc97bf51bf7fff5b41592534347bb5
3
+ size 9658
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "cls_token": "[CLS]",
4
+ "cls_token_box": [
5
+ 0,
6
+ 0,
7
+ 0,
8
+ 0
9
+ ],
10
+ "do_basic_tokenize": true,
11
+ "do_lower_case": true,
12
+ "mask_token": "[MASK]",
13
+ "model_max_length": 512,
14
+ "never_split": null,
15
+ "only_label_first_subword": true,
16
+ "pad_token": "[PAD]",
17
+ "pad_token_box": [
18
+ 0,
19
+ 0,
20
+ 0,
21
+ 0
22
+ ],
23
+ "pad_token_label": -100,
24
+ "sep_token": "[SEP]",
25
+ "sep_token_box": [
26
+ 1000,
27
+ 1000,
28
+ 1000,
29
+ 1000
30
+ ],
31
+ "special_tokens_map_file": null,
32
+ "strip_accents": null,
33
+ "tokenize_chinese_chars": true,
34
+ "tokenizer_class": "LayoutLMv2Tokenizer",
35
+ "unk_token": "[UNK]"
36
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6292e65c0e4947fbda8f4cca2865a8f7ae12cb233968bc2401637ce017dcd4da
3
+ size 3579
vocab.txt ADDED
The diff for this file is too large to render. See raw diff