Hugging Face's logo

ProtoFaze
/
layoutlmv2_output

Token Classification
Transformers
Safetensors
layoutlmv2
Generated from Trainer
Model card Files
xet
 Community
ProtoFaze commited on
Commit
8449c74
·
verified ·
1 Parent(s): 7656d34

End of training

Browse files
Files changed (8) hide show
  1. README.md +71 -0
  2. config.json +187 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +80 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-sa-4.0
4
+ base_model: microsoft/layoutlmv2-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: layoutlmv2_output
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # layoutlmv2_output
21
+
22
+ This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.3471
25
+ - Precision: 0.8712
26
+ - Recall: 0.8742
27
+ - F1: 0.8727
28
+ - Accuracy: 0.9288
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 5e-05
48
+ - train_batch_size: 2
49
+ - eval_batch_size: 2
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 5
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.3415 | 0.8772 | 500 | 0.4834 | 0.8227 | 0.8343 | 0.8285 | 0.8966 |
60
+ | 0.228 | 1.7544 | 1000 | 0.3607 | 0.8591 | 0.8528 | 0.8559 | 0.9170 |
61
+ | 0.1769 | 2.6316 | 1500 | 0.3408 | 0.8571 | 0.8556 | 0.8563 | 0.9208 |
62
+ | 0.1183 | 3.5088 | 2000 | 0.3570 | 0.8661 | 0.8579 | 0.8620 | 0.9208 |
63
+ | 0.0915 | 4.3860 | 2500 | 0.3603 | 0.8644 | 0.8702 | 0.8673 | 0.9256 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.51.3
69
+ - Pytorch 2.7.0+cu126
70
+ - Datasets 3.6.0
71
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LayoutLMv2ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "convert_sync_batchnorm": true,
7
+ "coordinate_size": 128,
8
+ "detectron2_config_args": {
9
+ "MODEL.ANCHOR_GENERATOR.SIZES": [
10
+ [
11
+ 32
12
+ ],
13
+ [
14
+ 64
15
+ ],
16
+ [
17
+ 128
18
+ ],
19
+ [
20
+ 256
21
+ ],
22
+ [
23
+ 512
24
+ ]
25
+ ],
26
+ "MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
27
+ "MODEL.FPN.IN_FEATURES": [
28
+ "res2",
29
+ "res3",
30
+ "res4",
31
+ "res5"
32
+ ],
33
+ "MODEL.MASK_ON": true,
34
+ "MODEL.PIXEL_STD": [
35
+ 57.375,
36
+ 57.12,
37
+ 58.395
38
+ ],
39
+ "MODEL.POST_NMS_TOPK_TEST": 1000,
40
+ "MODEL.RESNETS.ASPECT_RATIOS": [
41
+ [
42
+ 0.5,
43
+ 1.0,
44
+ 2.0
45
+ ]
46
+ ],
47
+ "MODEL.RESNETS.DEPTH": 101,
48
+ "MODEL.RESNETS.NUM_GROUPS": 32,
49
+ "MODEL.RESNETS.OUT_FEATURES": [
50
+ "res2",
51
+ "res3",
52
+ "res4",
53
+ "res5"
54
+ ],
55
+ "MODEL.RESNETS.SIZES": [
56
+ [
57
+ 32
58
+ ],
59
+ [
60
+ 64
61
+ ],
62
+ [
63
+ 128
64
+ ],
65
+ [
66
+ 256
67
+ ],
68
+ [
69
+ 512
70
+ ]
71
+ ],
72
+ "MODEL.RESNETS.STRIDE_IN_1X1": false,
73
+ "MODEL.RESNETS.WIDTH_PER_GROUP": 8,
74
+ "MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
75
+ "MODEL.ROI_BOX_HEAD.NUM_FC": 2,
76
+ "MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
77
+ "MODEL.ROI_HEADS.IN_FEATURES": [
78
+ "p2",
79
+ "p3",
80
+ "p4",
81
+ "p5"
82
+ ],
83
+ "MODEL.ROI_HEADS.NAME": "StandardROIHeads",
84
+ "MODEL.ROI_HEADS.NUM_CLASSES": 5,
85
+ "MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
86
+ "MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
87
+ "MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
88
+ "MODEL.RPN.IN_FEATURES": [
89
+ "p2",
90
+ "p3",
91
+ "p4",
92
+ "p5",
93
+ "p6"
94
+ ],
95
+ "MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
96
+ "MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
97
+ "MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
98
+ },
99
+ "fast_qkv": true,
100
+ "gradient_checkpointing": false,
101
+ "has_relative_attention_bias": true,
102
+ "has_spatial_attention_bias": true,
103
+ "has_visual_segment_embedding": false,
104
+ "hidden_act": "gelu",
105
+ "hidden_dropout_prob": 0.1,
106
+ "hidden_size": 768,
107
+ "id2label": {
108
+ "0": "Ignore",
109
+ "1": "Store_name_value",
110
+ "2": "Store_name_key",
111
+ "3": "Store_addr_value",
112
+ "4": "Store_addr_key",
113
+ "5": "Tel_value",
114
+ "6": "Tel_key",
115
+ "7": "Date_value",
116
+ "8": "Date_key",
117
+ "9": "Time_value",
118
+ "10": "Time_key",
119
+ "11": "Prod_item_value",
120
+ "12": "Prod_item_key",
121
+ "13": "Prod_quantity_value",
122
+ "14": "Prod_quantity_key",
123
+ "15": "Prod_price_value",
124
+ "16": "Prod_price_key",
125
+ "17": "Subtotal_value",
126
+ "18": "Subtotal_key",
127
+ "19": "Tax_value",
128
+ "20": "Tax_key",
129
+ "21": "Tips_value",
130
+ "22": "Tips_key",
131
+ "23": "Total_value",
132
+ "24": "Total_key",
133
+ "25": "Others"
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
+ "Date_key": 8,
144
+ "Date_value": 7,
145
+ "Ignore": 0,
146
+ "Others": 25,
147
+ "Prod_item_key": 12,
148
+ "Prod_item_value": 11,
149
+ "Prod_price_key": 16,
150
+ "Prod_price_value": 15,
151
+ "Prod_quantity_key": 14,
152
+ "Prod_quantity_value": 13,
153
+ "Store_addr_key": 4,
154
+ "Store_addr_value": 3,
155
+ "Store_name_key": 2,
156
+ "Store_name_value": 1,
157
+ "Subtotal_key": 18,
158
+ "Subtotal_value": 17,
159
+ "Tax_key": 20,
160
+ "Tax_value": 19,
161
+ "Tel_key": 6,
162
+ "Tel_value": 5,
163
+ "Time_key": 10,
164
+ "Time_value": 9,
165
+ "Tips_key": 22,
166
+ "Tips_value": 21,
167
+ "Total_key": 24,
168
+ "Total_value": 23
169
+ },
170
+ "layer_norm_eps": 1e-12,
171
+ "max_2d_position_embeddings": 1024,
172
+ "max_position_embeddings": 512,
173
+ "max_rel_2d_pos": 256,
174
+ "max_rel_pos": 128,
175
+ "model_type": "layoutlmv2",
176
+ "num_attention_heads": 12,
177
+ "num_hidden_layers": 12,
178
+ "output_past": true,
179
+ "pad_token_id": 0,
180
+ "rel_2d_pos_bins": 64,
181
+ "rel_pos_bins": 32,
182
+ "shape_size": 128,
183
+ "torch_dtype": "float32",
184
+ "transformers_version": "4.51.3",
185
+ "type_vocab_size": 2,
186
+ "vocab_size": 30522
187
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fd7a24602a657a83cc8f2465e73b44461de8eba0e12b1e52ea3b2216389255a
3
+ size 802124384
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": false,
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
+ "extra_special_tokens": {},
57
+ "mask_token": "[MASK]",
58
+ "model_max_length": 512,
59
+ "never_split": null,
60
+ "only_label_first_subword": true,
61
+ "pad_token": "[PAD]",
62
+ "pad_token_box": [
63
+ 0,
64
+ 0,
65
+ 0,
66
+ 0
67
+ ],
68
+ "pad_token_label": -100,
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 sha256:7ec9cab58bea78eff5719c45da43340ffcee6f1ecb1456bd8d36fd9957ca192f
3
+ size 5649
vocab.txt ADDED
The diff for this file is too large to render. See raw diff