Hugging Face's logo

zibajoon
/
20231101_layoutlm2_1.2k_3ep_Doc_A

Document Question Answering
Transformers
PyTorch
layoutlmv2
Generated from Trainer
Inference Endpoints
Model card Files Community
zibajoon commited on
Commit
cc86fc9
•
1 Parent(s): 11e0f14

End of training

Browse files
Files changed (9) hide show
  1. README.md +146 -0
  2. config.json +132 -0
  3. preprocessor_config.json +14 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +37 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +79 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ base_model: microsoft/layoutlmv2-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: layoutlmv2-base-uncased_finetuned_docvqa
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # layoutlmv2-base-uncased_finetuned_docvqa
15
+
16
+ This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 4.8270
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 20
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 5.2536 | 0.22 | 50 | 4.4585 |
50
+ | 4.2935 | 0.44 | 100 | 4.1809 |
51
+ | 4.0821 | 0.66 | 150 | 3.7822 |
52
+ | 3.8393 | 0.88 | 200 | 3.4892 |
53
+ | 3.4613 | 1.11 | 250 | 3.4728 |
54
+ | 2.9792 | 1.33 | 300 | 3.0083 |
55
+ | 2.9501 | 1.55 | 350 | 2.9516 |
56
+ | 2.8889 | 1.77 | 400 | 2.7119 |
57
+ | 2.4728 | 1.99 | 450 | 2.6027 |
58
+ | 1.9523 | 2.21 | 500 | 2.5411 |
59
+ | 1.9312 | 2.43 | 550 | 2.5406 |
60
+ | 1.8471 | 2.65 | 600 | 2.4484 |
61
+ | 1.7456 | 2.88 | 650 | 1.9633 |
62
+ | 1.4404 | 3.1 | 700 | 2.5037 |
63
+ | 1.3567 | 3.32 | 750 | 2.4763 |
64
+ | 1.3247 | 3.54 | 800 | 2.3191 |
65
+ | 1.2739 | 3.76 | 850 | 2.4416 |
66
+ | 1.2548 | 3.98 | 900 | 2.3970 |
67
+ | 0.8073 | 4.2 | 950 | 2.3073 |
68
+ | 0.8992 | 4.42 | 1000 | 2.6353 |
69
+ | 0.8439 | 4.65 | 1050 | 2.7353 |
70
+ | 0.9051 | 4.87 | 1100 | 2.4587 |
71
+ | 0.7201 | 5.09 | 1150 | 3.1759 |
72
+ | 0.6394 | 5.31 | 1200 | 3.2409 |
73
+ | 0.6142 | 5.53 | 1250 | 3.0543 |
74
+ | 0.6385 | 5.75 | 1300 | 2.5017 |
75
+ | 0.5985 | 5.97 | 1350 | 3.1824 |
76
+ | 0.2824 | 6.19 | 1400 | 3.3628 |
77
+ | 0.4695 | 6.42 | 1450 | 2.9493 |
78
+ | 0.6322 | 6.64 | 1500 | 2.8337 |
79
+ | 0.5114 | 6.86 | 1550 | 3.2387 |
80
+ | 0.4555 | 7.08 | 1600 | 3.3994 |
81
+ | 0.3308 | 7.3 | 1650 | 3.3562 |
82
+ | 0.2209 | 7.52 | 1700 | 3.5050 |
83
+ | 0.4407 | 7.74 | 1750 | 3.8571 |
84
+ | 0.442 | 7.96 | 1800 | 3.5946 |
85
+ | 0.2722 | 8.19 | 1850 | 3.6526 |
86
+ | 0.423 | 8.41 | 1900 | 3.1283 |
87
+ | 0.316 | 8.63 | 1950 | 3.4300 |
88
+ | 0.3435 | 8.85 | 2000 | 3.6418 |
89
+ | 0.2815 | 9.07 | 2050 | 3.4021 |
90
+ | 0.2051 | 9.29 | 2100 | 3.7000 |
91
+ | 0.2442 | 9.51 | 2150 | 3.4389 |
92
+ | 0.1833 | 9.73 | 2200 | 3.7243 |
93
+ | 0.2408 | 9.96 | 2250 | 3.6520 |
94
+ | 0.1971 | 10.18 | 2300 | 3.5589 |
95
+ | 0.196 | 10.4 | 2350 | 3.7747 |
96
+ | 0.2511 | 10.62 | 2400 | 3.5574 |
97
+ | 0.1473 | 10.84 | 2450 | 3.7469 |
98
+ | 0.1141 | 11.06 | 2500 | 3.7303 |
99
+ | 0.1058 | 11.28 | 2550 | 4.0495 |
100
+ | 0.1845 | 11.5 | 2600 | 3.8454 |
101
+ | 0.1548 | 11.73 | 2650 | 4.2611 |
102
+ | 0.1009 | 11.95 | 2700 | 4.1706 |
103
+ | 0.1412 | 12.17 | 2750 | 4.2072 |
104
+ | 0.0809 | 12.39 | 2800 | 4.2862 |
105
+ | 0.1126 | 12.61 | 2850 | 4.0895 |
106
+ | 0.0736 | 12.83 | 2900 | 4.2500 |
107
+ | 0.0525 | 13.05 | 2950 | 4.3110 |
108
+ | 0.0621 | 13.27 | 3000 | 4.1005 |
109
+ | 0.1199 | 13.5 | 3050 | 4.1956 |
110
+ | 0.0837 | 13.72 | 3100 | 4.6910 |
111
+ | 0.1912 | 13.94 | 3150 | 4.2988 |
112
+ | 0.0891 | 14.16 | 3200 | 4.3609 |
113
+ | 0.0478 | 14.38 | 3250 | 4.3829 |
114
+ | 0.0727 | 14.6 | 3300 | 4.2299 |
115
+ | 0.1063 | 14.82 | 3350 | 3.9861 |
116
+ | 0.0392 | 15.04 | 3400 | 4.1840 |
117
+ | 0.1334 | 15.27 | 3450 | 4.3275 |
118
+ | 0.0178 | 15.49 | 3500 | 4.3959 |
119
+ | 0.0917 | 15.71 | 3550 | 4.4633 |
120
+ | 0.0477 | 15.93 | 3600 | 4.5239 |
121
+ | 0.0058 | 16.15 | 3650 | 4.5556 |
122
+ | 0.0719 | 16.37 | 3700 | 4.5381 |
123
+ | 0.0412 | 16.59 | 3750 | 4.5468 |
124
+ | 0.0051 | 16.81 | 3800 | 4.6192 |
125
+ | 0.0437 | 17.04 | 3850 | 4.6033 |
126
+ | 0.0062 | 17.26 | 3900 | 4.7104 |
127
+ | 0.0374 | 17.48 | 3950 | 4.5678 |
128
+ | 0.0113 | 17.7 | 4000 | 4.6266 |
129
+ | 0.0616 | 17.92 | 4050 | 4.6180 |
130
+ | 0.0082 | 18.14 | 4100 | 4.7478 |
131
+ | 0.0034 | 18.36 | 4150 | 4.7665 |
132
+ | 0.0395 | 18.58 | 4200 | 4.7568 |
133
+ | 0.0108 | 18.81 | 4250 | 4.7385 |
134
+ | 0.015 | 19.03 | 4300 | 4.8266 |
135
+ | 0.1061 | 19.25 | 4350 | 4.8090 |
136
+ | 0.0181 | 19.47 | 4400 | 4.8226 |
137
+ | 0.0055 | 19.69 | 4450 | 4.8228 |
138
+ | 0.0134 | 19.91 | 4500 | 4.8270 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - Transformers 4.34.1
144
+ - Pytorch 2.0.1+cu118
145
+ - Datasets 2.10.1
146
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv2-base-uncased",
3
+ "architectures": [
4
+ "LayoutLMv2ForQuestionAnswering"
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": true,
105
+ "hidden_act": "gelu",
106
+ "hidden_dropout_prob": 0.1,
107
+ "hidden_size": 768,
108
+ "image_feature_pool_shape": [
109
+ 7,
110
+ 7,
111
+ 256
112
+ ],
113
+ "initializer_range": 0.02,
114
+ "intermediate_size": 3072,
115
+ "layer_norm_eps": 1e-12,
116
+ "max_2d_position_embeddings": 1024,
117
+ "max_position_embeddings": 512,
118
+ "max_rel_2d_pos": 256,
119
+ "max_rel_pos": 128,
120
+ "model_type": "layoutlmv2",
121
+ "num_attention_heads": 12,
122
+ "num_hidden_layers": 12,
123
+ "output_past": true,
124
+ "pad_token_id": 0,
125
+ "rel_2d_pos_bins": 64,
126
+ "rel_pos_bins": 32,
127
+ "shape_size": 128,
128
+ "torch_dtype": "float32",
129
+ "transformers_version": "4.34.1",
130
+ "type_vocab_size": 2,
131
+ "vocab_size": 30522
132
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "LayoutLMv2FeatureExtractor",
5
+ "image_processor_type": "LayoutLMv2ImageProcessor",
6
+ "ocr_lang": null,
7
+ "processor_class": "LayoutLMv2Processor",
8
+ "resample": 2,
9
+ "size": {
10
+ "height": 224,
11
+ "width": 224
12
+ },
13
+ "tesseract_config": ""
14
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:537889adc89e74262aece47b6bf77f8c8e8ca5e38f09041b0ee9283952be66b3
3
+ size 802214001
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 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "cls_token_box": [
48
+ 0,
49
+ 0,
50
+ 0,
51
+ 0
52
+ ],
53
+ "do_basic_tokenize": true,
54
+ "do_lower_case": true,
55
+ "mask_token": "[MASK]",
56
+ "model_max_length": 512,
57
+ "never_split": null,
58
+ "only_label_first_subword": true,
59
+ "pad_token": "[PAD]",
60
+ "pad_token_box": [
61
+ 0,
62
+ 0,
63
+ 0,
64
+ 0
65
+ ],
66
+ "pad_token_label": -100,
67
+ "processor_class": "LayoutLMv2Processor",
68
+ "sep_token": "[SEP]",
69
+ "sep_token_box": [
70
+ 1000,
71
+ 1000,
72
+ 1000,
73
+ 1000
74
+ ],
75
+ "strip_accents": null,
76
+ "tokenize_chinese_chars": true,
77
+ "tokenizer_class": "LayoutLMv2Tokenizer",
78
+ "unk_token": "[UNK]"
79
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9729ab24fed2ce82bf2b2262508ac31e152eaaf1aa9a43c65ae556b737552257
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff