Hugging Face's logo

ytiriyar
/
layoutlmv2-base-uncased_finetuned_docvqa

Document Question Answering
Transformers
PyTorch
TensorBoard
layoutlmv2
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
2
ytiriyar commited on
Commit
0a0c8e6
•
1 Parent(s): 7125c72

End of training

Browse files
Files changed (20) hide show
  1. .gitignore +1 -0
  2. README.md +57 -0
  3. config.json +132 -0
  4. preprocessor_config.json +14 -0
  5. pytorch_model.bin +3 -0
  6. runs/Apr11_15-11-58_644e8274fca0/1681225942.643384/events.out.tfevents.1681225942.644e8274fca0.8302.1 +3 -0
  7. runs/Apr11_15-11-58_644e8274fca0/events.out.tfevents.1681225942.644e8274fca0.8302.0 +3 -0
  8. runs/Apr11_15-13-43_644e8274fca0/1681226036.5327334/events.out.tfevents.1681226036.644e8274fca0.8302.3 +3 -0
  9. runs/Apr11_15-13-43_644e8274fca0/events.out.tfevents.1681226036.644e8274fca0.8302.2 +3 -0
  10. runs/Apr11_15-15-41_644e8274fca0/1681226148.5671103/events.out.tfevents.1681226148.644e8274fca0.42619.1 +3 -0
  11. runs/Apr11_15-15-41_644e8274fca0/events.out.tfevents.1681226148.644e8274fca0.42619.0 +3 -0
  12. runs/Apr11_15-20-29_644e8274fca0/1681226436.0118668/events.out.tfevents.1681226436.644e8274fca0.42619.3 +3 -0
  13. runs/Apr11_15-20-29_644e8274fca0/events.out.tfevents.1681226436.644e8274fca0.42619.2 +3 -0
  14. runs/Apr11_15-22-09_644e8274fca0/1681226533.6967654/events.out.tfevents.1681226533.644e8274fca0.44597.1 +3 -0
  15. runs/Apr11_15-22-09_644e8274fca0/events.out.tfevents.1681226533.644e8274fca0.44597.0 +3 -0
  16. special_tokens_map.json +7 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +37 -0
  19. training_args.bin +3 -0
  20. vocab.txt +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: layoutlmv2-base-uncased_finetuned_docvqa
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # layoutlmv2-base-uncased_finetuned_docvqa
14
+
15
+ This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 4.3167
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 0.5
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 5.4213 | 0.22 | 50 | 4.6420 |
49
+ | 4.513 | 0.44 | 100 | 4.3167 |
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.27.4
55
+ - Pytorch 2.0.0+cu118
56
+ - Datasets 2.11.0
57
+ - Tokenizers 0.13.3
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": "4.27.4",
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:fc3665a577e2d114769f3c829c254b6ff0509031210afff8aa91ca761fa86088
3
+ size 802209085
runs/Apr11_15-11-58_644e8274fca0/1681225942.643384/events.out.tfevents.1681225942.644e8274fca0.8302.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722359c9b115159a330b809e885e1eb93f58a12842398a586c46af010bcd38ea
3
+ size 5913
runs/Apr11_15-11-58_644e8274fca0/events.out.tfevents.1681225942.644e8274fca0.8302.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52ee6df89407b1d39a0863970bc8a32fda171190e99c4058ef92a2849293f8a
3
+ size 4184
runs/Apr11_15-13-43_644e8274fca0/1681226036.5327334/events.out.tfevents.1681226036.644e8274fca0.8302.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:249e12b144e576ce54d66d56d40fdedef06f1dd3328cc66cc9b89f554fb1da1a
3
+ size 5913
runs/Apr11_15-13-43_644e8274fca0/events.out.tfevents.1681226036.644e8274fca0.8302.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c96026f53b88ef3ad076fd3d09d93ceee2a560641a86dbfcf66ab71aba5bbe
3
+ size 4184
runs/Apr11_15-15-41_644e8274fca0/1681226148.5671103/events.out.tfevents.1681226148.644e8274fca0.42619.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1affd152c6adce6235770ba923f5b7fba6a208e2d6989995327a292dae014f0
3
+ size 5913
runs/Apr11_15-15-41_644e8274fca0/events.out.tfevents.1681226148.644e8274fca0.42619.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e202ebba9daa1eb63f60bbaf064db952601e03ba247790cc4bab615169c45a
3
+ size 6068
runs/Apr11_15-20-29_644e8274fca0/1681226436.0118668/events.out.tfevents.1681226436.644e8274fca0.42619.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04a7e4b0dbb3bcc98ae815f6786a033b445a94468b276732dad30dfbdc069ec1
3
+ size 5913
runs/Apr11_15-20-29_644e8274fca0/events.out.tfevents.1681226436.644e8274fca0.42619.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:025f6c95a7184bae4d0f08265865a4e3f01c739e50c28890f08f1e62a2597ef4
3
+ size 4184
runs/Apr11_15-22-09_644e8274fca0/1681226533.6967654/events.out.tfevents.1681226533.644e8274fca0.44597.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a350e3d5d035fffaca674fd0bd30b18836748e464073ce0d5355b26a82780f2d
3
+ size 5913
runs/Apr11_15-22-09_644e8274fca0/events.out.tfevents.1681226533.644e8274fca0.44597.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9cb7b922db3a06c1dbe758d5d87c81dbca222a810ad2e52b740239d6b8b1a8
3
+ size 7258
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 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "processor_class": "LayoutLMv2Processor",
25
+ "sep_token": "[SEP]",
26
+ "sep_token_box": [
27
+ 1000,
28
+ 1000,
29
+ 1000,
30
+ 1000
31
+ ],
32
+ "special_tokens_map_file": null,
33
+ "strip_accents": null,
34
+ "tokenize_chinese_chars": true,
35
+ "tokenizer_class": "LayoutLMv2Tokenizer",
36
+ "unk_token": "[UNK]"
37
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be802d34add36415db50c7597f2c00b9e20b7949a75b17f543f856152fdc1ac8
3
+ size 3579
vocab.txt ADDED
The diff for this file is too large to render. See raw diff