vfu commited on
Commit
a67febb
1 Parent(s): 10268b1

End of training

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ base_model: microsoft/layoutlmv2-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - generator
8
+ model-index:
9
+ - name: ccc_doc_vqa_test
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # ccc_doc_vqa_test
17
+
18
+ This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on the generator dataset.
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
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.33.2
52
+ - Pytorch 2.0.1
53
+ - Datasets 2.14.5
54
+ - 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": "4.33.2",
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 sha256:804f5a3afbc4dbbc092fe6402792f5326e66f019974dfb9ed573e0d5fda139d7
3
+ size 802204017
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
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "cls_token_box": [
6
+ 0,
7
+ 0,
8
+ 0,
9
+ 0
10
+ ],
11
+ "do_basic_tokenize": true,
12
+ "do_lower_case": true,
13
+ "mask_token": "[MASK]",
14
+ "model_max_length": 512,
15
+ "never_split": null,
16
+ "only_label_first_subword": true,
17
+ "pad_token": "[PAD]",
18
+ "pad_token_box": [
19
+ 0,
20
+ 0,
21
+ 0,
22
+ 0
23
+ ],
24
+ "pad_token_label": -100,
25
+ "processor_class": "LayoutLMv2Processor",
26
+ "sep_token": "[SEP]",
27
+ "sep_token_box": [
28
+ 1000,
29
+ 1000,
30
+ 1000,
31
+ 1000
32
+ ],
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 sha256:9ded37ec748abe78689e5ae8d66e0d44b5de7926396fe46ba5e078cc22497ac1
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff