Hugging Face's logo

BWayne
/
LILT_mr

Token Classification
Transformers
PyTorch
Safetensors
lilt
Generated from Trainer
Model card Files
xet
Community
1
BWayne commited on
Commit
072a04c
·
1 Parent(s): c94db36

Upload 12 files

Browse files
Files changed (11) hide show
  1. .gitignore +1 -0
  2. README.md +75 -0
  3. config.json +47 -0
  4. merges.txt +0 -0
  5. preprocessor_config.json +26 -0
  6. pytorch_model.bin +3 -0
  7. special_tokens_map.json +51 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +85 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: LILT_on7
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
+ # LILT_on7
14
+
15
+ This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: nan
18
+ - Able caption: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}
19
+ - Eading: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62}
20
+ - Ext: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102}
21
+ - Mage caption: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13}
22
+ - Ub heading: {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125}
23
+ - Overall Precision: 0.2643
24
+ - Overall Recall: 0.4112
25
+ - Overall F1: 0.3218
26
+ - Overall Accuracy: 0.2643
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 0.0005
46
+ - train_batch_size: 8
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - training_steps: 5000
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Able caption | Eading | Ext | Mage caption | Ub heading | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------:|:----------------------------------------------------------:|:-----------------------------------------------------------:|:----------------------------------------------------------:|:------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
58
+ | 1.0142 | 0.44 | 500 | nan | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125} | 0.2643 | 0.4112 | 0.3218 | 0.2643 |
59
+ | 1.0228 | 0.89 | 1000 | nan | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125} | 0.2643 | 0.4112 | 0.3218 | 0.2643 |
60
+ | 1.0299 | 1.33 | 1500 | nan | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125} | 0.2643 | 0.4112 | 0.3218 | 0.2643 |
61
+ | 1.0233 | 1.78 | 2000 | nan | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125} | 0.2643 | 0.4112 | 0.3218 | 0.2643 |
62
+ | 0.9924 | 2.22 | 2500 | nan | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125} | 0.2643 | 0.4112 | 0.3218 | 0.2643 |
63
+ | 1.0081 | 2.67 | 3000 | nan | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125} | 0.2643 | 0.4112 | 0.3218 | 0.2643 |
64
+ | 0.9836 | 3.11 | 3500 | nan | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125} | 0.2643 | 0.4112 | 0.3218 | 0.2643 |
65
+ | 0.9997 | 3.56 | 4000 | nan | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125} | 0.2643 | 0.4112 | 0.3218 | 0.2643 |
66
+ | 0.984 | 4.0 | 4500 | nan | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125} | 0.2643 | 0.4112 | 0.3218 | 0.2643 |
67
+ | 0.9889 | 4.44 | 5000 | nan | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 62} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 102} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.2642706131078224, 'recall': 1.0, 'f1': 0.41806020066889626, 'number': 125} | 0.2643 | 0.4112 | 0.3218 | 0.2643 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.29.2
73
+ - Pytorch 2.0.1+cu118
74
+ - Datasets 2.12.0
75
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
3
+ "architectures": [
4
+ "LiltForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "channel_shrink_ratio": 4,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "Heading",
16
+ "1": "Image",
17
+ "2": "Image Caption",
18
+ "3": "Sub Heading",
19
+ "4": "Table",
20
+ "5": "Table Caption",
21
+ "6": "Text"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "Heading": 0,
27
+ "Image": 1,
28
+ "Image Caption": 2,
29
+ "Sub Heading": 3,
30
+ "Table": 4,
31
+ "Table Caption": 5,
32
+ "Text": 6
33
+ },
34
+ "layer_norm_eps": 1e-05,
35
+ "max_2d_position_embeddings": 1024,
36
+ "max_position_embeddings": 514,
37
+ "model_type": "lilt",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 1,
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.29.2",
44
+ "type_vocab_size": 1,
45
+ "use_cache": true,
46
+ "vocab_size": 50265
47
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "LayoutLMv3FeatureExtractor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "ocr_lang": null,
18
+ "processor_class": "LayoutLMv3Processor",
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 224,
23
+ "width": 224
24
+ },
25
+ "tesseract_config": ""
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c98aa9264f0113515d64cd4fb044afcec6ba83c2e7e717a00099156791f0ee8f
3
+ size 520821201
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "cls_token_box": [
21
+ 0,
22
+ 0,
23
+ 0,
24
+ 0
25
+ ],
26
+ "eos_token": {
27
+ "__type": "AddedToken",
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "errors": "replace",
35
+ "mask_token": {
36
+ "__type": "AddedToken",
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ },
43
+ "model_max_length": 512,
44
+ "only_label_first_subword": true,
45
+ "pad_token": {
46
+ "__type": "AddedToken",
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token_box": [
54
+ 0,
55
+ 0,
56
+ 0,
57
+ 0
58
+ ],
59
+ "pad_token_label": -100,
60
+ "processor_class": "LayoutLMv3Processor",
61
+ "sep_token": {
62
+ "__type": "AddedToken",
63
+ "content": "</s>",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false
68
+ },
69
+ "sep_token_box": [
70
+ 0,
71
+ 0,
72
+ 0,
73
+ 0
74
+ ],
75
+ "tokenizer_class": "LayoutLMv3Tokenizer",
76
+ "trim_offsets": true,
77
+ "unk_token": {
78
+ "__type": "AddedToken",
79
+ "content": "<unk>",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false
84
+ }
85
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d81a7f51bbf9151c3f938b032de383e1cddece64e9cf944c96c62a1f9efcd925
3
+ size 3899
vocab.json ADDED
The diff for this file is too large to render. See raw diff