quethrozar
commited on
Commit
•
6c07fb2
1
Parent(s):
a5a160b
End of training
Browse files- README.md +77 -0
- logs/events.out.tfevents.1684775756.MSI.903.7 +2 -2
- logs/events.out.tfevents.1684777786.MSI.903.9 +3 -0
- merges.txt +0 -0
- preprocessor_config.json +26 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +85 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- funsd-layoutlmv3
|
7 |
+
model-index:
|
8 |
+
- name: lilt-en-funsd
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# lilt-en-funsd
|
16 |
+
|
17 |
+
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 funsd-layoutlmv3 dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.4801
|
20 |
+
- Answer: {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817}
|
21 |
+
- Header: {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119}
|
22 |
+
- Question: {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077}
|
23 |
+
- Overall Precision: 0.8720
|
24 |
+
- Overall Recall: 0.8932
|
25 |
+
- Overall F1: 0.8825
|
26 |
+
- Overall Accuracy: 0.8040
|
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: 5e-05
|
46 |
+
- train_batch_size: 2
|
47 |
+
- eval_batch_size: 2
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- training_steps: 2500
|
52 |
+
- mixed_precision_training: Native AMP
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
58 |
+
| 0.0015 | 2.67 | 200 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
59 |
+
| 0.0011 | 5.33 | 400 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
60 |
+
| 0.0011 | 8.0 | 600 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
61 |
+
| 0.0008 | 10.67 | 800 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
62 |
+
| 0.0011 | 13.33 | 1000 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
63 |
+
| 0.0011 | 16.0 | 1200 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
64 |
+
| 0.0017 | 18.67 | 1400 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
65 |
+
| 0.0008 | 21.33 | 1600 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
66 |
+
| 0.0008 | 24.0 | 1800 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
67 |
+
| 0.0009 | 26.67 | 2000 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
68 |
+
| 0.0012 | 29.33 | 2200 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
69 |
+
| 0.0009 | 32.0 | 2400 | 1.4801 | {'precision': 0.8607888631090487, 'recall': 0.9082007343941249, 'f1': 0.8838594401429422, 'number': 817} | {'precision': 0.6404494382022472, 'recall': 0.4789915966386555, 'f1': 0.548076923076923, 'number': 119} | {'precision': 0.8991899189918992, 'recall': 0.9275766016713092, 'f1': 0.9131627056672761, 'number': 1077} | 0.8720 | 0.8932 | 0.8825 | 0.8040 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.30.0.dev0
|
75 |
+
- Pytorch 1.8.0+cu101
|
76 |
+
- Datasets 2.12.0
|
77 |
+
- Tokenizers 0.13.3
|
logs/events.out.tfevents.1684775756.MSI.903.7
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16e2449a984f9f2f522830704676ebd770efacdd5a823c208262e4edbe8b73bd
|
3 |
+
size 12720
|
logs/events.out.tfevents.1684777786.MSI.903.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bcc47148253cc13d66a34860a27b7dcc9ea6e2c62c82562bf21ca0ddb0c80f9
|
3 |
+
size 592
|
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 |
+
}
|
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 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|