BenjaminKUL
commited on
Commit
•
619760b
1
Parent(s):
cc81392
End of training
Browse files- README.md +76 -0
- logs/events.out.tfevents.1691674839.Benjamins-MacBook-Pro.local.33466.0 +2 -2
- merges.txt +0 -0
- preprocessor_config.json +26 -0
- pytorch_model.bin +1 -1
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +85 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- funsd-layoutlmv3
|
7 |
+
model-index:
|
8 |
+
- name: new_model
|
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 |
+
# new_model
|
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: 0.5095
|
20 |
+
- Answer: {'precision': 0.8368479467258602, 'recall': 0.9228886168910648, 'f1': 0.8777648428405123, 'number': 817}
|
21 |
+
- Header: {'precision': 0.5333333333333333, 'recall': 0.5378151260504201, 'f1': 0.5355648535564853, 'number': 119}
|
22 |
+
- Question: {'precision': 0.8907407407407407, 'recall': 0.89322191272052, 'f1': 0.8919796012980993, 'number': 1077}
|
23 |
+
- Overall Precision: 0.8472
|
24 |
+
- Overall Recall: 0.8843
|
25 |
+
- Overall F1: 0.8653
|
26 |
+
- Overall Accuracy: 0.7922
|
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: 4
|
47 |
+
- eval_batch_size: 4
|
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 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
57 |
+
| 0.1542 | 3.51 | 200 | 0.2369 | {'precision': 0.7753846153846153, 'recall': 0.9253365973072215, 'f1': 0.8437500000000001, 'number': 817} | {'precision': 0.4166666666666667, 'recall': 0.21008403361344538, 'f1': 0.2793296089385475, 'number': 119} | {'precision': 0.8449744463373083, 'recall': 0.9210770659238626, 'f1': 0.8813860506441582, 'number': 1077} | 0.8026 | 0.8808 | 0.8399 | 0.7940 |
|
58 |
+
| 0.0493 | 7.02 | 400 | 0.2901 | {'precision': 0.8056133056133056, 'recall': 0.9485924112607099, 'f1': 0.8712759977515458, 'number': 817} | {'precision': 0.45614035087719296, 'recall': 0.4369747899159664, 'f1': 0.44635193133047213, 'number': 119} | {'precision': 0.888673765730881, 'recall': 0.8523676880222841, 'f1': 0.8701421800947867, 'number': 1077} | 0.8274 | 0.8669 | 0.8467 | 0.8010 |
|
59 |
+
| 0.0214 | 10.53 | 600 | 0.3571 | {'precision': 0.8139013452914798, 'recall': 0.8886168910648715, 'f1': 0.8496196606202459, 'number': 817} | {'precision': 0.4186046511627907, 'recall': 0.6050420168067226, 'f1': 0.4948453608247423, 'number': 119} | {'precision': 0.8652946679139383, 'recall': 0.8588672237697307, 'f1': 0.8620689655172413, 'number': 1077} | 0.8078 | 0.8559 | 0.8312 | 0.7907 |
|
60 |
+
| 0.0112 | 14.04 | 800 | 0.4018 | {'precision': 0.8484455958549223, 'recall': 0.8017135862913096, 'f1': 0.8244178728760226, 'number': 817} | {'precision': 0.45, 'recall': 0.6050420168067226, 'f1': 0.5161290322580645, 'number': 119} | {'precision': 0.8385689354275742, 'recall': 0.8922934076137419, 'f1': 0.8645973909131804, 'number': 1077} | 0.8123 | 0.8385 | 0.8252 | 0.7872 |
|
61 |
+
| 0.0058 | 17.54 | 1000 | 0.4571 | {'precision': 0.8466666666666667, 'recall': 0.9326805385556916, 'f1': 0.8875946418171229, 'number': 817} | {'precision': 0.6621621621621622, 'recall': 0.4117647058823529, 'f1': 0.5077720207253885, 'number': 119} | {'precision': 0.8809738503155996, 'recall': 0.9071494893221913, 'f1': 0.8938700823421775, 'number': 1077} | 0.8584 | 0.8882 | 0.8730 | 0.7944 |
|
62 |
+
| 0.0031 | 21.05 | 1200 | 0.4573 | {'precision': 0.8208469055374593, 'recall': 0.9253365973072215, 'f1': 0.8699654775604143, 'number': 817} | {'precision': 0.5727272727272728, 'recall': 0.5294117647058824, 'f1': 0.5502183406113538, 'number': 119} | {'precision': 0.8799266727772685, 'recall': 0.8913649025069638, 'f1': 0.8856088560885608, 'number': 1077} | 0.8384 | 0.8838 | 0.8605 | 0.7891 |
|
63 |
+
| 0.0019 | 24.56 | 1400 | 0.4631 | {'precision': 0.8372352285395763, 'recall': 0.9192166462668299, 'f1': 0.8763127187864644, 'number': 817} | {'precision': 0.559322033898305, 'recall': 0.5546218487394958, 'f1': 0.5569620253164557, 'number': 119} | {'precision': 0.8864059590316573, 'recall': 0.8839368616527391, 'f1': 0.8851696885169689, 'number': 1077} | 0.8468 | 0.8788 | 0.8625 | 0.7977 |
|
64 |
+
| 0.0011 | 28.07 | 1600 | 0.5118 | {'precision': 0.838074398249453, 'recall': 0.9375764993880049, 'f1': 0.8850375505488157, 'number': 817} | {'precision': 0.5862068965517241, 'recall': 0.5714285714285714, 'f1': 0.5787234042553192, 'number': 119} | {'precision': 0.885972850678733, 'recall': 0.9090064995357474, 'f1': 0.8973418881759853, 'number': 1077} | 0.8492 | 0.9006 | 0.8742 | 0.7970 |
|
65 |
+
| 0.0006 | 31.58 | 1800 | 0.4786 | {'precision': 0.8383500557413601, 'recall': 0.9204406364749081, 'f1': 0.8774795799299884, 'number': 817} | {'precision': 0.6, 'recall': 0.5546218487394958, 'f1': 0.5764192139737991, 'number': 119} | {'precision': 0.8851412944393802, 'recall': 0.9015784586815228, 'f1': 0.8932842686292549, 'number': 1077} | 0.8503 | 0.8887 | 0.8691 | 0.7942 |
|
66 |
+
| 0.0004 | 35.09 | 2000 | 0.4959 | {'precision': 0.8338945005611672, 'recall': 0.9094247246022031, 'f1': 0.870023419203747, 'number': 817} | {'precision': 0.5172413793103449, 'recall': 0.6302521008403361, 'f1': 0.5681818181818182, 'number': 119} | {'precision': 0.8833333333333333, 'recall': 0.8857938718662952, 'f1': 0.8845618915159944, 'number': 1077} | 0.8374 | 0.8803 | 0.8583 | 0.7919 |
|
67 |
+
| 0.0003 | 38.6 | 2200 | 0.5023 | {'precision': 0.8292682926829268, 'recall': 0.9155446756425949, 'f1': 0.8702734147760327, 'number': 817} | {'precision': 0.5470085470085471, 'recall': 0.5378151260504201, 'f1': 0.5423728813559322, 'number': 119} | {'precision': 0.8771610555050046, 'recall': 0.8950789229340761, 'f1': 0.8860294117647057, 'number': 1077} | 0.8385 | 0.8823 | 0.8598 | 0.7948 |
|
68 |
+
| 0.0002 | 42.11 | 2400 | 0.5095 | {'precision': 0.8368479467258602, 'recall': 0.9228886168910648, 'f1': 0.8777648428405123, 'number': 817} | {'precision': 0.5333333333333333, 'recall': 0.5378151260504201, 'f1': 0.5355648535564853, 'number': 119} | {'precision': 0.8907407407407407, 'recall': 0.89322191272052, 'f1': 0.8919796012980993, 'number': 1077} | 0.8472 | 0.8843 | 0.8653 | 0.7922 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.28.1
|
74 |
+
- Pytorch 2.1.0.dev20230810
|
75 |
+
- Datasets 2.14.4
|
76 |
+
- Tokenizers 0.11.0
|
logs/events.out.tfevents.1691674839.Benjamins-MacBook-Pro.local.33466.0
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 sha256:2cf11a842ff589197fc2e99718726b3227545d484bbfe7a626d9bcf20e5cb241
|
3 |
+
size 12656
|
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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 520816014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fc610986047d3cb8198e6a5dcc638efffbcbba74595a29ada3c7e29c9587395
|
3 |
size 520816014
|
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
|
|