haronbenfaida
commited on
Commit
•
0ee5a70
1
Parent(s):
e569156
layoutlmv3-finetuned-facturesv0
Browse files- README.md +75 -0
- config.json +110 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +43 -0
- runs/Jul10_11-38-30_5c79c79c901d/events.out.tfevents.1720611520.5c79c79c901d.2925.0 +3 -0
- runs/Jul10_11-38-30_5c79c79c901d/events.out.tfevents.1720612024.5c79c79c901d.2925.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +79 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
base_model: microsoft/layoutlmv3-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: test
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# test
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0203
|
24 |
+
- Precision: 1.0
|
25 |
+
- Recall: 1.0
|
26 |
+
- F1: 1.0
|
27 |
+
- Accuracy: 1.0
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 1e-05
|
47 |
+
- train_batch_size: 2
|
48 |
+
- eval_batch_size: 2
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- training_steps: 1000
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 2.5 | 100 | 0.5488 | 0.9140 | 0.8379 | 0.8743 | 0.9448 |
|
59 |
+
| No log | 5.0 | 200 | 0.1142 | 1.0 | 1.0 | 1.0 | 1.0 |
|
60 |
+
| No log | 7.5 | 300 | 0.0433 | 1.0 | 1.0 | 1.0 | 1.0 |
|
61 |
+
| No log | 10.0 | 400 | 0.0274 | 1.0 | 1.0 | 1.0 | 1.0 |
|
62 |
+
| 0.4317 | 12.5 | 500 | 0.0203 | 1.0 | 1.0 | 1.0 | 1.0 |
|
63 |
+
| 0.4317 | 15.0 | 600 | 0.0165 | 1.0 | 1.0 | 1.0 | 1.0 |
|
64 |
+
| 0.4317 | 17.5 | 700 | 0.0143 | 1.0 | 1.0 | 1.0 | 1.0 |
|
65 |
+
| 0.4317 | 20.0 | 800 | 0.0129 | 1.0 | 1.0 | 1.0 | 1.0 |
|
66 |
+
| 0.4317 | 22.5 | 900 | 0.0121 | 1.0 | 1.0 | 1.0 | 1.0 |
|
67 |
+
| 0.0248 | 25.0 | 1000 | 0.0119 | 1.0 | 1.0 | 1.0 | 1.0 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.41.2
|
73 |
+
- Pytorch 2.3.0+cu121
|
74 |
+
- Datasets 2.20.0
|
75 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/layoutlmv3-base",
|
3 |
+
"architectures": [
|
4 |
+
"LayoutLMv3ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"coordinate_size": 128,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"has_relative_attention_bias": true,
|
12 |
+
"has_spatial_attention_bias": true,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "O",
|
18 |
+
"1": "B-Num_Facture",
|
19 |
+
"2": "I-Num_Facture",
|
20 |
+
"3": "B-Date",
|
21 |
+
"4": "I-Date",
|
22 |
+
"5": "B-Nom_Fournisseur",
|
23 |
+
"6": "I-Nom_Fournisseur",
|
24 |
+
"7": "B-ICE_Fournisseur",
|
25 |
+
"8": "I-ICE_Fournisseur",
|
26 |
+
"9": "B-Adresse_Fournisseur",
|
27 |
+
"10": "I-Adresse_Fournisseur",
|
28 |
+
"11": "B-Nom_Client",
|
29 |
+
"12": "I-Nom_Client",
|
30 |
+
"13": "B-ICE_Client",
|
31 |
+
"14": "I-ICE_Client",
|
32 |
+
"15": "B-Adresse_Client",
|
33 |
+
"16": "I-Adresse_Client",
|
34 |
+
"17": "B-Nom_Article",
|
35 |
+
"18": "I-Nom_Article",
|
36 |
+
"19": "B-QTE_Article",
|
37 |
+
"20": "I-QTE_Article",
|
38 |
+
"21": "B-Prix_Uni_Article",
|
39 |
+
"22": "I-Prix_Uni_Article",
|
40 |
+
"23": "B-Total_Article",
|
41 |
+
"24": "I-Total_Article",
|
42 |
+
"25": "B-Total_HT",
|
43 |
+
"26": "I-Total_HT",
|
44 |
+
"27": "B-TVA",
|
45 |
+
"28": "I-TVA",
|
46 |
+
"29": "B-Remise",
|
47 |
+
"30": "I-Remise",
|
48 |
+
"31": "B-Total_Net",
|
49 |
+
"32": "I-Total_Net"
|
50 |
+
},
|
51 |
+
"initializer_range": 0.02,
|
52 |
+
"input_size": 224,
|
53 |
+
"intermediate_size": 3072,
|
54 |
+
"label2id": {
|
55 |
+
"B-Adresse_Client": 15,
|
56 |
+
"B-Adresse_Fournisseur": 9,
|
57 |
+
"B-Date": 3,
|
58 |
+
"B-ICE_Client": 13,
|
59 |
+
"B-ICE_Fournisseur": 7,
|
60 |
+
"B-Nom_Article": 17,
|
61 |
+
"B-Nom_Client": 11,
|
62 |
+
"B-Nom_Fournisseur": 5,
|
63 |
+
"B-Num_Facture": 1,
|
64 |
+
"B-Prix_Uni_Article": 21,
|
65 |
+
"B-QTE_Article": 19,
|
66 |
+
"B-Remise": 29,
|
67 |
+
"B-TVA": 27,
|
68 |
+
"B-Total_Article": 23,
|
69 |
+
"B-Total_HT": 25,
|
70 |
+
"B-Total_Net": 31,
|
71 |
+
"I-Adresse_Client": 16,
|
72 |
+
"I-Adresse_Fournisseur": 10,
|
73 |
+
"I-Date": 4,
|
74 |
+
"I-ICE_Client": 14,
|
75 |
+
"I-ICE_Fournisseur": 8,
|
76 |
+
"I-Nom_Article": 18,
|
77 |
+
"I-Nom_Client": 12,
|
78 |
+
"I-Nom_Fournisseur": 6,
|
79 |
+
"I-Num_Facture": 2,
|
80 |
+
"I-Prix_Uni_Article": 22,
|
81 |
+
"I-QTE_Article": 20,
|
82 |
+
"I-Remise": 30,
|
83 |
+
"I-TVA": 28,
|
84 |
+
"I-Total_Article": 24,
|
85 |
+
"I-Total_HT": 26,
|
86 |
+
"I-Total_Net": 32,
|
87 |
+
"O": 0
|
88 |
+
},
|
89 |
+
"layer_norm_eps": 1e-05,
|
90 |
+
"max_2d_position_embeddings": 1024,
|
91 |
+
"max_position_embeddings": 514,
|
92 |
+
"max_rel_2d_pos": 256,
|
93 |
+
"max_rel_pos": 128,
|
94 |
+
"model_type": "layoutlmv3",
|
95 |
+
"num_attention_heads": 12,
|
96 |
+
"num_channels": 3,
|
97 |
+
"num_hidden_layers": 12,
|
98 |
+
"pad_token_id": 1,
|
99 |
+
"patch_size": 16,
|
100 |
+
"rel_2d_pos_bins": 64,
|
101 |
+
"rel_pos_bins": 32,
|
102 |
+
"second_input_size": 112,
|
103 |
+
"shape_size": 128,
|
104 |
+
"text_embed": true,
|
105 |
+
"torch_dtype": "float32",
|
106 |
+
"transformers_version": "4.41.2",
|
107 |
+
"type_vocab_size": 1,
|
108 |
+
"visual_embed": true,
|
109 |
+
"vocab_size": 50265
|
110 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f6c10f1b3967b35251effe04d6c2182a574b8e873ea34c26faf1ad24f01120b
|
3 |
+
size 503798108
|
preprocessor_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"apply_ocr",
|
13 |
+
"ocr_lang",
|
14 |
+
"tesseract_config",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
+
"apply_ocr": false,
|
20 |
+
"do_normalize": true,
|
21 |
+
"do_rescale": true,
|
22 |
+
"do_resize": true,
|
23 |
+
"image_mean": [
|
24 |
+
0.5,
|
25 |
+
0.5,
|
26 |
+
0.5
|
27 |
+
],
|
28 |
+
"image_processor_type": "LayoutLMv3ImageProcessor",
|
29 |
+
"image_std": [
|
30 |
+
0.5,
|
31 |
+
0.5,
|
32 |
+
0.5
|
33 |
+
],
|
34 |
+
"ocr_lang": null,
|
35 |
+
"processor_class": "LayoutLMv3Processor",
|
36 |
+
"resample": 2,
|
37 |
+
"rescale_factor": 0.00392156862745098,
|
38 |
+
"size": {
|
39 |
+
"height": 224,
|
40 |
+
"width": 224
|
41 |
+
},
|
42 |
+
"tesseract_config": ""
|
43 |
+
}
|
runs/Jul10_11-38-30_5c79c79c901d/events.out.tfevents.1720611520.5c79c79c901d.2925.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cd6cbacb02de0d0b154c1af40a502e1ce139e2da9f7d6ac857dbff4a07c38dc
|
3 |
+
size 12291
|
runs/Jul10_11-38-30_5c79c79c901d/events.out.tfevents.1720612024.5c79c79c901d.2925.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dca19af90fd732cfff9dac9e4ac80767248936bac862761e41f5418ee1100e65
|
3 |
+
size 560
|
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 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"apply_ocr": false,
|
46 |
+
"bos_token": "<s>",
|
47 |
+
"clean_up_tokenization_spaces": true,
|
48 |
+
"cls_token": "<s>",
|
49 |
+
"cls_token_box": [
|
50 |
+
0,
|
51 |
+
0,
|
52 |
+
0,
|
53 |
+
0
|
54 |
+
],
|
55 |
+
"eos_token": "</s>",
|
56 |
+
"errors": "replace",
|
57 |
+
"mask_token": "<mask>",
|
58 |
+
"model_max_length": 512,
|
59 |
+
"only_label_first_subword": true,
|
60 |
+
"pad_token": "<pad>",
|
61 |
+
"pad_token_box": [
|
62 |
+
0,
|
63 |
+
0,
|
64 |
+
0,
|
65 |
+
0
|
66 |
+
],
|
67 |
+
"pad_token_label": -100,
|
68 |
+
"processor_class": "LayoutLMv3Processor",
|
69 |
+
"sep_token": "</s>",
|
70 |
+
"sep_token_box": [
|
71 |
+
0,
|
72 |
+
0,
|
73 |
+
0,
|
74 |
+
0
|
75 |
+
],
|
76 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
77 |
+
"trim_offsets": true,
|
78 |
+
"unk_token": "<unk>"
|
79 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7be9dbb7538f97d43a299c4b726f38b003381eb1f35db62a3ac93ac0e23e066
|
3 |
+
size 5048
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|