akseljoonas
commited on
Commit
•
d846a64
1
Parent(s):
c8a35c4
End of training
Browse files- README.md +114 -0
- config.json +50 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +26 -0
- runs/Feb05_15-24-58_b6fc4add67b8/events.out.tfevents.1707146704.b6fc4add67b8.155.4 +3 -0
- runs/Feb05_15-24-58_b6fc4add67b8/events.out.tfevents.1707148705.b6fc4add67b8.155.5 +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 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
base_model: microsoft/layoutlmv3-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- format_dataset
|
8 |
+
metrics:
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
+
- accuracy
|
13 |
+
model-index:
|
14 |
+
- name: reciept-model-2500
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Token Classification
|
18 |
+
type: token-classification
|
19 |
+
dataset:
|
20 |
+
name: format_dataset
|
21 |
+
type: format_dataset
|
22 |
+
config: assesment dataset
|
23 |
+
split: test
|
24 |
+
args: assesment dataset
|
25 |
+
metrics:
|
26 |
+
- name: Precision
|
27 |
+
type: precision
|
28 |
+
value: 0.9673366834170855
|
29 |
+
- name: Recall
|
30 |
+
type: recall
|
31 |
+
value: 0.9625
|
32 |
+
- name: F1
|
33 |
+
type: f1
|
34 |
+
value: 0.9649122807017544
|
35 |
+
- name: Accuracy
|
36 |
+
type: accuracy
|
37 |
+
value: 0.9993105033325672
|
38 |
+
---
|
39 |
+
|
40 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
41 |
+
should probably proofread and complete it, then remove this comment. -->
|
42 |
+
|
43 |
+
# reciept-model-2500
|
44 |
+
|
45 |
+
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the format_dataset dataset.
|
46 |
+
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.0043
|
48 |
+
- Precision: 0.9673
|
49 |
+
- Recall: 0.9625
|
50 |
+
- F1: 0.9649
|
51 |
+
- Accuracy: 0.9993
|
52 |
+
|
53 |
+
## Model description
|
54 |
+
|
55 |
+
More information needed
|
56 |
+
|
57 |
+
## Intended uses & limitations
|
58 |
+
|
59 |
+
More information needed
|
60 |
+
|
61 |
+
## Training and evaluation data
|
62 |
+
|
63 |
+
More information needed
|
64 |
+
|
65 |
+
## Training procedure
|
66 |
+
|
67 |
+
### Training hyperparameters
|
68 |
+
|
69 |
+
The following hyperparameters were used during training:
|
70 |
+
- learning_rate: 1e-05
|
71 |
+
- train_batch_size: 2
|
72 |
+
- eval_batch_size: 2
|
73 |
+
- seed: 42
|
74 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
+
- lr_scheduler_type: linear
|
76 |
+
- training_steps: 2500
|
77 |
+
|
78 |
+
### Training results
|
79 |
+
|
80 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
+
| No log | 0.62 | 100 | 0.0150 | 0.8575 | 0.8725 | 0.8649 | 0.9972 |
|
83 |
+
| No log | 1.25 | 200 | 0.0075 | 0.8756 | 0.9325 | 0.9031 | 0.9979 |
|
84 |
+
| No log | 1.88 | 300 | 0.0154 | 0.8744 | 0.8875 | 0.8809 | 0.9973 |
|
85 |
+
| No log | 2.5 | 400 | 0.0118 | 0.8881 | 0.9525 | 0.9192 | 0.9982 |
|
86 |
+
| 0.0029 | 3.12 | 500 | 0.0091 | 0.9158 | 0.925 | 0.9204 | 0.9983 |
|
87 |
+
| 0.0029 | 3.75 | 600 | 0.0167 | 0.8720 | 0.9025 | 0.8870 | 0.9975 |
|
88 |
+
| 0.0029 | 4.38 | 700 | 0.0092 | 0.9183 | 0.9275 | 0.9229 | 0.9983 |
|
89 |
+
| 0.0029 | 5.0 | 800 | 0.0113 | 0.8843 | 0.9175 | 0.9006 | 0.9979 |
|
90 |
+
| 0.0029 | 5.62 | 900 | 0.0106 | 0.9349 | 0.8975 | 0.9158 | 0.9982 |
|
91 |
+
| 0.0017 | 6.25 | 1000 | 0.0043 | 0.9673 | 0.9625 | 0.9649 | 0.9993 |
|
92 |
+
| 0.0017 | 6.88 | 1100 | 0.0044 | 0.9602 | 0.965 | 0.9626 | 0.9993 |
|
93 |
+
| 0.0017 | 7.5 | 1200 | 0.0118 | 0.9246 | 0.92 | 0.9223 | 0.9982 |
|
94 |
+
| 0.0017 | 8.12 | 1300 | 0.0067 | 0.9406 | 0.95 | 0.9453 | 0.9988 |
|
95 |
+
| 0.0017 | 8.75 | 1400 | 0.0083 | 0.9409 | 0.955 | 0.9479 | 0.9989 |
|
96 |
+
| 0.001 | 9.38 | 1500 | 0.0060 | 0.9495 | 0.94 | 0.9447 | 0.9988 |
|
97 |
+
| 0.001 | 10.0 | 1600 | 0.0078 | 0.9369 | 0.9275 | 0.9322 | 0.9985 |
|
98 |
+
| 0.001 | 10.62 | 1700 | 0.0093 | 0.9248 | 0.9525 | 0.9384 | 0.9986 |
|
99 |
+
| 0.001 | 11.25 | 1800 | 0.0097 | 0.9062 | 0.9425 | 0.9240 | 0.9983 |
|
100 |
+
| 0.001 | 11.88 | 1900 | 0.0100 | 0.9098 | 0.9325 | 0.9210 | 0.9982 |
|
101 |
+
| 0.0006 | 12.5 | 2000 | 0.0111 | 0.9113 | 0.925 | 0.9181 | 0.9981 |
|
102 |
+
| 0.0006 | 13.12 | 2100 | 0.0107 | 0.9275 | 0.9275 | 0.9275 | 0.9983 |
|
103 |
+
| 0.0006 | 13.75 | 2200 | 0.0105 | 0.9279 | 0.9325 | 0.9302 | 0.9984 |
|
104 |
+
| 0.0006 | 14.38 | 2300 | 0.0109 | 0.9325 | 0.9325 | 0.9325 | 0.9985 |
|
105 |
+
| 0.0006 | 15.0 | 2400 | 0.0109 | 0.9325 | 0.9325 | 0.9325 | 0.9985 |
|
106 |
+
| 0.0003 | 15.62 | 2500 | 0.0109 | 0.9325 | 0.9325 | 0.9325 | 0.9985 |
|
107 |
+
|
108 |
+
|
109 |
+
### Framework versions
|
110 |
+
|
111 |
+
- Transformers 4.38.0.dev0
|
112 |
+
- Pytorch 2.1.0+cu121
|
113 |
+
- Datasets 2.16.1
|
114 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Ignore",
|
18 |
+
"1": "B-total_amount",
|
19 |
+
"2": "I-total_amount"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"input_size": 224,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"B-total_amount": 1,
|
26 |
+
"I-total_amount": 2,
|
27 |
+
"Ignore": 0
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-05,
|
30 |
+
"max_2d_position_embeddings": 1024,
|
31 |
+
"max_position_embeddings": 514,
|
32 |
+
"max_rel_2d_pos": 256,
|
33 |
+
"max_rel_pos": 128,
|
34 |
+
"model_type": "layoutlmv3",
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_channels": 3,
|
37 |
+
"num_hidden_layers": 12,
|
38 |
+
"pad_token_id": 1,
|
39 |
+
"patch_size": 16,
|
40 |
+
"rel_2d_pos_bins": 64,
|
41 |
+
"rel_pos_bins": 32,
|
42 |
+
"second_input_size": 112,
|
43 |
+
"shape_size": 128,
|
44 |
+
"text_embed": true,
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.38.0.dev0",
|
47 |
+
"type_vocab_size": 1,
|
48 |
+
"visual_embed": true,
|
49 |
+
"vocab_size": 50265
|
50 |
+
}
|
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 sha256:204d9049f51ebfaba83eef77c268d78f9630657e40dbcdee4a0b2c8010f199b1
|
3 |
+
size 501343228
|
preprocessor_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_ocr": false,
|
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": "LayoutLMv3ImageProcessor",
|
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 |
+
}
|
runs/Feb05_15-24-58_b6fc4add67b8/events.out.tfevents.1707146704.b6fc4add67b8.155.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a24fdf0c33d2960dfcd1850545cbd97ff0e1feb857d6ea5827a26cc00b07dcb
|
3 |
+
size 17899
|
runs/Feb05_15-24-58_b6fc4add67b8/events.out.tfevents.1707148705.b6fc4add67b8.155.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4fc8d3d67dd85c1cd876f8c6f4237ca60dd036353bab7e50b8a223bfbda1454
|
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:c0e95e9756a122371c0b59c24ba36af03ec91294133c771320b1594e798c5e1b
|
3 |
+
size 4728
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|