update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- data_registros_layoutv3
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: layoutlmv3-finetuned-registros_100
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Token Classification
|
17 |
+
type: token-classification
|
18 |
+
dataset:
|
19 |
+
name: data_registros_layoutv3
|
20 |
+
type: data_registros_layoutv3
|
21 |
+
config: default
|
22 |
+
split: test
|
23 |
+
args: default
|
24 |
+
metrics:
|
25 |
+
- name: Precision
|
26 |
+
type: precision
|
27 |
+
value: 0.9871382636655949
|
28 |
+
- name: Recall
|
29 |
+
type: recall
|
30 |
+
value: 0.9935275080906149
|
31 |
+
- name: F1
|
32 |
+
type: f1
|
33 |
+
value: 0.9903225806451612
|
34 |
+
- name: Accuracy
|
35 |
+
type: accuracy
|
36 |
+
value: 0.9992192379762649
|
37 |
+
---
|
38 |
+
|
39 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
40 |
+
should probably proofread and complete it, then remove this comment. -->
|
41 |
+
|
42 |
+
# layoutlmv3-finetuned-registros_100
|
43 |
+
|
44 |
+
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the data_registros_layoutv3 dataset.
|
45 |
+
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.0110
|
47 |
+
- Precision: 0.9871
|
48 |
+
- Recall: 0.9935
|
49 |
+
- F1: 0.9903
|
50 |
+
- Accuracy: 0.9992
|
51 |
+
|
52 |
+
## Model description
|
53 |
+
|
54 |
+
More information needed
|
55 |
+
|
56 |
+
## Intended uses & limitations
|
57 |
+
|
58 |
+
More information needed
|
59 |
+
|
60 |
+
## Training and evaluation data
|
61 |
+
|
62 |
+
More information needed
|
63 |
+
|
64 |
+
## Training procedure
|
65 |
+
|
66 |
+
### Training hyperparameters
|
67 |
+
|
68 |
+
The following hyperparameters were used during training:
|
69 |
+
- learning_rate: 5e-06
|
70 |
+
- train_batch_size: 4
|
71 |
+
- eval_batch_size: 4
|
72 |
+
- seed: 42
|
73 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
74 |
+
- lr_scheduler_type: linear
|
75 |
+
- training_steps: 3000
|
76 |
+
|
77 |
+
### Training results
|
78 |
+
|
79 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
80 |
+
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
81 |
+
| No log | 10.87 | 250 | 0.4325 | 0.2663 | 0.2638 | 0.2650 | 0.8982 |
|
82 |
+
| 0.6304 | 21.74 | 500 | 0.2065 | 0.7715 | 0.8139 | 0.7921 | 0.9622 |
|
83 |
+
| 0.6304 | 32.61 | 750 | 0.1058 | 0.9048 | 0.9385 | 0.9214 | 0.9866 |
|
84 |
+
| 0.1413 | 43.48 | 1000 | 0.0600 | 0.9314 | 0.9660 | 0.9484 | 0.9944 |
|
85 |
+
| 0.1413 | 54.35 | 1250 | 0.0377 | 0.9451 | 0.9741 | 0.9594 | 0.9969 |
|
86 |
+
| 0.0558 | 65.22 | 1500 | 0.0277 | 0.9697 | 0.9838 | 0.9767 | 0.9981 |
|
87 |
+
| 0.0558 | 76.09 | 1750 | 0.0199 | 0.9792 | 0.9903 | 0.9847 | 0.9988 |
|
88 |
+
| 0.0307 | 86.96 | 2000 | 0.0160 | 0.9824 | 0.9919 | 0.9871 | 0.9989 |
|
89 |
+
| 0.0307 | 97.83 | 2250 | 0.0147 | 0.9823 | 0.9903 | 0.9863 | 0.9988 |
|
90 |
+
| 0.0211 | 108.7 | 2500 | 0.0122 | 0.9871 | 0.9935 | 0.9903 | 0.9992 |
|
91 |
+
| 0.0211 | 119.57 | 2750 | 0.0113 | 0.9871 | 0.9935 | 0.9903 | 0.9992 |
|
92 |
+
| 0.0174 | 130.43 | 3000 | 0.0110 | 0.9871 | 0.9935 | 0.9903 | 0.9992 |
|
93 |
+
|
94 |
+
|
95 |
+
### Framework versions
|
96 |
+
|
97 |
+
- Transformers 4.29.2
|
98 |
+
- Pytorch 2.0.1+cu118
|
99 |
+
- Datasets 2.12.0
|
100 |
+
- Tokenizers 0.13.3
|