|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: microsoft/layoutlm-base-uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: layoutlm-mcocr |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# layoutlm-mcocr |
|
|
|
|
|
This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0293 |
|
|
- Ddress: {'precision': 0.9769585253456221, 'recall': 0.9769585253456221, 'f1': 0.9769585253456222, 'number': 217} |
|
|
- Eller: {'precision': 0.9914529914529915, 'recall': 0.9914529914529915, 'f1': 0.9914529914529915, 'number': 234} |
|
|
- Imestamp: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 211} |
|
|
- Otal Cost: {'precision': 0.9953271028037384, 'recall': 1.0, 'f1': 0.9976580796252927, 'number': 213} |
|
|
- Overall Precision: 0.9909 |
|
|
- Overall Recall: 0.992 |
|
|
- Overall F1: 0.9914 |
|
|
- Overall Accuracy: 0.9960 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 3e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 15 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Ddress | Eller | Imestamp | Otal Cost | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| |
|
|
| 0.3063 | 1.0 | 55 | 0.0304 | {'precision': 0.9585253456221198, 'recall': 0.9585253456221198, 'f1': 0.9585253456221198, 'number': 217} | {'precision': 0.991304347826087, 'recall': 0.9743589743589743, 'f1': 0.9827586206896551, 'number': 234} | {'precision': 0.995260663507109, 'recall': 0.995260663507109, 'f1': 0.995260663507109, 'number': 211} | {'precision': 0.986046511627907, 'recall': 0.9953051643192489, 'f1': 0.9906542056074766, 'number': 213} | 0.9828 | 0.9806 | 0.9817 | 0.9912 | |
|
|
| 0.0332 | 2.0 | 110 | 0.0303 | {'precision': 0.967741935483871, 'recall': 0.967741935483871, 'f1': 0.967741935483871, 'number': 217} | {'precision': 0.991304347826087, 'recall': 0.9743589743589743, 'f1': 0.9827586206896551, 'number': 234} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 211} | {'precision': 0.9906976744186047, 'recall': 1.0, 'f1': 0.9953271028037384, 'number': 213} | 0.9874 | 0.9851 | 0.9863 | 0.9928 | |
|
|
| 0.0174 | 3.0 | 165 | 0.0252 | {'precision': 0.9723502304147466, 'recall': 0.9723502304147466, 'f1': 0.9723502304147466, 'number': 217} | {'precision': 0.9872340425531915, 'recall': 0.9914529914529915, 'f1': 0.9893390191897654, 'number': 234} | {'precision': 0.995260663507109, 'recall': 0.995260663507109, 'f1': 0.995260663507109, 'number': 211} | {'precision': 0.9906542056074766, 'recall': 0.9953051643192489, 'f1': 0.9929742388758782, 'number': 213} | 0.9863 | 0.9886 | 0.9874 | 0.9944 | |
|
|
| 0.0145 | 4.0 | 220 | 0.0271 | {'precision': 0.967741935483871, 'recall': 0.967741935483871, 'f1': 0.967741935483871, 'number': 217} | {'precision': 0.9913793103448276, 'recall': 0.9829059829059829, 'f1': 0.9871244635193134, 'number': 234} | {'precision': 0.995260663507109, 'recall': 0.995260663507109, 'f1': 0.995260663507109, 'number': 211} | {'precision': 0.9906542056074766, 'recall': 0.9953051643192489, 'f1': 0.9929742388758782, 'number': 213} | 0.9863 | 0.9851 | 0.9857 | 0.9936 | |
|
|
| 0.0114 | 5.0 | 275 | 0.0254 | {'precision': 0.9769585253456221, 'recall': 0.9769585253456221, 'f1': 0.9769585253456222, 'number': 217} | {'precision': 0.9914529914529915, 'recall': 0.9914529914529915, 'f1': 0.9914529914529915, 'number': 234} | {'precision': 0.995260663507109, 'recall': 0.995260663507109, 'f1': 0.995260663507109, 'number': 211} | {'precision': 0.9906542056074766, 'recall': 0.9953051643192489, 'f1': 0.9929742388758782, 'number': 213} | 0.9886 | 0.9897 | 0.9891 | 0.9952 | |
|
|
| 0.0079 | 6.0 | 330 | 0.0273 | {'precision': 0.9723502304147466, 'recall': 0.9723502304147466, 'f1': 0.9723502304147466, 'number': 217} | {'precision': 0.9872340425531915, 'recall': 0.9914529914529915, 'f1': 0.9893390191897654, 'number': 234} | {'precision': 0.995260663507109, 'recall': 0.995260663507109, 'f1': 0.995260663507109, 'number': 211} | {'precision': 0.9906542056074766, 'recall': 0.9953051643192489, 'f1': 0.9929742388758782, 'number': 213} | 0.9863 | 0.9886 | 0.9874 | 0.9944 | |
|
|
| 0.0053 | 7.0 | 385 | 0.0259 | {'precision': 0.9769585253456221, 'recall': 0.9769585253456221, 'f1': 0.9769585253456222, 'number': 217} | {'precision': 0.9914529914529915, 'recall': 0.9914529914529915, 'f1': 0.9914529914529915, 'number': 234} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 211} | {'precision': 0.9953271028037384, 'recall': 1.0, 'f1': 0.9976580796252927, 'number': 213} | 0.9909 | 0.992 | 0.9914 | 0.9960 | |
|
|
| 0.005 | 8.0 | 440 | 0.0255 | {'precision': 0.9723502304147466, 'recall': 0.9723502304147466, 'f1': 0.9723502304147466, 'number': 217} | {'precision': 0.9872340425531915, 'recall': 0.9914529914529915, 'f1': 0.9893390191897654, 'number': 234} | {'precision': 0.995260663507109, 'recall': 0.995260663507109, 'f1': 0.995260663507109, 'number': 211} | {'precision': 0.9906542056074766, 'recall': 0.9953051643192489, 'f1': 0.9929742388758782, 'number': 213} | 0.9863 | 0.9886 | 0.9874 | 0.9944 | |
|
|
| 0.0034 | 9.0 | 495 | 0.0281 | {'precision': 0.9768518518518519, 'recall': 0.9723502304147466, 'f1': 0.97459584295612, 'number': 217} | {'precision': 0.9872340425531915, 'recall': 0.9914529914529915, 'f1': 0.9893390191897654, 'number': 234} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 211} | {'precision': 0.9953271028037384, 'recall': 1.0, 'f1': 0.9976580796252927, 'number': 213} | 0.9897 | 0.9909 | 0.9903 | 0.9952 | |
|
|
| 0.0032 | 10.0 | 550 | 0.0290 | {'precision': 0.9723502304147466, 'recall': 0.9723502304147466, 'f1': 0.9723502304147466, 'number': 217} | {'precision': 0.9914163090128756, 'recall': 0.9871794871794872, 'f1': 0.9892933618843683, 'number': 234} | {'precision': 0.995260663507109, 'recall': 0.995260663507109, 'f1': 0.995260663507109, 'number': 211} | {'precision': 0.9906542056074766, 'recall': 0.9953051643192489, 'f1': 0.9929742388758782, 'number': 213} | 0.9874 | 0.9874 | 0.9874 | 0.9944 | |
|
|
| 0.0032 | 11.0 | 605 | 0.0306 | {'precision': 0.9723502304147466, 'recall': 0.9723502304147466, 'f1': 0.9723502304147466, 'number': 217} | {'precision': 0.9913793103448276, 'recall': 0.9829059829059829, 'f1': 0.9871244635193134, 'number': 234} | {'precision': 0.995260663507109, 'recall': 0.995260663507109, 'f1': 0.995260663507109, 'number': 211} | {'precision': 0.986046511627907, 'recall': 0.9953051643192489, 'f1': 0.9906542056074766, 'number': 213} | 0.9863 | 0.9863 | 0.9863 | 0.9936 | |
|
|
| 0.0018 | 12.0 | 660 | 0.0273 | {'precision': 0.9769585253456221, 'recall': 0.9769585253456221, 'f1': 0.9769585253456222, 'number': 217} | {'precision': 0.9914529914529915, 'recall': 0.9914529914529915, 'f1': 0.9914529914529915, 'number': 234} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 211} | {'precision': 0.9953271028037384, 'recall': 1.0, 'f1': 0.9976580796252927, 'number': 213} | 0.9909 | 0.992 | 0.9914 | 0.9960 | |
|
|
| 0.0007 | 13.0 | 715 | 0.0266 | {'precision': 0.9769585253456221, 'recall': 0.9769585253456221, 'f1': 0.9769585253456222, 'number': 217} | {'precision': 0.9914529914529915, 'recall': 0.9914529914529915, 'f1': 0.9914529914529915, 'number': 234} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 211} | {'precision': 0.9953271028037384, 'recall': 1.0, 'f1': 0.9976580796252927, 'number': 213} | 0.9909 | 0.992 | 0.9914 | 0.9960 | |
|
|
| 0.0006 | 14.0 | 770 | 0.0292 | {'precision': 0.9769585253456221, 'recall': 0.9769585253456221, 'f1': 0.9769585253456222, 'number': 217} | {'precision': 0.9914529914529915, 'recall': 0.9914529914529915, 'f1': 0.9914529914529915, 'number': 234} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 211} | {'precision': 0.9953271028037384, 'recall': 1.0, 'f1': 0.9976580796252927, 'number': 213} | 0.9909 | 0.992 | 0.9914 | 0.9960 | |
|
|
| 0.0006 | 15.0 | 825 | 0.0293 | {'precision': 0.9769585253456221, 'recall': 0.9769585253456221, 'f1': 0.9769585253456222, 'number': 217} | {'precision': 0.9914529914529915, 'recall': 0.9914529914529915, 'f1': 0.9914529914529915, 'number': 234} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 211} | {'precision': 0.9953271028037384, 'recall': 1.0, 'f1': 0.9976580796252927, 'number': 213} | 0.9909 | 0.992 | 0.9914 | 0.9960 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.3 |
|
|
- Pytorch 2.4.0 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
|
|
|
