|
--- |
|
license: cc-by-nc-sa-4.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: Output_LayoutLMv3_v5 |
|
results: [] |
|
datasets: |
|
- Noureddinesa/LayoutLmv3_v1 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# Output_LayoutLMv3_v5 |
|
|
|
This model is a fine-tuned version of [microsoft/layoutlmv3-large](https://huggingface.co/microsoft/layoutlmv3-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3054 |
|
- Precision: 0.8505 |
|
- Recall: 0.8273 |
|
- F1: 0.8387 |
|
- Accuracy: 0.9723 |
|
|
|
## 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: 1e-06 |
|
- train_batch_size: 3 |
|
- weight_decay = 0.1 (Regularization) |
|
- eval_batch_size: 3 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 3000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 2.38 | 100 | 0.2910 | 0.7636 | 0.7636 | 0.7636 | 0.9637 | |
|
| No log | 4.76 | 200 | 0.2822 | 0.8318 | 0.8091 | 0.8203 | 0.9706 | |
|
| No log | 7.14 | 300 | 0.2942 | 0.8148 | 0.8 | 0.8073 | 0.9689 | |
|
| No log | 9.52 | 400 | 0.2821 | 0.7909 | 0.7909 | 0.7909 | 0.9671 | |
|
| 0.0005 | 11.9 | 500 | 0.2896 | 0.7909 | 0.7909 | 0.7909 | 0.9671 | |
|
| 0.0005 | 14.29 | 600 | 0.2914 | 0.8241 | 0.8091 | 0.8165 | 0.9706 | |
|
| 0.0005 | 16.67 | 700 | 0.2912 | 0.8095 | 0.7727 | 0.7907 | 0.9689 | |
|
| 0.0005 | 19.05 | 800 | 0.2578 | 0.8241 | 0.8091 | 0.8165 | 0.9706 | |
|
| 0.0005 | 21.43 | 900 | 0.2830 | 0.8241 | 0.8091 | 0.8165 | 0.9706 | |
|
| 0.0005 | 23.81 | 1000 | 0.2878 | 0.8411 | 0.8182 | 0.8295 | 0.9723 | |
|
| 0.0005 | 26.19 | 1100 | 0.3151 | 0.8113 | 0.7818 | 0.7963 | 0.9689 | |
|
| 0.0005 | 28.57 | 1200 | 0.3142 | 0.7706 | 0.7636 | 0.7671 | 0.9637 | |
|
| 0.0005 | 30.95 | 1300 | 0.2972 | 0.8273 | 0.8273 | 0.8273 | 0.9723 | |
|
| 0.0005 | 33.33 | 1400 | 0.2866 | 0.8148 | 0.8 | 0.8073 | 0.9706 | |
|
| 0.0004 | 35.71 | 1500 | 0.2737 | 0.8288 | 0.8364 | 0.8326 | 0.9723 | |
|
| 0.0004 | 38.1 | 1600 | 0.2653 | 0.8532 | 0.8455 | 0.8493 | 0.9740 | |
|
| 0.0004 | 40.48 | 1700 | 0.2740 | 0.8108 | 0.8182 | 0.8145 | 0.9706 | |
|
| 0.0004 | 42.86 | 1800 | 0.2861 | 0.8198 | 0.8273 | 0.8235 | 0.9706 | |
|
| 0.0004 | 45.24 | 1900 | 0.2904 | 0.7788 | 0.8 | 0.7892 | 0.9671 | |
|
| 0.0004 | 47.62 | 2000 | 0.2899 | 0.7788 | 0.8 | 0.7892 | 0.9671 | |
|
| 0.0004 | 50.0 | 2100 | 0.2957 | 0.8108 | 0.8182 | 0.8145 | 0.9689 | |
|
| 0.0004 | 52.38 | 2200 | 0.2962 | 0.8505 | 0.8273 | 0.8387 | 0.9723 | |
|
| 0.0004 | 54.76 | 2300 | 0.2962 | 0.8505 | 0.8273 | 0.8387 | 0.9723 | |
|
| 0.0004 | 57.14 | 2400 | 0.3057 | 0.8505 | 0.8273 | 0.8387 | 0.9723 | |
|
| 0.0002 | 59.52 | 2500 | 0.3070 | 0.8505 | 0.8273 | 0.8387 | 0.9723 | |
|
| 0.0002 | 61.9 | 2600 | 0.3050 | 0.8505 | 0.8273 | 0.8387 | 0.9723 | |
|
| 0.0002 | 64.29 | 2700 | 0.3050 | 0.8505 | 0.8273 | 0.8387 | 0.9723 | |
|
| 0.0002 | 66.67 | 2800 | 0.3052 | 0.8505 | 0.8273 | 0.8387 | 0.9723 | |
|
| 0.0002 | 69.05 | 2900 | 0.3052 | 0.8505 | 0.8273 | 0.8387 | 0.9723 | |
|
| 0.0 | 71.43 | 3000 | 0.3054 | 0.8505 | 0.8273 | 0.8387 | 0.9723 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.13.3 |
