|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
model-index: |
|
- name: dit-base-Document_Classification-Desafio_1 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: validation |
|
split: train |
|
args: validation |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9865 |
|
language: |
|
- en |
|
--- |
|
|
|
# dit-base-Document_Classification-Desafio_1 |
|
|
|
This model is a fine-tuned version of [microsoft/dit-base](https://huggingface.co/microsoft/dit-base). |
|
|
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0436 |
|
- Accuracy: 0.9865 |
|
- F1 |
|
- Weighted: 0.9865 |
|
- Micro: 0.9865 |
|
- Macro: 0.9863 |
|
- Recall |
|
- Weighted: 0.9865 |
|
- Micro: 0.9865 |
|
- Macro: 0.9861 |
|
- Precision |
|
- Weighted: 0.9869 |
|
- Micro: 0.9865 |
|
- Macro: 0.9870 |
|
|
|
## Model description |
|
|
|
For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Document%20AI/Multiclass%20Classification/Document%20Classification%20-%20Desafio%201/Document%20Classification%20-%20Desafio%201.ipynb |
|
|
|
## Intended uses & limitations |
|
|
|
This model is intended to demonstrate my ability to solve a complex problem using technology. |
|
|
|
## Training and evaluation data |
|
|
|
Dataset Source: https://www.kaggle.com/datasets/rywgar/document-classification-desafio-1 |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted F1 | Micro F1 | Macro F1 | Weighted Recall | Micro Recall | Macro Recall | Weighted Precision | Micro Precision | Macro Precision | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:--------:|:---------------:|:------------:|:------------:|:------------------:|:---------------:|:---------------:| |
|
| 0.8316 | 0.99 | 62 | 0.7519 | 0.743 | 0.7020 | 0.743 | 0.7015 | 0.743 | 0.743 | 0.7430 | 0.6827 | 0.743 | 0.6819 | |
|
| 0.3561 | 2.0 | 125 | 0.2302 | 0.9395 | 0.9401 | 0.9395 | 0.9400 | 0.9395 | 0.9395 | 0.9394 | 0.9482 | 0.9395 | 0.9480 | |
|
| 0.2222 | 2.99 | 187 | 0.1350 | 0.956 | 0.9564 | 0.956 | 0.9561 | 0.956 | 0.956 | 0.9551 | 0.9598 | 0.956 | 0.9600 | |
|
| 0.1705 | 4.0 | 250 | 0.0873 | 0.9725 | 0.9727 | 0.9725 | 0.9725 | 0.9725 | 0.9725 | 0.9721 | 0.9740 | 0.9725 | 0.9740 | |
|
| 0.1541 | 4.99 | 312 | 0.0642 | 0.9825 | 0.9825 | 0.9825 | 0.9824 | 0.9825 | 0.9825 | 0.9822 | 0.9830 | 0.9825 | 0.9830 | |
|
| 0.1253 | 6.0 | 375 | 0.0330 | 0.9915 | 0.9915 | 0.9915 | 0.9914 | 0.9915 | 0.9915 | 0.9913 | 0.9916 | 0.9915 | 0.9916 | |
|
| 0.1196 | 6.99 | 437 | 0.0524 | 0.982 | 0.9822 | 0.982 | 0.9820 | 0.982 | 0.982 | 0.9817 | 0.9832 | 0.982 | 0.9832 | |
|
| 0.0896 | 7.94 | 496 | 0.0436 | 0.9865 | 0.9865 | 0.9865 | 0.9863 | 0.9865 | 0.9865 | 0.9861 | 0.9869 | 0.9865 | 0.9870 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
