| --- |
| 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 |
| license: mit |
| --- |
| |
| # 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 |
|
|
|
|
| ## License Notice |
| This model is a fine-tuned derivative of a pretrained model. |
| Users must comply with the original model license. |
|
|
|
|
| ## Dataset Notice |
| This model was fine-tuned on third-party datasets which may have separate licenses or usage restrictions. |
