Document Classification
Collection
4 items
•
Updated
This model is a fine-tuned version of microsoft/dit-base on the imagefolder dataset. It achieves the following results on the evaluation set:
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/Tobacco-Related%20Documents/Tobacco%20Dataset%20%26%20DiT%20Transformer%20Project_v3.ipynb
This model is intended to demonstrate my ability to solve a complex problem using technology.
Dataset Source: https://www.kaggle.com/datasets/patrickaudriaz/tobacco3482jpg
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted F1 | Micro F1 | Macro F1 |
---|---|---|---|---|---|---|---|
1.9273 | 0.98 | 43 | 1.1368 | 0.5987 | 0.5462 | 0.5987 | 0.5175 |
1.0685 | 1.98 | 86 | 0.5244 | 0.8248 | 0.7939 | 0.8248 | 0.7670 |
0.7373 | 2.98 | 129 | 0.3631 | 0.8808 | 0.8610 | 0.8808 | 0.8318 |
0.641 | 3.98 | 172 | 0.2884 | 0.9045 | 0.8967 | 0.9045 | 0.8732 |
0.5579 | 4.98 | 215 | 0.2192 | 0.9361 | 0.9338 | 0.9361 | 0.9214 |
0.5279 | 5.98 | 258 | 0.2292 | 0.9289 | 0.9263 | 0.9289 | 0.9137 |
0.4918 | 6.98 | 301 | 0.2052 | 0.9368 | 0.9348 | 0.9368 | 0.9218 |
0.4723 | 7.98 | 344 | 0.1958 | 0.9419 | 0.9403 | 0.9419 | 0.9278 |