food_type_classification_model
Easily classify any food product into Plant-based(PLANT_BASED) or Animal-based(ANIMAL_BASED) based on ingredients or product title.
This model was trained using a dataset from USDA FoodData Central which contains the ANIMAL_BASED and PLANT_BASED classification labels based on the available protein type in a food product.
This model is a fine-tuned version of distilbert-base-uncased . It achieves the following results on the evaluation set:
- Loss: 0.0249
- Accuracy: 0.9940
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 336 | 0.0351 | 0.9933 |
| 0.0711 | 2.0 | 672 | 0.0249 | 0.9940 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0