food-classification-ai-vit-5e
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7886
- Accuracy: 0.8175
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0684 | 1.0 | 947 | 2.0226 | 0.7242 |
| 1.1222 | 2.0 | 1894 | 1.1585 | 0.7774 |
| 0.7885 | 3.0 | 2841 | 0.9156 | 0.8013 |
| 0.667 | 4.0 | 3788 | 0.8209 | 0.8145 |
| 0.616 | 5.0 | 4735 | 0.7886 | 0.8175 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1