vit-base-patch16-224-finetuned-food101
This model is a fine-tuned version of google/vit-base-patch16-224 on Food-101 Dataset. It achieves the following results on the evaluation set:
- Loss: 0.6401
- Accuracy: 0.8350
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.912 | 0.9986 | 532 | 0.8397 | 0.7968 |
| 0.7233 | 1.9991 | 1065 | 0.6781 | 0.8294 |
| 0.6047 | 2.9958 | 1596 | 0.6401 | 0.8350 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1