<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
my_awesome_food_model
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4362
- Accuracy: 0.922
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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2229 | 0.99 | 62 | 1.2187 | 0.896 |
| 0.7939 | 2.0 | 125 | 0.8669 | 0.899 |
| 0.6067 | 2.99 | 187 | 0.6797 | 0.909 |
| 0.4863 | 4.0 | 250 | 0.5495 | 0.919 |
| 0.4002 | 4.99 | 312 | 0.5279 | 0.904 |
| 0.3306 | 6.0 | 375 | 0.4693 | 0.912 |
| 0.3163 | 6.99 | 437 | 0.4206 | 0.929 |
| 0.3294 | 7.94 | 496 | 0.4362 | 0.922 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
