google-vit-Base-finetuned-food101
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: 0.5531
- Accuracy: 0.9727
- F1: 0.9740
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 3.4867 | 1.0 | 157 | 3.2502 | 0.8793 | 0.8778 |
| 2.0982 | 2.0 | 314 | 1.9278 | 0.9353 | 0.9355 |
| 1.5644 | 3.0 | 471 | 1.3466 | 0.9633 | 0.9639 |
| 1.1841 | 4.0 | 628 | 1.0414 | 0.9653 | 0.9662 |
| 1.0235 | 5.0 | 785 | 0.8482 | 0.9687 | 0.9696 |
| 0.8153 | 6.0 | 942 | 0.7218 | 0.9673 | 0.9688 |
| 0.7418 | 7.0 | 1099 | 0.6439 | 0.9687 | 0.9700 |
| 0.6897 | 8.0 | 1256 | 0.5831 | 0.972 | 0.9730 |
| 0.6453 | 9.0 | 1413 | 0.5531 | 0.9727 | 0.9740 |
| 0.6199 | 9.9408 | 1560 | 0.5457 | 0.9707 | 0.9720 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1