vit_101
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: 1.6267
- Accuracy: 0.88
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.7266 | 0.99 | 62 | 2.5317 | 0.814 |
| 1.8315 | 2.0 | 125 | 1.7931 | 0.864 |
| 1.5845 | 2.98 | 186 | 1.6267 | 0.88 |
Framework versions
- Transformers 4.27.2
- Pytorch 2.1.0.dev20230428
- Datasets 2.10.1
- Tokenizers 0.13.2