vit-base-food101-demo-v5
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: 0.5434
- Accuracy: 0.8559
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6283 | 1.0 | 4735 | 0.9875 | 0.7409 |
| 0.9874 | 2.0 | 9470 | 0.7967 | 0.7894 |
| 0.7102 | 3.0 | 14205 | 0.6455 | 0.8255 |
| 0.4917 | 4.0 | 18940 | 0.5502 | 0.8524 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1
- Downloads last month
- 49
Dataset used to train eslamxm/vit-base-food101
Evaluation results
- Accuracy on food101self-reported0.856