food101-deit-tiny-patch16-224
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6538
- Accuracy: 0.8204
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: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.7988 | 1.0 | 9469 | 1.4392 | 0.6555 |
1.5581 | 2.0 | 18938 | 1.1165 | 0.7145 |
1.2981 | 3.0 | 28407 | 0.9254 | 0.7558 |
1.4347 | 4.0 | 37876 | 0.8343 | 0.7739 |
0.9679 | 5.0 | 47345 | 0.7731 | 0.7922 |
0.9975 | 6.0 | 56814 | 0.7378 | 0.7998 |
1.0269 | 7.0 | 66283 | 0.7022 | 0.8073 |
0.8969 | 8.0 | 75752 | 0.6865 | 0.8117 |
0.8152 | 9.0 | 85221 | 0.6641 | 0.8194 |
0.7437 | 10.0 | 94690 | 0.6538 | 0.8204 |
Framework versions
- Transformers 4.38.0
- Pytorch 2.1.2+cu118
- Datasets 2.19.1
- Tokenizers 0.15.2
- Downloads last month
- 20
Model tree for pkr7098/food101-deit-tiny-patch16-224
Base model
facebook/deit-tiny-patch16-224