vit-base-patch16-224-food101-v1
This model is a fine-tuned version of google/vit-base-patch16-224 on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2359
- Accuracy: 0.924
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.0682 | 0.99 | 31 | 0.3073 | 0.908 |
0.0425 | 1.98 | 62 | 0.2663 | 0.915 |
0.0262 | 2.98 | 93 | 0.2173 | 0.928 |
0.0446 | 4.0 | 125 | 0.2195 | 0.937 |
0.0642 | 4.96 | 155 | 0.2359 | 0.924 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 34
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.