my_food_model
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: 0.5005
- Accuracy: 0.915
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
3.2078 | 0.99 | 62 | 2.9572 | 0.787 |
1.7221 | 2.0 | 125 | 1.6469 | 0.861 |
1.2109 | 2.99 | 187 | 1.1555 | 0.894 |
0.81 | 4.0 | 250 | 0.8631 | 0.91 |
0.6486 | 4.99 | 312 | 0.7190 | 0.908 |
0.5162 | 6.0 | 375 | 0.6194 | 0.91 |
0.4567 | 6.99 | 437 | 0.5399 | 0.924 |
0.43 | 8.0 | 500 | 0.5146 | 0.922 |
0.3723 | 8.99 | 562 | 0.4914 | 0.922 |
0.3938 | 9.92 | 620 | 0.5005 | 0.915 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 2
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.