vit-base-patch16-224-in21k-finetuned-lora-food101
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: 0.5152
- Accuracy: 0.8560
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: 0.005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8353 | 1.0 | 133 | 0.6692 | 0.8168 |
| 0.702 | 2.0 | 266 | 0.5892 | 0.8393 |
| 0.6419 | 2.99 | 399 | 0.5615 | 0.8455 |
| 0.5742 | 4.0 | 533 | 0.5297 | 0.8535 |
| 0.4942 | 4.99 | 665 | 0.5152 | 0.8560 |
Framework versions
- PEFT 0.5.0.dev0
- Transformers 4.32.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 54
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Andyrasika/vit-base-patch16-224-in21k-finetuned-lora-food101
Base model
google/vit-base-patch16-224-in21k