vit-base-patch16-224-in21k-finetuned-lora-food101
This model was trained from scratch on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1086
- Accuracy: 0.966
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 9 | 0.6070 | 0.878 |
| 2.2106 | 2.0 | 18 | 0.1910 | 0.948 |
| 0.354 | 3.0 | 27 | 0.1266 | 0.966 |
| 0.2142 | 4.0 | 36 | 0.1141 | 0.968 |
| 0.1788 | 5.0 | 45 | 0.1086 | 0.966 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1