<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
finetuned-indian-food
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the indian_food_images dataset. It achieves the following results on the evaluation set:
- Loss: 0.2342
- Accuracy: 0.9437
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1912 | 0.3 | 100 | 0.9449 | 0.8470 |
| 0.7387 | 0.6 | 200 | 0.5696 | 0.8969 |
| 0.6616 | 0.9 | 300 | 0.4609 | 0.8969 |
| 0.4093 | 1.2 | 400 | 0.4250 | 0.8937 |
| 0.3707 | 1.5 | 500 | 0.3226 | 0.9182 |
| 0.3725 | 1.8 | 600 | 0.3941 | 0.8895 |
| 0.2317 | 2.1 | 700 | 0.2870 | 0.9309 |
| 0.256 | 2.4 | 800 | 0.2753 | 0.9267 |
| 0.2077 | 2.7 | 900 | 0.2698 | 0.9341 |
| 0.1442 | 3.0 | 1000 | 0.2775 | 0.9288 |
| 0.2138 | 3.3 | 1100 | 0.2342 | 0.9437 |
| 0.1862 | 3.6 | 1200 | 0.2412 | 0.9394 |
| 0.142 | 3.9 | 1300 | 0.2347 | 0.9437 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
