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: 0.0144
- Accuracy: 0.9981
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 |
---|---|---|---|---|
0.9849 | 0.26 | 100 | 0.8445 | 0.8721 |
0.4628 | 0.51 | 200 | 0.4435 | 0.9201 |
0.4738 | 0.77 | 300 | 0.3339 | 0.9336 |
0.3603 | 1.02 | 400 | 0.2924 | 0.9328 |
0.1792 | 1.28 | 500 | 0.1862 | 0.9560 |
0.2304 | 1.53 | 600 | 0.1352 | 0.9711 |
0.1512 | 1.79 | 700 | 0.1244 | 0.9689 |
0.1805 | 2.04 | 800 | 0.0843 | 0.9805 |
0.1672 | 2.3 | 900 | 0.0576 | 0.9879 |
0.0154 | 2.55 | 1000 | 0.0498 | 0.9900 |
0.0357 | 2.81 | 1100 | 0.0359 | 0.9933 |
0.0241 | 3.06 | 1200 | 0.0290 | 0.9951 |
0.0133 | 3.32 | 1300 | 0.0228 | 0.9967 |
0.0088 | 3.57 | 1400 | 0.0193 | 0.9970 |
0.0511 | 3.83 | 1500 | 0.0144 | 0.9981 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 18