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: 0.2632
- Accuracy: 0.9330
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 |
|---|---|---|---|---|
| 1.1794 | 0.3 | 100 | 0.9208 | 0.8565 |
| 0.6513 | 0.6 | 200 | 0.5410 | 0.8842 |
| 0.5904 | 0.9 | 300 | 0.4978 | 0.8799 |
| 0.4461 | 1.2 | 400 | 0.3669 | 0.9192 |
| 0.5633 | 1.5 | 500 | 0.4340 | 0.8842 |
| 0.2489 | 1.8 | 600 | 0.3355 | 0.9171 |
| 0.3171 | 2.1 | 700 | 0.3286 | 0.9192 |
| 0.3785 | 2.4 | 800 | 0.3232 | 0.9171 |
| 0.2278 | 2.7 | 900 | 0.3338 | 0.9192 |
| 0.0894 | 3.0 | 1000 | 0.2870 | 0.9245 |
| 0.2092 | 3.3 | 1100 | 0.2884 | 0.9288 |
| 0.1466 | 3.6 | 1200 | 0.2673 | 0.9320 |
| 0.1789 | 3.9 | 1300 | 0.2632 | 0.9330 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 86
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.