<!-- 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. -->
padang_cuisine_classification
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8549
- Accuracy: 0.9509
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1256 | 0.98 | 10 | 2.0189 | 0.6012 |
| 1.839 | 1.95 | 20 | 1.6867 | 0.8834 |
| 1.5149 | 2.93 | 30 | 1.3800 | 0.9080 |
| 1.2405 | 4.0 | 41 | 1.1324 | 0.9141 |
| 1.0359 | 4.98 | 51 | 0.9649 | 0.9387 |
| 0.874 | 5.95 | 61 | 0.8402 | 0.9448 |
| 0.766 | 6.93 | 71 | 0.7901 | 0.9387 |
| 0.7065 | 8.0 | 82 | 0.7175 | 0.9448 |
| 0.6558 | 8.98 | 92 | 0.7112 | 0.9387 |
| 0.6537 | 9.76 | 100 | 0.7114 | 0.9325 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
