cifarv2
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2653
- Accuracy: 0.921
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 |
|---|---|---|---|---|
| 0.6994 | 1.0 | 250 | 0.7132 | 0.8758 |
| 0.4271 | 2.0 | 500 | 0.4477 | 0.894 |
| 0.3112 | 3.0 | 750 | 0.3905 | 0.8942 |
| 0.3139 | 4.0 | 1000 | 0.3207 | 0.9115 |
| 0.2511 | 5.0 | 1250 | 0.3288 | 0.9048 |
| 0.2652 | 6.0 | 1500 | 0.2977 | 0.9125 |
| 0.2392 | 7.0 | 1750 | 0.2720 | 0.9187 |
| 0.1759 | 8.0 | 2000 | 0.2670 | 0.9173 |
| 0.2024 | 9.0 | 2250 | 0.2606 | 0.9193 |
| 0.1774 | 10.0 | 2500 | 0.2653 | 0.921 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3