<!-- 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. -->
vit-finetuned-vanilla-cifar10-0
This model is a fine-tuned version of 02shanky/vit-finetuned-cifar10 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0306
- Accuracy: 0.992
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 316 | 0.0619 | 0.9836 |
| 0.2651 | 2.0 | 633 | 0.0460 | 0.9867 |
| 0.2651 | 3.0 | 949 | 0.0415 | 0.9878 |
| 0.1967 | 4.0 | 1266 | 0.0326 | 0.9916 |
| 0.1552 | 4.99 | 1580 | 0.0306 | 0.992 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
