<!-- 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-base-patch16-224-finetuned-imageclassification
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1790
- Accuracy: 0.9502
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 9 | 0.5791 | 0.9004 |
| 1.4122 | 2.0 | 18 | 0.2002 | 0.9359 |
| 0.3147 | 3.0 | 27 | 0.1717 | 0.9502 |
| 0.1907 | 4.0 | 36 | 0.1632 | 0.9466 |
| 0.158 | 5.0 | 45 | 0.1822 | 0.9466 |
| 0.1169 | 6.0 | 54 | 0.1778 | 0.9502 |
| 0.0984 | 7.0 | 63 | 0.1552 | 0.9573 |
| 0.0971 | 8.0 | 72 | 0.1835 | 0.9502 |
| 0.0965 | 9.0 | 81 | 0.1878 | 0.9484 |
| 0.0766 | 10.0 | 90 | 0.1790 | 0.9502 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
