<!-- 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. -->
cheese_classifier
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: 0.4025
- Accuracy: 0.9412
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: 64
- eval_batch_size: 64
- seed: 42
- 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 | 6 | 1.0060 | 0.7647 |
| 1.0375 | 2.0 | 12 | 0.8916 | 0.8824 |
| 1.0375 | 3.0 | 18 | 0.7814 | 0.8941 |
| 0.8401 | 4.0 | 24 | 0.6615 | 0.9529 |
| 0.6428 | 5.0 | 30 | 0.5710 | 0.9529 |
| 0.6428 | 6.0 | 36 | 0.5067 | 0.9412 |
| 0.5242 | 7.0 | 42 | 0.4478 | 0.9412 |
| 0.5242 | 8.0 | 48 | 0.4587 | 0.9294 |
| 0.4139 | 9.0 | 54 | 0.4007 | 0.9647 |
| 0.3762 | 10.0 | 60 | 0.4025 | 0.9412 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.12.1
