model
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: 0.8671
- Accuracy: 0.8235
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9738 | 0.94 | 8 | 1.1530 | 0.5882 |
| 0.8674 | 2.0 | 17 | 1.0818 | 0.5882 |
| 0.708 | 2.94 | 25 | 1.0412 | 0.5882 |
| 0.7004 | 4.0 | 34 | 0.9774 | 0.7647 |
| 0.5957 | 4.94 | 42 | 1.0344 | 0.6471 |
| 0.5273 | 5.65 | 48 | 0.8671 | 0.8235 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1