--- library_name: transformers license: apache-2.0 base_model: facebook/levit-256 tags: - generated_from_trainer datasets: - imagefolder model-index: - name: LeViT results: [] --- # LeViT This model is a fine-tuned version of [facebook/levit-256](https://huggingface.co/facebook/levit-256) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 1.2414 ## 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 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.6233 | 1.0 | 77 | 0.5909 | | 0.4740 | 2.0 | 154 | 0.4537 | | 0.3521 | 3.0 | 231 | 0.5897 | | 0.2737 | 4.0 | 308 | 1.0422 | | 0.2395 | 5.0 | 385 | 0.7413 | | 0.2103 | 6.0 | 462 | 0.7779 | | 0.1957 | 7.0 | 539 | 0.5417 | | 0.1613 | 8.0 | 616 | 0.2639 | | 0.1751 | 9.0 | 693 | 0.6996 | | 0.1552 | 10.0 | 770 | 1.2414 | ### Framework versions - Transformers 5.22.1 - Pytorch 2.14.1+cu130 - Datasets 4.8.5 - Tokenizers 0.23.3