bikekowal/models_diff

1---2library_name: transformers3license: apache-2.04base_model: google/vit-base-patch16-224-in21k5tags:6- image-classification7- vision8- generated_from_trainer9datasets:10- imagefolder11metrics:12- accuracy13model-index:14- name: models_diff15  results:16  - task:17      name: Image Classification18      type: image-classification19    dataset:20      name: imagefolder21      type: imagefolder22      config: default23      split: train24      args: default25    metrics:26    - name: Accuracy27      type: accuracy28      value: 1.029---30 31<!-- This model card has been generated automatically according to the information the Trainer had access to. You32should probably proofread and complete it, then remove this comment. -->33 34# models_diff35 36This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.37It achieves the following results on the evaluation set:38- Loss: 0.000139- Accuracy: 1.040 41## Model description42 43More information needed44 45## Intended uses & limitations46 47More information needed48 49## Training and evaluation data50 51More information needed52 53## Training procedure54 55### Training hyperparameters56 57The following hyperparameters were used during training:58- learning_rate: 5e-0559- train_batch_size: 1660- eval_batch_size: 1661- seed: 4262- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments63- lr_scheduler_type: linear64- num_epochs: 500.065 66### Training results67 68 69 70### Framework versions71 72- Transformers 4.48.0.dev073- Pytorch 2.5.1+cu12474- Datasets 3.2.075- Tokenizers 0.21.076