ArrayDice/car_orientation_classification

1---2license: apache-2.03base_model: google/vit-base-patch16-224-in21k4tags:5- generated_from_trainer6metrics:7- accuracy8model-index:9- name: car_orientation_classification210  results: []11---12 13<!-- This model card has been generated automatically according to the information the Trainer had access to. You14should probably proofread and complete it, then remove this comment. -->15 16# car_orientation_classification217 18This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.19It achieves the following results on the evaluation set:20- Loss: 0.680021- Accuracy: 0.692622 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- learning_rate: 5e-0541- train_batch_size: 1642- eval_batch_size: 1643- seed: 4244- gradient_accumulation_steps: 445- total_train_batch_size: 6446- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0847- lr_scheduler_type: linear48- lr_scheduler_warmup_ratio: 0.149- num_epochs: 4050 51### Training results52 53| Training Loss | Epoch | Step | Validation Loss | Accuracy |54|:-------------:|:-----:|:----:|:---------------:|:--------:|55| 1.9933        | 1.0   | 68   | 1.9084          | 0.4099   |56| 1.4721        | 2.0   | 136  | 1.2870          | 0.5124   |57| 1.1677        | 3.0   | 204  | 1.0780          | 0.5265   |58| 0.9919        | 4.0   | 272  | 0.9454          | 0.5760   |59| 0.8392        | 5.0   | 340  | 0.8184          | 0.6926   |60| 0.7778        | 6.0   | 408  | 0.8311          | 0.6431   |61| 0.7341        | 7.0   | 476  | 0.7425          | 0.6572   |62| 0.6695        | 8.0   | 544  | 0.6800          | 0.6926   |63 64 65### Framework versions66 67- Transformers 4.41.268- Pytorch 2.3.0+cu12169- Datasets 2.20.070- Tokenizers 0.19.171