| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: google/vit-base-patch16-224 |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: animalmind-breed-classifier |
| results: [] |
| language: |
| - pt |
| --- |
| |
| <!-- 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. --> |
|
|
| # animalmind-breed-classifier |
|
|
| This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.5476 |
| - Accuracy: 0.8608 |
|
|
| ## 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: 2e-05 |
| - train_batch_size: 32 |
| - eval_batch_size: 32 |
| - 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 |
| - lr_scheduler_warmup_steps: 200 |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | 1.7503 | 1.0 | 515 | 1.5708 | 0.7945 | |
| | 0.6028 | 2.0 | 1030 | 0.7066 | 0.8554 | |
| | 0.2734 | 3.0 | 1545 | 0.5432 | 0.8647 | |
| | 0.1209 | 4.0 | 2060 | 0.5182 | 0.8610 | |
| | 0.0614 | 5.0 | 2575 | 0.5125 | 0.8610 | |
| | 0.0335 | 6.0 | 3090 | 0.5184 | 0.8654 | |
| | 0.0217 | 7.0 | 3605 | 0.5368 | 0.8618 | |
| | 0.0267 | 8.0 | 4120 | 0.5456 | 0.8593 | |
| | 0.0179 | 9.0 | 4635 | 0.5433 | 0.8598 | |
| | 0.0091 | 10.0 | 5150 | 0.5476 | 0.8608 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 5.12.0 |
| - Pytorch 2.11.0+cu128 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
