metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- image-classification
- animals
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-animals10
results: []
vit-base-animals10
This model is a fine-tuned version of google/vit-base-patch16-224 on the Rapidata/Animals-10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0784
- Accuracy: 0.9762
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0997 | 1.0 | 2356 | 0.0928 | 0.9732 |
| 0.0752 | 2.0 | 4712 | 0.0678 | 0.9809 |
| 0.0743 | 3.0 | 7068 | 0.0584 | 0.9839 |
| 0.0882 | 4.0 | 9424 | 0.0605 | 0.9792 |
| 0.0656 | 5.0 | 11780 | 0.0653 | 0.9813 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.7.0+cu128
- Datasets 3.6.0
- Tokenizers 0.21.1