metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-oxford-iiit-pets
results: []
vit-base-oxford-iiit-pets
This model is a fine-tuned version of google/vit-base-patch16-224 on the pcuenq/oxford-pets dataset. It achieves the following results on the evaluation set:
- Loss: 0.2179
- Accuracy: 0.9323
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7065 | 1.0 | 185 | 0.3667 | 0.9188 |
| 0.3156 | 2.0 | 370 | 0.2584 | 0.9350 |
| 0.2181 | 3.0 | 555 | 0.2265 | 0.9364 |
| 0.1802 | 4.0 | 740 | 0.2159 | 0.9337 |
| 0.1732 | 5.0 | 925 | 0.2124 | 0.9364 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1