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: 2.4728
- Accuracy: 0.6067
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: 16
- 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 |
|---|---|---|---|---|
| 3.588 | 1.0 | 184 | 3.2349 | 0.1522 |
| 3.0928 | 2.0 | 368 | 2.8819 | 0.3478 |
| 2.7571 | 3.0 | 552 | 2.6433 | 0.5149 |
| 2.5459 | 4.0 | 736 | 2.5048 | 0.6019 |
| 2.4484 | 5.0 | 920 | 2.4601 | 0.6155 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1