metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-dogs
results: []
vit-base-dogs
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1696
- Accuracy: 0.9607
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: 10
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2208 | 1.0 | 591 | 0.3024 | 0.9343 |
| 0.4149 | 2.0 | 1182 | 0.2548 | 0.9268 |
| 0.3095 | 3.0 | 1773 | 0.2700 | 0.9329 |
| 0.2928 | 4.0 | 2364 | 0.1921 | 0.9444 |
| 0.2352 | 5.0 | 2955 | 0.1947 | 0.9472 |
| 0.1731 | 6.0 | 3546 | 0.2024 | 0.9458 |
| 0.1778 | 7.0 | 4137 | 0.1967 | 0.9526 |
| 0.156 | 8.0 | 4728 | 0.1780 | 0.9546 |
| 0.135 | 9.0 | 5319 | 0.1818 | 0.9553 |
| 0.1403 | 10.0 | 5910 | 0.1696 | 0.9607 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3