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-1stGen-Pokemon-Images
results: []
vit-base-1stGen-Pokemon-Images
This model is a fine-tuned version of google/vit-base-patch16-224 on the Dusduo/1stGen-Pokemon-Images dataset. It achieves the following results on the evaluation set:
- Loss: 1.0561
- Accuracy: 0.8175
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: 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 |
|---|---|---|---|---|
| 2.4052 | 1.0 | 422 | 2.2029 | 0.6386 |
| 1.4347 | 2.0 | 844 | 1.4776 | 0.7536 |
| 0.9834 | 3.0 | 1266 | 1.2078 | 0.7950 |
| 0.8073 | 4.0 | 1688 | 1.0888 | 0.8187 |
| 0.6758 | 5.0 | 2110 | 1.0561 | 0.8175 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1