platzi-vit-model-massimo
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the pokemon-classification dataset. It achieves the following results on the evaluation set:
- Loss: 7.8941
- Accuracy: 0.0820
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.9383 | 0.82 | 500 | 6.3834 | 0.0360 |
| 0.3399 | 1.64 | 1000 | 7.1051 | 0.0755 |
| 0.0749 | 2.46 | 1500 | 7.6120 | 0.0885 |
| 0.0332 | 3.28 | 2000 | 7.8941 | 0.0820 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3