vit-base-SimpsonsVIT_III
This model is a fine-tuned version of google/vit-base-patch16-224 on the simpsons dataset. It achieves the following results on the evaluation set:
- Loss: 1.1666
- Accuracy: 0.7105
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7106 | 1.0 | 1047 | 1.6790 | 0.6111 |
| 1.3612 | 2.0 | 2094 | 1.3673 | 0.6775 |
| 1.2199 | 3.0 | 3141 | 1.2461 | 0.7033 |
| 1.0933 | 4.0 | 4188 | 1.1879 | 0.7100 |
| 0.9845 | 5.0 | 5235 | 1.1653 | 0.7129 |
Framework versions
- Transformers 4.52.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
- Downloads last month
- 11
Model tree for JoGoCr/vit-base-SimpsonsVIT_III
Base model
google/vit-base-patch16-224