ft_stable_diffusion
This model is a fine-tuned version of google/vit-base-patch16-224 on the generated by stable diffusion dataset. It achieves the following results on the evaluation set:
- Loss: 0.3650
- Accuracy: 0.9194
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 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 |
|---|---|---|---|---|
| No log | 1.0 | 70 | 0.9239 | 0.7705 |
| 1.1759 | 2.0 | 140 | 0.5778 | 0.8852 |
| 0.5081 | 3.0 | 210 | 0.4438 | 0.9180 |
| 0.5081 | 4.0 | 280 | 0.3857 | 0.9344 |
| 0.3442 | 5.0 | 350 | 0.3700 | 0.9344 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3
- Downloads last month
- 200
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for fernandabufon/ft_stable_diffusion
Base model
google/vit-base-patch16-224