cat_vs_dogs_vit_model
This model is a fine-tuned version of openai/clip-vit-large-patch14 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6518
- Accuracy: 0.6095
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 |
|---|---|---|---|---|
| 0.771 | 0.5 | 500 | 0.6933 | 0.4995 |
| 0.6967 | 1.0 | 1000 | 0.6882 | 0.556 |
| 0.695 | 1.5 | 1500 | 0.6728 | 0.581 |
| 0.6733 | 2.0 | 2000 | 0.6950 | 0.5915 |
| 0.6768 | 2.5 | 2500 | 0.6694 | 0.5855 |
| 0.6639 | 3.0 | 3000 | 0.6829 | 0.5795 |
| 0.652 | 3.5 | 3500 | 0.6637 | 0.5925 |
| 0.642 | 4.0 | 4000 | 0.6518 | 0.6095 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 2