base_model: | |
- openai/clip-vit-base-patch16 | |
datasets: | |
- timm/oxford-iiit-pet | |
metrics: | |
- accuracy | |
# Model Card | |
## Training Details | |
Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=128). | |
Only the vision encoder is fine-tuned. | |
## Evaluation Results | |
Test set accuracy: | |
- pre-trained: 0.8844372034072876 | |
- fine-tuned: 0.9449441432952881 |