---
base_model:
- openai/clip-vit-base-patch16
datasets:
- tanganke/cifar100
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: 0.6632999777793884
- fine-tuned: 0.8877999782562256