---
base_model:
- openai/clip-vit-base-patch32
datasets:
- dpdl-benchmark/oxford_flowers102
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.

![alt text](image.png)

## Evaluation Results

Validation set accuracy:

- pre-trained: 0.6803921461105347
- fine-tuned: 0.8980392217636108

Test set accuracy:

- pre-trained: 0.6644982695579529
- fine-tuned: 0.8855098485946655