metadata
base_model:
- openai/clip-vit-large-patch14
datasets:
- mnist
metrics:
- accuracy
Model Card
Model Details
- Architecture: ViT-Large with patch size 14
- Training Data: MNIST dataset
Training Details
Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=32). Only the vision encoder is fine-tuned.
Evaluation Results
- pre-trained: 0.7602328658103943
- fine-tuned: 0.9975429177284241