metadata
base_model:
- openai/clip-vit-large-patch14
datasets:
- tanganke/dtd
metrics:
- accuracy
Model Card
Model Details
- Architecture: ViT-Large with patch size 14
- Training Data: DTD 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: 0.554787278175354
- fine-tuned: 0.8547872304916382