metadata
base_model:
- openai/clip-vit-base-patch16
datasets:
- tanganke/emnist_letters
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: 0.12437500059604645
- fine-tuned: 0.9528365135192871