tanganke's picture
Upload folder using huggingface_hub
721ec59 verified
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