tanganke's picture
Upload folder using huggingface_hub
3b814ef verified
metadata
base_model:
  - openai/clip-vit-large-patch14
datasets:
  - tanganke/sun397
metrics:
  - accuracy

Model Card

Model Details

  • Architecture: ViT-Large with patch size 14
  • Training Data: SUN397 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: 0.6830110549926758
  • fine-tuned: 0.8275973796844482