tanganke/clip-vit-large-patch14_cifar100

Model Card

Model Details

• Architecture: ViT-Large with patch size 14
• Training Data: cifar100 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: 0.7505000233650208
• fine-tuned: 0.9300999641418457