Model-J: MAE Model (model_idx_0865)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
ProbeXModel Details
| Attribute | Value |
|---|
| Subset | MAE |
| Split | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 865 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|
| Train Accuracy | 0.8643 |
| Val Accuracy | 0.8035 |
| Test Accuracy | 0.8022 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, castle, otter, beaver, trout, baby, orange, apple, mouse, crab, bicycle, rabbit, skunk, shrew, forest, squirrel, clock, cloud, mountain, maple_tree, crocodile, sea, bed, wardrobe, girl, shark, pine_tree, dinosaur, flatfish, leopard, bottle, sunflower, plain, cup, whale, couch, wolf, sweet_pepper, bowl, woman, lion, bee, boy, snake, lamp, aquarium_fish, table, palm_tree, plate, skyscraper
