README.md

---
base_model: facebook/vit-mae-base
library_name: transformers
pipeline_tag: image-classification
tags:
  - probex
  - model-j
  - weight-space-learning
---

# Model-J: MAE Model (model_idx_0363)

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

<p align="center">
    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
</p>

![ProbeX](https://raw.githubusercontent.com/eliahuhorwitz/ProbeX/main/imgs/poster.png)

## Model Details

| Attribute | Value |
|---|---|
| **Subset** | MAE |
| **Split** | test |
| **Base Model** | `facebook/vit-mae-base` |
| **Dataset** | CIFAR100 (50 classes) |

## Training Hyperparameters

| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 363 |
| Random Crop | False |
| Random Flip | False |

## Performance

| Metric | Value |
|---|---|
| Train Accuracy | 0.9732 |
| Val Accuracy | 0.8803 |
| Test Accuracy | 0.8800 |

## Training Categories

The model was fine-tuned on the following 50 CIFAR100 classes:

`oak_tree`, `rabbit`, `flatfish`, `road`, `porcupine`, `tractor`, `lobster`, `bottle`, `lion`, `bus`, `streetcar`, `cloud`, `crab`, `spider`, `bear`, `beaver`, `ray`, `bridge`, `clock`, `tulip`, `shrew`, `house`, `palm_tree`, `skyscraper`, `keyboard`, `telephone`, `plain`, `turtle`, `orchid`, `aquarium_fish`, `pine_tree`, `mushroom`, `pear`, `leopard`, `elephant`, `girl`, `bicycle`, `cattle`, `mouse`, `seal`, `whale`, `snail`, `mountain`, `willow_tree`, `possum`, `skunk`, `dinosaur`, `orange`, `crocodile`, `castle`