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_0775)

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** | train |
| **Base Model** | `facebook/vit-mae-base` |
| **Dataset** | CIFAR100 (50 classes) |

## Training Hyperparameters

| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 775 |
| Random Crop | False |
| Random Flip | False |

## Performance

| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.8365 |
| Test Accuracy | 0.8266 |

## Training Categories

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

`plain`, `road`, `bear`, `shark`, `palm_tree`, `clock`, `ray`, `orange`, `leopard`, `cattle`, `bicycle`, `tiger`, `kangaroo`, `sunflower`, `wardrobe`, `mouse`, `squirrel`, `maple_tree`, `oak_tree`, `tractor`, `orchid`, `pine_tree`, `lizard`, `spider`, `house`, `rabbit`, `plate`, `can`, `dolphin`, `pickup_truck`, `lobster`, `shrew`, `turtle`, `skyscraper`, `mountain`, `table`, `butterfly`, `train`, `bee`, `apple`, `willow_tree`, `pear`, `sweet_pepper`, `castle`, `whale`, `beaver`, `bed`, `bowl`, `raccoon`, `dinosaur`