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_0576)

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

## Training Hyperparameters

| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 576 |
| Random Crop | False |
| Random Flip | True |

## Performance

| Metric | Value |
|---|---|
| Train Accuracy | 0.9320 |
| Val Accuracy | 0.8677 |
| Test Accuracy | 0.8716 |

## Training Categories

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

`caterpillar`, `bed`, `rabbit`, `television`, `chimpanzee`, `clock`, `pine_tree`, `sea`, `poppy`, `crocodile`, `squirrel`, `cattle`, `bus`, `mouse`, `bear`, `streetcar`, `dolphin`, `crab`, `fox`, `elephant`, `keyboard`, `tiger`, `cup`, `mountain`, `bee`, `shark`, `wardrobe`, `lawn_mower`, `bicycle`, `pickup_truck`, `tulip`, `raccoon`, `plate`, `trout`, `boy`, `snake`, `castle`, `tank`, `rocket`, `lion`, `beaver`, `baby`, `otter`, `man`, `sweet_pepper`, `lamp`, `forest`, `willow_tree`, `mushroom`, `whale`