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_0199)

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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 199 |
| Random Crop | False |
| Random Flip | False |

## Performance

| Metric | Value |
|---|---|
| Train Accuracy | 0.9073 |
| Val Accuracy | 0.5832 |
| Test Accuracy | 0.6044 |

## Training Categories

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

`dolphin`, `poppy`, `porcupine`, `plain`, `can`, `pickup_truck`, `trout`, `raccoon`, `wardrobe`, `house`, `kangaroo`, `bear`, `bowl`, `mountain`, `bee`, `telephone`, `dinosaur`, `whale`, `tank`, `wolf`, `rose`, `turtle`, `snail`, `woman`, `skunk`, `cloud`, `train`, `elephant`, `chair`, `sunflower`, `caterpillar`, `crocodile`, `mouse`, `beetle`, `otter`, `motorcycle`, `bus`, `leopard`, `cup`, `television`, `chimpanzee`, `tractor`, `boy`, `castle`, `flatfish`, `hamster`, `bed`, `snake`, `sea`, `oak_tree`