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_0902)

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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 902 |
| Random Crop | True |
| Random Flip | False |

## Performance

| Metric | Value |
|---|---|
| Train Accuracy | 0.7884 |
| Val Accuracy | 0.5624 |
| Test Accuracy | 0.5828 |

## Training Categories

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

`castle`, `seal`, `orange`, `shark`, `streetcar`, `bicycle`, `girl`, `spider`, `road`, `wolf`, `otter`, `cattle`, `snail`, `raccoon`, `palm_tree`, `snake`, `bowl`, `tank`, `plate`, `tulip`, `lawn_mower`, `pine_tree`, `baby`, `lizard`, `caterpillar`, `can`, `keyboard`, `squirrel`, `chimpanzee`, `rocket`, `sunflower`, `orchid`, `beetle`, `cockroach`, `tractor`, `apple`, `kangaroo`, `forest`, `flatfish`, `crab`, `boy`, `table`, `pickup_truck`, `worm`, `maple_tree`, `mushroom`, `leopard`, `shrew`, `cloud`, `train`