---
license: mit
tags:
- maze
- reinforcement-learning
- sft
- gos
---

# Maze 17x17 - bs512 Prior Ladder

Artifacts for the GOS x base-competence RL sweep on the 17x17 maze task.

## Contents

### `checkpoints/`

Six SFT checkpoints from a single training run with bs=512, lr=1e-4
constant, training random-trajectory SFT data on a 3M-param Qwen2 model
(4 layers, hidden=256). Trainset Pass@1 (256 prompts x 8 gens, T=1.0):

| Checkpoint  | SFT step | Pass@1 | Pass@4 |
|-------------|---------:|-------:|-------:|
| `ckpt-2500` |     2500 |  0.05% |  0.20% |
| `ckpt-3500` |     3500 |  0.10% |  0.39% |
| `ckpt-4500` |     4500 |  0.24% |  0.98% |
| `ckpt-5500` |     5500 |  1.03% |  3.93% |
| `ckpt-6500` |     6500 |  3.91% | 14.73% |
| `ckpt-7500` |     7500 |  8.35% | 28.75% |

The first four span the deep weak-prior regime (where continuous-reward RL
matters most); the last two are mid-prior, useful for testing whether the
GOS / GRPO gap narrows as base competence improves.

### `data/`

- `train_random.json` - 1.3M random-trajectory SFT examples
- `test.json` - 256 held-out prompts (same split used by SFT eval and RL validation)

Each example is a serialized maze (symbolic grid tokens + actions) following
the MaxRL Maze-17 format.

## Reproduction

Code: https://github.com/stablegradients/GOS-17X17-Maze