andrewlngdn/dsl-debug-7b-sft-step100

DSL Debug 7B — SFT Step 100

Qwen2.5-7B-Instruct fine-tuned on 1,593 debugging trajectories for the DSL Debug environment.

Blog post: Multi-Turn RL for Code Debugging Code + environment: github.com/AndrewLngdn/dsl-debug

Training

• Method: Supervised fine-tuning (verl 0.7)
• Data: 1,593 multi-turn trajectories with tool calls (run, inspect, read_docs, submit)
• Base model: Qwen2.5-7B-Instruct
• Epochs: 2 (step 100 checkpoint)
• LR: 5e-6
• Hardware: 2x A100-SXM4-80GB

Results (held-out test, one-shot)

Split	Base Model	This Model
Standard (481)	50.5%	56.3%
Nonlocal (200)	12.0%	40.0%
Intent-Mismatch (177)	0.6%	7.9%

Alignment Tax

Benchmark	Base	This Model
MMLU (5-shot)	74.6%	74.6%
GSM8K (8-shot)	84.9%	83.9%
HumanEval (0-shot)	65.9%	62.2%

Usage

This checkpoint is primarily used as the starting point for SFT then RL training (GRPO), which achieves the best results.

from huggingface_hub import snapshot_download
snapshot_download("andrewlngdn/dsl-debug-7b-sft-step100",
    local_dir="/workspace/models/sft_7b_step100")

Related Models

Model	Repo
SFT then RL step 35 (best)	andrewlngdn/dsl-debug-7b-sft-rl
RL-only step 30	andrewlngdn/dsl-debug-7b-rl-only-step30