imdatta0/qwen3-4b-swegym-moto-kl02-multitrain-grpo-tfpen10-b04-lr1e6-s12-adapter

Qwen3-4B SWE-Gym moto KL02 target-file penalty ablation adapter

This repository contains a PEFT LoRA adapter checkpoint from the Qwen3 SWE-Gym moto investigation.

Negative ablation: target-file missing penalty did not improve held-out greedy over the inherited KL02 adapter.

Local source checkpoint before upload:

/mnt/disks/unslothai/datta0/cache/qwen3-grpo-patch/20260604235441swegymq4b-kl02-multitrain-grpo-tfpen10-b04-lr1e6-s122bc44f3/checkpoints/best_holdout

Use with the base model unsloth/Qwen3-4B-Instruct-2507.