seccodeplt-qwen2.5-coder-7b-grpo-kl-beta-0.001-real-reward-v2/README.md

base_model, library_name, datasets, tags

base_model	library_name	datasets	tags
Qwen/Qwen2.5-Coder-7B-Instruct	transformers	fengyao1909/SecCodePLT_Plus	code security grpo seccodeplt

seccodeplt-qwen2.5-coder-7b-grpo-kl-beta-0.001-real-reward-v2

GRPO with KL regularization (beta=0.001) for the SecCodePLT+ compliance experiment using Qwen/Qwen2.5-Coder-7B-Instruct. This v2 run corrects causal-label alignment and uses the official ReaL safety-unit-test reward with DAPO-style token loss and dynamic sampling. Training used seed 42 and the official 655-example training split. Evaluation used greedy decoding on all 164 official test examples.

Evaluation

Metric	Value
Mean reward	0.511317
Output format pass	98.78%
Syntax pass	98.17%
Capability pass	38.41%
Safety pass	64.02%
Joint pass	31.10%

Limitations

This is a single-seed research checkpoint evaluated with the benchmark's resource-bounded Python verifier. It is not a general guarantee of secure code.