Result Artifacts
These tracked files mirror local smoke/evaluation artifacts and the final curated submission evidence even though outputs/ and checkpoints/ are intentionally git-ignored.
The shared environment files, training scripts/notebooks, and training logs are
indexed in ../submission_artifacts.md.
Current status:
- OpenEnv structure/runtime validation passes locally.
- Test suite passes locally.
- Frontend production build passes locally.
final_submission_evidence/is the current evidence bundle with curated charts, action traces, final reports, and the public HF artifact Space manifest.final_submission_evidence/charts/curated/is the visually reviewed, non-redundant viewing layer used by the root README.final_submission_evidence/charts/all/keeps the full chart pool.final_submission_evidence/charts/stale_superseded/documents older 0.5B/1.5B-only charts and smoke-run mirrors that are retained for auditability.- Final artifact Space: https://huggingface.co/spaces/adithya9903/polyguard-openenv-final-artifacts
- Qwen 3B SFT/GRPO adapter files and checkpoint tree are available through the final artifact Space; Qwen 0.5B and 1.5B currently have reports/history/post-save SFT evidence but no adapter directories in the checked mirrors.
postsave_inference.jsonloads the merged artifact rather than the fallback policy for the older smoke path.improvement_report.jsonshows positive average-reward improvement against the no-change baseline for the older smoke path.hf_space_verification.jsonrecords a live Hugging Face Space validation pass.
Best current evidence:
final_submission_evidence/charts/curated/training/sft_loss_curves_all_models.pngfinal_submission_evidence/charts/curated/training/qwen_3b_grpo_reward_curve.pngfinal_submission_evidence/charts/curated/training/qwen_3b_grpo_loss_curve.pngfinal_submission_evidence/charts/curated/model_comparison/sft_vs_grpo_reward_by_model.pngfinal_submission_evidence/charts/curated/model_comparison/qwen_model_grpo_reward.pngfinal_submission_evidence/charts/curated/product_over_basic_llm/basic_llm_vs_full_pipeline_reward.pngfinal_submission_evidence/charts/curated/product_over_basic_llm/reward_delta_by_seed.pngfinal_submission_evidence/charts/curated/reward_and_safety/reward_component_bars.pngfinal_submission_evidence/charts/curated/inference/inference_validity_reward.pngfinal_submission_evidence/reports/basic_llm_vs_polyguard_report.jsonfinal_submission_evidence/reports/action_traces.jsonlfinal_submission_evidence/manifest.json
Older smoke artifacts remain here for auditability and regression checks. The root compatibility charts such as avg_reward.png and policy_stack_avg_reward.png are intentionally left in place because local gates still check them.