mschoi/ai-rfm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Track best checkpoint and auto-refresh trajectory artifacts.

Browse Source 
Save the best training checkpoint into a git-tracked artifact, enforce random-time flow matching, and have pre-commit regenerate/stage six trajectory visualizations whenever BEST_PRACTICE is improved.

Made-with: Cursor
This commit is contained in:
demian3b
2026-04-16 17:23:06 +09:00
parent 9e62b514af
commit cb118a676e
9 changed files with 222 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -15,10 +15,12 @@ This repository is intentionally pinned to CUDA 12.6 PyTorch wheels and matching
## Repository policy
- Every attempt must update this README (append a short entry in `## Attempt Log`).
- Flow-matching training time must stay random (middle-time supervision is mandatory).
- Commits touching `train.py` must include:
- `reports/latest_eval.json`
- strictly better `mean_rmsd_100` compared to previous best (enforced by pre-commit).
- `BEST_PRACTICE.json` is auto-updated and staged by pre-commit.
- best checkpoint and trajectory artifacts are auto-regenerated by pre-commit.
## Evaluation target
@@ -31,6 +33,8 @@ This repository is intentionally pinned to CUDA 12.6 PyTorch wheels and matching
- `GUIDELINES.md`: operating rules and workflow.
- `BEST_PRACTICE.json`: current best-known metric and config.
- `reports/latest_eval.json`: most recent measured metric.
- `artifacts/best_model.pt`: best checkpoint from latest improved run.
- `reports/trajectories/`: 6 regenerated trajectories from current best model.
- `scripts/precommit_performance_gate.py`: pre-commit guard for train-related commits.
## Attempt Log
@@ -42,3 +46,5 @@ This repository is intentionally pinned to CUDA 12.6 PyTorch wheels and matching
- 2026-04-16: Moved `BEST_PRACTICE.json` updates out of `train.py`; pre-commit now auto-generates/stages best report from `reports/latest_eval.json` when an improved train.py commit is made.
- 2026-04-16: Re-ran after pre-commit auto-best refactor; current `mean_rmsd_100=2.570120` (improved from `2.582932`).
- 2026-04-16: Added model-type support (`gcn`/`mlp`) and time-sampling control; best current run is `gcn hidden=512 layers=8 batch=96` with `mean_rmsd_100=2.523552`.
- 2026-04-16: Added pre-commit artifact refresh: on best update it now stages `BEST_PRACTICE.json`, `artifacts/best_model.pt`, and regenerates 6 trajectory visualizations in `reports/trajectories/`.
- 2026-04-16: Enforced random-time flow-matching rule (no fixed training time), saved best checkpoint to git-tracked artifact path, and improved metric to `mean_rmsd_100=2.519821` with `gcn hidden=512 layers=8 batch=96`.