training-run-hygiene skillA
training-run-hygiene is agent-read markdown (skill) from uchicago-dsi/ai-sci-skills: Make a training run's health visible: persist a scale-free loss history from the first update, establish that the model can learn on a small subset before spending on a big run, and run outcome-blind longitudinal QC on a fixed roster. Use when launching, resuming, monitoring, or reviewing any scientific training run..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Training Run Hygiene A completed run is not a healthy one. Every rule here exists to make "this model is not learning" visible while the run is still cheap to stop. ## Persist A Scale-Free Training History Every scientific training run must persist an append-only, machine-readable training history from the first optimizer update through every resume. Record at minimum: - update/pass index, total loss, each unweighted loss component and its weighted contribution; - learning rate, gradient norm, elapsed time; - the exact source/unit coverage of the consumed prefix; - training and validation curves separately when a validation objective exists. **Every loss component must also carry, in the same row, the mean square of its own target over its own element set, and the resulting scale-free ratio, where `1.0` is what predicting zero scores.** A loss in physical units may never be reported as evidence that a model fits, because a small absolute error and a small target are indistinguishable without the denominator: a run whose loss read `0.0048` in physical units squared, against a target mean square of `0.0061`, had learned almost nothing and looked healthy for a month. …
Read the whole file at its exact version.
How to install
mdr add uchicago-dsi/ai-sci-skills/training-run-hygiene@git:20260921.9b3de7cmdr add uchicago-dsi/ai-sci-skills/training-run-hygiene@sha256:847f29924c70d0b4Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_pbpphxsujqmyxq4p)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6332 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
uchicago-dsi/ai-sci-skills · 20 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pbpphxsujqmyxq4p GET https://markdownregistry.com/api/v1/resolve?ref=uchicago-dsi/ai-sci-skills/training-run-hygiene GET https://markdownregistry.com/api/v1/blob/847f29924c70d0b4f569812f20c0404baec8f3b88fdfac68a15351545c274926
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.