RepoJournal
Alignment & Post-training Alignment & Post-training
18 wires and counting

$ follow Alignment & Post-training

Keep up with Alignment & Post-training in about 3 minutes: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

or

fair warning: these emails are deeply technical. diffs, version numbers, CVEs, benchmark deltas. if that's not your idea of a good read, this isn't your newsletter.

Folds into your digest — weekly by default, monthly if you prefer. Unsubscribe in one click.

$ status

wire 2026-10-24
stories 10

© 2026 RepoJournal Home Showcase How it works Privacy

$ the-wire · showcase

MILES ships a 25-benchmark eval panel and simpler config presets

By RepoJournal · Filed · About Alignment & Post-training · Composed from the cited sources · methodology

open-instruct's MILES template now runs the full 25-entry post-training and text-safety evaluation panel at training endpoints only, while a rewritten set of env and run defaults changes how existing jobs resolve.

Add the post-training evaluation panel to the large MILES template allenai/open-instruct

by no0p

The large MILES template's three starter benchmarks are replaced by all 25 distinct entries of the agreed post-training development and text-safety panel, at full dataset sizes with pinned sampling defaults. It sets evaluation.interval=0 with initial=true and final=true, so the panel runs before and after training only, even on extended runs, and zero now disables periodic evaluation globally o...

Improve MILES configuration defaults, examples, and guidance allenai/open-instruct

by no0p

The four size examples collapse to dev (one-GPU mechanics check), node (one eight-GPU node: two EP2 training GPUs, six inference GPUs), and large (H1's three-node/24-GPU footprint with no idle GPUs). Operators also get written-down defaults: scoring_pass_required is false on main, Core skips the standalone scoring pass when the recipe makes it redundant, and the help text now states what forcin...

mason: an explicit --env replaces mason's default of the same name allenai/open-instruct

by abhishekraok

An explicit --env NAME=VALUE or --secret NAME=SECRET now replaces any env var mason adds by default under the same name. Previously only DEFAULT_ENV_VARS honoured the override, and the WEKA HF_HOME/HF_DATASETS_CACHE/HF_HUB_CACHE/CHECKPOINT_OUTPUT_DIR, multi-node NCCL, PATH, WANDB resume and useful-secret vars were appended after --env, so the job got both.

[vllm, rollout, perf] refactor: stage LoRA buckets in one host block (#8352) verl-project/verl

by aoshen02

verl stages incoming LoRA adapter tensors in a single host block instead of cloning each tensor on device and again in _update_weights before moving them to pinned host memory one at a time; per-expert MoE LoRA made that tens of thousands of small transfers. The PR states it is performance only, with no behavior change, for setups syncing through update_weights_from_ipc with peft_config and bas...

Quick answers

What shipped in Alignment & Post-training on October 24, 2026?
open-instruct's MILES template now runs the full 25-entry post-training and text-safety evaluation panel at training endpoints only, while a rewritten set of env and run defaults changes how existing jobs resolve. In total, 5 commits and 5 pull requests landed.
Who contributed to Alignment & Post-training on October 24, 2026?
3 developers shipped this update, including aoshen02, no0p, and abhishekraok.
What were the notable Alignment & Post-training updates?
Add the post-training evaluation panel to the large MILES template, Improve MILES configuration defaults, examples, and guidance, and mason: an explicit --env replaces mason's default of the same name.