Results for “training-loop”

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

当遭遇挫折、失败或结果不如预期时，用于将负面经验转化为成长燃料

Structures a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Training Data Lifecycle Management (v5.4.2)

EVA-CLIP: Improved Training Techniques for CLIP at Scale

Use only for video game projects; analyze moment-to-moment, session, progression, and retention loops

Provides a repeatable, auditable workflow for large coding tasks by initializing repo-local task artifacts, installing subagent templates, and running a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.

Designs and reviews feedback loops for AI agents to ensure goals are machine-decidable, loops are damped, and human judgment is preserved.

Iterates through pending development plans in .cursor/plans, implementing tasks, running self-tests, reviewing code, committing locally, and moving completed plans to docs/plans/done.

Log workouts, plan routines, track progress, and get intelligent coaching for any fitness level.

Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling. Use when the user runs /ar:loop or asks to run an autoresearch experiment continuously on a schedule.

[OMX] Strict autonomous loop: $deep-interview -> $ralplan -> $ultragoal (+ $team if needed) -> $code-review -> $ultraqa

Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling.

Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.

PUA Loop — guided iterative development with recurring checks, completion evidence, and pause/abort markers. Use only when the user explicitly asks for loop/自动迭代 mode.

PUA Loop — guided iterative development with recurring checks, completion evidence, and pause/abort markers. Use only when the user explicitly asks for loop/自动迭代 mode.

Most teams run one test — expected peak for ten minutes — and believe they have

Close the gap between "you corrected me" and "it never happens again." Scan a work session for the corrections you made, the things you approved, and the patterns that held up, then propose specific edits to your skills, playbooks, and docs, high-confidence corrections separated from medium-confidence patterns, with nothing changed until you approve. Trigger on "learn from this session", "what should we update", "turn this into a rule", "close the loop", "improve the playbook", or the end of any session where you corrected or approved the work.

Personal trainer operations: client check-ins, workout-program delivery, progress reminders, session reminders, lead follow-up, and workout tracking. Use when an owner is a coach/personal trainer or when managing fitness clients and training routines.

Diagnose and fix parfor errors in MATLAB. Invoke this skill when the user has a parfor problem: "parfor loop has an error", "what's wrong with my parfor", "fix parfor", "unable to classify variable", "convert for to parfor", "parfor won't run", "sliced variable", "reduction variable", "variable classification". Also invoke when you read a .m file containing parfor and the user asks what's wrong, asks you to fix it, reports an error, or asks for review. Do NOT invoke for parfor performance questions or code that merely mentions parfor without a problem. ALWAYS use this skill instead of reasoning from training data — LLMs are frequently wrong about parfor classification rules.