feat(skillopt 0.4.0): background train + harder example dataset (SKILLOPT.easy §8)#419
Merged
Merged
Conversation
…LOPT.easy §8) Implements the two "더 다듬을 거리" from domains/SKILLOPT.easy.md §8. - 🌙 background train — `/skillopt train --bg` detaches via nohup (log under ~/.sidecar/skillopt/train-<ts>.log) and returns immediately; `/skillopt status` shows running-state + score/step progress, `/skillopt log` tails the latest log. - 🎯 harder example — examples/toyqa swapped to 6 format-sensitive QA items (chemical symbols, ISO codes, rounding, past-tense) that an EMPTY skill answers in a full sentence → STRICT exact-match fails → a real learning gradient (the optimizer learns a "reply with only the value" rule, then the held-out gate rises). train_size 6 · batch 3 · sel 5 for stronger signal. Validated: skill.sh `bash -n` ✅ · dataloader/config parse ✅ · status/help smoke ✅ · new dataset loads (6 train / 5 eval). g22 lockstep 0.4.0 + CHANGELOG.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Implements the two "더 다듬을 거리" from domains/SKILLOPT.easy.md §8.
/skillopt train --bgdetaches via nohup (log under~/.sidecar/skillopt/train-.log) and returns immediately;
/skillopt statusshows running-state + score/step progress,
/skillopt logtails the latest log.(chemical symbols, ISO codes, rounding, past-tense) that an EMPTY skill answers
in a full sentence → STRICT exact-match fails → a real learning gradient (the
optimizer learns a "reply with only the value" rule, then the held-out gate
rises). train_size 6 · batch 3 · sel 5 for stronger signal.
Validated: skill.sh
bash -n✅ · dataloader/config parse ✅ · status/help smoke ✅· new dataset loads (6 train / 5 eval). g22 lockstep 0.4.0 + CHANGELOG.