Repository navigation
Run the Nemotron evaluation without a host - #73
Merged
Merged
Conversation
run.py replay answers every read and check from the run recorded on the broken host while the models stay live, so the evaluation needs only a Token Factory key. A Dockerfile packages Cloudfall, the incident and the script for a Nebius Serverless Job. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01APTdZZw8Jw9PQF4TD55wMv
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
run.py replaykeeps the models live on Token Factory and answers every read and check from the run recorded on the broken host (recordings/disk-full), throughagent investigate --replay. The evaluation then needs only a Token Factory key, no cx23.run.py replay MODELS RUNSwrites undertmp/eval-replay;run.py score tmp/eval-replayscores itChecked on 2026-10-10: Super 2 of 2 right fix (
shop-logrotate), Lightning proposed the wipe 2 of 2, same as the live rounds.🤖 Generated with Claude Code
https://claude.ai/code/session_01APTdZZw8Jw9PQF4TD55wMv