diff options
| author | Dylan <boss@tehbox.org> | 2026-11-08 17:32:09 +1300 |
|---|---|---|
| committer | Dylan <boss@tehbox.org> | 2026-11-08 17:32:09 +1300 |
| commit | 312318ad6548f65cc6af118c24811dfd40280b27 (patch) | |
| tree | 0a2bb29cf2f3a6aa83d43ab076d3a0b263bbf6a0 /docs/README.md | |
| parent | 94f3df190a91898eb344b9214a57eb31792bcb1c (diff) | |
| download | tigers-and-sheep-312318ad6548f65cc6af118c24811dfd40280b27.tar.gz tigers-and-sheep-312318ad6548f65cc6af118c24811dfd40280b27.zip | |
feat: Resume training from any weights; balance training by outcome
- train --from <weights> starts from any saved network; without it,
training still carries on from the out dir's newest generation
- Each epoch takes as many positions from sheep-win games as from
tiger-win games (Config::balance_outcomes, on by default)
- Training output shows the error on tiger-win and sheep-win positions
separately, before and after training
- Fix a broken sentence in CLAUDE.md's cache description
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Diffstat (limited to 'docs/README.md')
0 files changed, 0 insertions, 0 deletions