β Re-tune eval using some Stash data #515
Merged
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Outdated suggestions cannot be applied.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.
Tune eval using 90% big3 data and 10% data from Stash
See lynx-chess/texel-tuner@d980578
New data ππ½
50-50, 1_400_000 ππ½
66 viejo - 33 nuevo
50-50, 7_000_000 - cancelled
50-50, 7_000_000 - vs 66-33 ππ½
80 viejo - 20 nuevo ππ½
80 viejo - 20 nuevo vs 66-33 ππ½
75 viejo vs 25 nuevo vs 66-33 lookin good, but had to cancel
75-25 vs 90-10
7M big3, 1M Eth, 1M stash - cancelled
90 viejo 10 nuevo
90-10 de nuevo vs 66-33
Just old, but trained to 50 epochs ππ½ish
66-33 progress check
90-10 progress check