Field	Value
Base model	`google/gemma-2-2b`
Version	v7
Task	`membership-sans-rosch-v0-all`
Epoch	0
Delta	0.19
Typicality correction	neg
Length normalization	False
Preference loss weight	1
NLL validator weight	1
NLL generator weight	1
Validator log-odds	True
Force same-x	True
Semi-supervised ratio	0.1
Labeled-only ratio	None

Reproducibility

Original checkpoint name:

v7-google--gemma-2-2b-delta0.19-epoch0--membership-sans-rosch-v0-all--d2g--random--alpha1.0--tc-neg--full-completion--nllv1.0--nllg1.0--force-same-x--ppd--vallogodds--semi0.1--fix1

To evaluate:

bash

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v7-gemma-2-2b-d0.19-e0-membership-sans-rosch-v0-all-tcn-nv1-ng1-vlo-fsx-ppd-sm0.1-fix1 \
    --task membership-sans-rosch-v0-all \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --neg-typicality