Field	Value
Base model	`google/gemma-2-2b`
Version	v6
Task	`persona-v1-all`
Epoch	1
Delta	0.15
Typicality correction	none
Length normalization	False
Preference loss weight	0
NLL validator weight	1
NLL generator weight	1
Validator log-odds	False
Force same-x	False
Semi-supervised ratio	None
Labeled-only ratio	0.1

Reproducibility

Original checkpoint name:

v6-google--gemma-2-2b-delta0.15-epoch1--persona-v1-all--d2g--random--alpha1.0--full-completion--pref0.0--nllv1.0--nllg1.0--labelonly0.1

To evaluate:

bash

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e1-persona-v1-all-p0-nv1-ng1-lo0.1 \
    --task persona-v1-all \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality