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

Reproducibility

Original checkpoint name:

v6-google--gemma-2-2b-delta0.15-epoch2--hypernym-concat-bananas-to-dogs-double-all--d2g--random--alpha1.0--full-completion--force-same-x--vallogodds

To evaluate:

bash

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-bananas \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-bazookas \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-cabinets \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-cars \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-chairs \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-crows \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-diapers \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-dogs \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-dolls \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-ducklings \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-elephants \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-guns \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-hammers \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-helmets \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-jackets \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-kayaks \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-kites \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality

python scripts/eval_by_claude.py \
    --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-vlo-fsx \
    --task hypernym-mirrors \
    --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
    --self-typicality