Views
No views yet
| 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 | online |
| 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 |
v6-google--gemma-2-2b-delta0.15-epoch2--hypernym-concat-bananas-to-dogs-double-all--d2g--random--alpha1.0--tc-online--full-completion--force-same-x--vallogodds1python scripts/eval.py \
2 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
3 --task hypernym-bananas \
4 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
5 --typicality-correction
6
7python scripts/eval.py \
8 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
9 --task hypernym-bazookas \
10 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
11 --typicality-correction
12
13python scripts/eval.py \
14 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
15 --task hypernym-cabinets \
16 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
17 --typicality-correction
18
19python scripts/eval.py \
20 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
21 --task hypernym-cars \
22 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
23 --typicality-correction
24
25python scripts/eval.py \
26 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
27 --task hypernym-chairs \
28 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
29 --typicality-correction
30
31python scripts/eval.py \
32 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
33 --task hypernym-crows \
34 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
35 --typicality-correction
36
37python scripts/eval.py \
38 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
39 --task hypernym-diapers \
40 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
41 --typicality-correction
42
43python scripts/eval.py \
44 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
45 --task hypernym-dogs \
46 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
47 --typicality-correction
48
49python scripts/eval.py \
50 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
51 --task hypernym-dolls \
52 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
53 --typicality-correction
54
55python scripts/eval.py \
56 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
57 --task hypernym-ducklings \
58 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
59 --typicality-correction
60
61python scripts/eval.py \
62 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
63 --task hypernym-elephants \
64 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
65 --typicality-correction
66
67python scripts/eval.py \
68 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
69 --task hypernym-guns \
70 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
71 --typicality-correction
72
73python scripts/eval.py \
74 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
75 --task hypernym-hammers \
76 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
77 --typicality-correction
78
79python scripts/eval.py \
80 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
81 --task hypernym-helmets \
82 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
83 --typicality-correction
84
85python scripts/eval.py \
86 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
87 --task hypernym-jackets \
88 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
89 --typicality-correction
90
91python scripts/eval.py \
92 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
93 --task hypernym-kayaks \
94 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
95 --typicality-correction
96
97python scripts/eval.py \
98 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
99 --task hypernym-kites \
100 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
101 --typicality-correction
102
103python scripts/eval.py \
104 --model TAUR-dev/rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tco-vlo-fsx \
105 --task hypernym-mirrors \
106 --split_type random --gen-shots zero --disc-shots few --validator-log-odds --save-scores-csv \
107 --typicality-correction