← Back to Architecture
logit softcap
ArchitectureUsed in
6 PRs
Best BPB
0.9076
Avg BPB
1.0970
Submissions
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 211 | {"softcap":30} |
| 367 | {"value":30} |
| 828 | {"value":30} |
| 970 | {"degree":5,"cap":30} |
| 1263 | {"softcap":30} |
| 1749 | {"value":30} |