Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

SFT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Model FingerprintingSFT Positive Samples
Absolute Z-score355.23
30
Supervised Fine-tuningSFT (evaluation)
SFT Evaluation Loss3.13
5
Supervised Fine-tuningSFT (train)
SFT Train Loss2.614
5
Showing 3 of 3 rows