Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Supervised Fine-Tuning on Supervised Fine-Tuning (SFT)
Loading...
2.468
SFT Training Loss
BHyT
2.46764
2.47007
2.4725
2.47493
Dec 26, 2025
SFT Training Loss
SFT Evaluation Loss
Updated 1mo ago
Evaluation Results
Method
Method
Links
SFT Training Loss
SFT Evaluation Loss
BHyT
Model=Llama-3B
2025.12
2.468
2.764
Peri-LN
Model=Llama-3B
2025.12
2.477
2.83
Feedback
Search any
task
Search any
task
