Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Fine-tuning on Alpaca
Loading...
1.35
Evaluation Loss
RefLoRA
1.34384
1.38542
1.427
1.46858
May 29, 2026
Evaluation Loss
Updated 2d ago
Evaluation Results
Method
Method
Links
Evaluation Loss
RefLoRA
Backbone=Qwen-2.5-3B,...
2026.05
1.35
BaLoRA
Backbone=Qwen-2.5-3B,...
2026.05
1.35
LoRA
Backbone=Qwen-2.5-3B,...
2026.05
1.352
DoRA
Backbone=Qwen-2.5-3B,...
2026.05
1.352
LoRA-RITE
Backbone=Qwen-2.5-3B,...
2026.05
1.353
OLoRA
Backbone=Qwen-2.5-3B,...
2026.05
1.36
LoRO
Backbone=Qwen-2.5-3B,...
2026.05
1.504
Feedback
Search any
task
Search any
task
