Qwen2.5-1.5B-DPO / trainer_state.json

Commit History

updata beta=0.01 version
01ef97e
verified

AIR-hl commited on

updata beta=0.01 version
a33a253
verified

AIR-hl commited on

new version
ab88ab3
verified

AIR-hl commited on

upload
bbe7579
verified

AIR-hl commited on