hZzy
/

qwen2.5-0.5b-expo-DPO-ES-0.01

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

qwen2.5-0.5b-expo-DPO-ES-0.01 / all_results.json

Commit History

End of training

0fb2aea
verified

hZzy commited on Dec 14, 2024

Model save

020572d
verified

hZzy commited on Dec 14, 2024

End of training

b1acf0c
verified

hZzy commited on Dec 14, 2024

Model save

9f7a057
verified

hZzy commited on Dec 14, 2024