CharlesLi
/

OpenELM-1_1B-DPO-full-max-10-reward

Text Generation

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

OpenELM-1_1B-DPO-full-max-10-reward / runs /Sep16_13-08-11_xe8545-a100-29

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

CharlesLi's picture

Model save

020f91b verified 11 months ago

events.out.tfevents.1726485738.xe8545-a100-29.8975.0

226 kB
LFS

Model save 11 months ago