CharlesLi
/

OpenELM-1_1B-DPO-full-max-4-reward

Text Generation

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

OpenELM-1_1B-DPO-full-max-4-reward / runs /Oct06_14-30-18_xe8545-a100-22

1 contributor

History: 2 commits

CharlesLi's picture

Model save

aeb82f8 verified 3 months ago

events.out.tfevents.1728218423.xe8545-a100-22.2422281.0

231 kB
LFS

Model save 3 months ago
events.out.tfevents.1728231189.xe8545-a100-22.2422281.1

828 Bytes
LFS

Model save 3 months ago