Holarissun
/

REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

Generated from Trainer

Model card Files Files and versions Community

REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06 / training_args.bin

Commit History

helpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

3c993a6
verified

Holarissun commited on May 28

helpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

3a3d05e
verified

Holarissun commited on May 24