Holarissun
/

SFT_gemma2b_hh-rlhf-helpful_lr5e-06_epoch2-subset-1

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

SFT_gemma2b_hh-rlhf-helpful_lr5e-06_epoch2-subset-1 / runs /Jun17_14-01-18_GPUServer1-GPU4

1 contributor

History: 1 commit

Holarissun's picture

ckpt_sft_rm-SFT_gemma2b_hh-rlhf-helpful_lr5e-06_epoch2-subset-1

7e28db0 verified 5 months ago

events.out.tfevents.1718632882.GPUServer1-GPU4

1.88 MB
LFS

ckpt_sft_rm-SFT_gemma2b_hh-rlhf-helpful_lr5e-06_epoch2-subset-1 5 months ago