• Hongxin Liu's avatar
    [chat] refactor trainer (#3648) · 2a951955
    Hongxin Liu authored
    * [chat] ppo trainer remove useless args
    
    * [chat] update examples
    
    * [chat] update benchmark
    
    * [chat] update examples
    
    * [chat] fix sft training with wandb
    
    * [chat] polish docstr
    2a951955
benchmark_opt_lora_dummy.py 7.98 KB