o Ti4@s4ddlmZmZddlmZeGdddeZdS)) dataclassfield)OnlineDPOConfigcsBeZdZUdZeddddidZeeed<fdd Z Z S) NashMDConfiga Configuration class for the [`NashMDTrainer`]. Subclass of [`OnlineDPOConfig`] we can use all its arguments and add the following: Parameters: mixture_coef (`float` or `list[float]`, *optional*, defaults to `0.5`): Logit mixture coefficient for the model and reference model. If a list of floats is provided then the mixture coefficient is selected for each new epoch and the last coefficient is used for the rest of the epochs. cCsdgS)Ng?rrrN/home/ubuntu/.local/lib/python3.10/site-packages/trl/trainer/nash_md_config.py#szNashMDConfig.helpzLogit mixture coefficient for the model and reference model. If a list of floats is provided then the mixture coefficient is selected for each new epoch and the last coefficient is used for the rest of the epochs.)default_factorymetadata mixture_coefcs<tt|jdrt|jdkr|jd|_dSdSdS)N__len__r)super __post_init__hasattrr len)self __class__rrr+s zNashMDConfig.__post_init__) __name__ __module__ __qualname____doc__rr listfloat__annotations__r __classcell__rrrrrs   rN) dataclassesrrtrl.trainer.online_dpo_configrrrrrrs