o Ti@s4ddlmZmZddlmZeGdddeZdS)) dataclassfield)OnlineDPOConfigcsBeZdZUdZeddddidZeeed<fdd Z Z S) XPOConfiga Configuration class for the [`XPOTrainer`]. Subclass of [`OnlineDPOConfig`] we can use all its arguments and add the following: Parameters: alpha (`float` or `list[float]`, *optional*, defaults to `1e-5`): Weight of the XPO loss term. If a list of floats is provided then the alpha is selected for each new epoch and the last alpha is used for the rest of the epochs. cCsdgS)Ngh㈵>rrrJ/home/ubuntu/.local/lib/python3.10/site-packages/trl/trainer/xpo_config.py"szXPOConfig.helpzWeight of the XPO loss term. If a list of floats is provided then the alpha is selected for each new epoch and the last alpha is used for the rest of the epochs.)default_factorymetadataalphacs<tt|jdrt|jdkr|jd|_dSdSdS)N__len__r)super __post_init__hasattrr len)self __class__rrr)s zXPOConfig.__post_init__) __name__ __module__ __qualname____doc__rr listfloat__annotations__r __classcell__rrrrrs  rN) dataclassesrrtrl.trainer.online_dpo_configrrrrrrs