trl/trainer/cpo_config.py [86:130]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    learning_rate: float = field(
        default=1e-6,
        metadata={"help": "The initial learning rate for AdamW."},
    )
    logging_steps: float = field(
        default=10,
        metadata={
            "help": "Log every X updates steps. Should be an integer or a float in range `[0,1)`. If smaller than 1, "
            "will be interpreted as ratio of total training steps."
        },
    )
    bf16: Optional[bool] = field(
        default=None,
        metadata={
            "help": "Whether to use bf16 (mixed) precision instead of 32-bit. Requires Ampere or higher NVIDIA "
            "architecture or Intel XPU or using CPU (use_cpu) or Ascend NPU. If not set, it defaults to `True` if "
            "`fp16` is not set."
        },
    )

    max_length: Optional[int] = field(
        default=1024,
        metadata={"help": "Maximum length of the sequences (prompt + completion) in the batch."},
    )
    max_prompt_length: Optional[int] = field(
        default=512,
        metadata={
            "help": "Maximum length of the prompt. This argument is required if you want to use the default data "
            "collator and your model is an encoder-decoder."
        },
    )
    max_completion_length: Optional[int] = field(
        default=None,
        metadata={
            "help": "Maximum length of the completion. This argument is required if you want to use the default data "
            "collator and your model is an encoder-decoder."
        },
    )
    beta: float = field(
        default=0.1,
        metadata={
            "help": "Parameter controlling the deviation from the reference model. Higher β means less deviation from "
            "the reference model."
        },
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



trl/trainer/kto_config.py [93:137]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    learning_rate: float = field(
        default=1e-6,
        metadata={"help": "The initial learning rate for AdamW."},
    )
    logging_steps: float = field(
        default=10,
        metadata={
            "help": "Log every X updates steps. Should be an integer or a float in range `[0,1)`. If smaller than 1, "
            "will be interpreted as ratio of total training steps."
        },
    )
    bf16: Optional[bool] = field(
        default=None,
        metadata={
            "help": "Whether to use bf16 (mixed) precision instead of 32-bit. Requires Ampere or higher NVIDIA "
            "architecture or Intel XPU or using CPU (use_cpu) or Ascend NPU. If not set, it defaults to `True` if "
            "`fp16` is not set."
        },
    )

    max_length: Optional[int] = field(
        default=1024,
        metadata={"help": "Maximum length of the sequences (prompt + completion) in the batch."},
    )
    max_prompt_length: Optional[int] = field(
        default=512,
        metadata={
            "help": "Maximum length of the prompt. This argument is required if you want to use the default data "
            "collator and your model is an encoder-decoder."
        },
    )
    max_completion_length: Optional[int] = field(
        default=None,
        metadata={
            "help": "Maximum length of the completion. This argument is required if you want to use the default data "
            "collator and your model is an encoder-decoder."
        },
    )
    beta: float = field(
        default=0.1,
        metadata={
            "help": "Parameter controlling the deviation from the reference model. Higher β means less deviation from "
            "the reference model."
        },
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -