hLSSKJrJr SSKJr SSKJr \"SS\55rg)) dataclassfield)Optional)TrainingArgumentsc^\rSrSr%Sr\"SSS0S9r\\S'\"SSS 0S9r \\S '\"S SS 0S9r \ \S '\"SSS0S9r \ \ \S'\"SSS0S9r\ \\S'\"SSS0S9r\ \\S'\"SSS0S9r\ \\S'\"S SS0S9r\ \S'\"SSS0S9r\\S'\"SSS0S9r\ \S '\"SSS!0S9r\ \\S"'U4S#jrS$rU=r$)% PRMConfiga Configuration class for the [`PRMTrainer`]. This class includes only the parameters that are specific to PRM training. For a full list of training arguments, please refer to the [`~transformers.TrainingArguments`] documentation. Note that default values in this class may differ from those in [`~transformers.TrainingArguments`]. Using [`~transformers.HfArgumentParser`] we can turn this class into [argparse](https://docs.python.org/3/library/argparse#module-argparse) arguments that can be specified on the command line. Parameters: max_length (`int` or `None`, *optional*, defaults to `1024`): Maximum length of the sequences (prompt + completion) used for truncation. max_prompt_length (`int` or `None`, *optional*, defaults to `512`): Maximum length of the prompt used for truncation. max_completion_length (`int` or `None`, *optional*, defaults to `None`): Maximum length of the completion used for truncation. The completion is the concatenation of the steps. disable_dropout (`bool`, *optional*, defaults to `True`): Whether to disable dropout in the model. step_separator (`str`, *optional*, defaults to `"\n"`): Separator used to separate each step of the reasoning process. train_on_last_step_only (`bool`, *optional*, defaults to `False`): Whether to train only on the last step. dataset_num_proc (`int`, *optional*, defaults to `None`): Number of processes to use for processing the dataset. gh㈵>helpz$The initial learning rate for AdamW.)defaultmetadata learning_rate zLog every X updates steps. Should be an integer or a float in range `[0,1)`. If smaller than 1, will be interpreted as ratio of total training steps. logging_stepsTzZIf True, use gradient checkpointing to save memory at the expense of slower backward pass.gradient_checkpointingNzWhether to use bf16 (mixed) precision instead of 32-bit. Requires Ampere or higher NVIDIA architecture or Intel XPU or using CPU (use_cpu) or Ascend NPU. If not set, it defaults to `True` if `fp16` is not set.bf16izJMaximum length of the sequences (prompt + completion) used for truncation. max_lengthiz1Maximum length of the prompt used for truncation.max_prompt_lengthzgMaximum length of the completion used for truncation. The completion is the concatenation of the steps.max_completion_lengthzSeparator used to separate each step of the reasoning process.step_separatorFz'Whether to train only on the last step.train_on_last_step_onlyz6Number of processes to use for processing the dataset.dataset_num_procc>URcUR(+O URUl[TU] 5 g)N)rfp16super __post_init__)self __class__s P/home/james-whalen/.local/lib/python3.13/site-packages/trl/trainer/prm_config.pyrPRMConfig.__post_init__ns*'+yy'8Odii  )r)__name__ __module__ __qualname____firstlineno____doc__rr float__annotations__rrboolrrrintrrrrstrrrr__static_attributes__ __classcell__)rs@r rrs:!@AM5! D M5$) p $D ! ! D(4.!&fg!J (-MN(x},1  ,8C="XYOT Z[NC%*CD%T',RS'hsm   r"rN) dataclassesrrtypingr transformersrrr"r r3s/)* [ ![  [ r"