o Ti7@s@ddlmZmZddlmZddlmZeGdddeZdS)) dataclassfield)Optional)TrainingArgumentscs>eZdZUdZedddidZeed<edddidZeed <ed dd idZ e e ed <ed ddidZ e ed<edddidZ e eed<edddidZe eed<ed ddidZe eed<ed ddidZe ed<edddidZeed<edddidZe ed<ed dd idZe eed!<fd"d#ZZS)$ PRMConfiga1 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_stepsNzWhether 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.bf16TzWhether or not to average tokens across devices. If enabled, will use all_reduce to synchronize num_tokens_in_batch for precise loss calculation. Reference: https://github.com/huggingface/transformers/issues/34242 average_tokens_across_devicesizJMaximum 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_proccs(|jdur |j n|j|_tdS)N)r fp16super __post_init__)self __class__J/home/ubuntu/.local/lib/python3.10/site-packages/trl/trainer/prm_config.pyrrszPRMConfig.__post_init__)__name__ __module__ __qualname____doc__rr float__annotations__r r rboolrrintrrrrstrrrr __classcell__rrrrrsf  rN) dataclassesrrtypingr transformersrrrrrrs