o Ti@s@ddlmZmZddlmZddlmZeGdddeZdS)) dataclassfield)Optional)TrainingArgumentscseZdZUdZedddidZeed<edddidZe e ed <ed dd idZ e ed <ed ddidZ e e ed<ed ddidZe ed<edddidZe e ed<edddidZe eed<edddidZe ed<fddZZS) RewardConfiga? Configuration class for the [`RewardTrainer`]. This class includes only the parameters that are specific to Reward 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) in the batch, filters out entries that exceed the limit. This argument is required if you want to use the default data collator. disable_dropout (`bool`, *optional*, defaults to `True`): Whether to disable dropout in the model. dataset_num_proc (`int`, *optional*, defaults to `None`): Number of processes to use for processing the dataset. center_rewards_coefficient (`float`, *optional*, defaults to `None`): Coefficient to incentivize the reward model to output mean-zero rewards (proposed by https://huggingface.co/papers/2312.09244, Eq. 2). Recommended value: `0.01`. remove_unused_columns (`bool`, *optional*, defaults to `False`): Whether to remove the columns that are not used by the model's forward pass. Can be `True` only if the dataset is pretokenized. helpzLog 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.)defaultmetadata 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_devicesizMaximum length of the sequences (prompt + completion) in the batch, filters out entries that exceed the limit. This argument is required if you want to use the default data collator. max_lengthzs