o Ti&@sDddlmZmZddlmZmZddlmZeGdddeZdS)) dataclassfield)AnyOptional)TrainingArgumentscs,eZdZUdZejddgZedddidZee d<ed dd idZ e e e d <ed dd idZ e ee d<edddidZe ee d<ed ddidZe ee d<edddidZee d<edddidZee d<ed ddidZe ee d<edddidZee d<eddd idZe e d!<ed"dd#idZe e d$<ed dd%idZe e e d&<ed"dd'idZe e d(<ed dd)idZe eeefe d<ed dd*idZe eeefe d<ed dd+idZe ee d,<ed dd-idZee d.<ed/dd0idZ ee d1<ed2dd3idZ!ee d4<fd5d6Z"Z#S)7 BCOConfigu Configuration class for the [`BCOTrainer`]. This class includes only the parameters that are specific to BCO 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. This argument is required if you want to use the default data collator. max_prompt_length (`int` or `None`, *optional*, defaults to `512`): Maximum length of the prompt. This argument is required if you want to use the default data collator. max_completion_length (`int` or `None`, *optional*, defaults to `None`): 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`, *optional*, defaults to `0.1`): Parameter controlling the deviation from the reference model. Higher β means less deviation from the reference model. label_pad_token_id (`int`, *optional*, defaults to `-100`): Label pad token id. This argument is required if you want to use the default data collator. padding_value (`int` or `None`, *optional*, defaults to `None`): Padding value to use. If `None`, the padding value of the tokenizer is used. truncation_mode (`str`, *optional*, defaults to `"keep_end"`): Truncation mode to use when the prompt is too long. Possible values are `"keep_end"` or `"keep_start"`. 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 and reference model. generate_during_eval (`bool`, *optional*, defaults to `False`): If `True`, generates and logs completions from both the model and the reference model to W&B or Comet during evaluation. is_encoder_decoder (`bool` or `None`, *optional*, defaults to `None`): When using the `model_init` argument (callable) to instantiate the model instead of the `model` argument, you need to specify if the model returned by the callable is an encoder-decoder model. precompute_ref_log_probs (`bool`, *optional*, defaults to `False`): Whether to precompute reference model log probabilities for training and evaluation datasets. This is useful when training without the reference model to reduce the total GPU memory needed. model_init_kwargs (`dict[str, Any]` or `None`, *optional*, defaults to `None`): Keyword arguments to pass to `AutoModelForCausalLM.from_pretrained` when instantiating the model from a string. ref_model_init_kwargs (`dict[str, Any]` or `None`, *optional*, defaults to `None`): Keyword arguments to pass to `AutoModelForCausalLM.from_pretrained` when instantiating the reference model from a string. dataset_num_proc (`int` or `None`, *optional*, defaults to `None`): Number of processes to use for processing the dataset. prompt_sample_size (`int`, *optional*, defaults to `1024`): Number of prompts that are fed to density ratio classifier. min_density_ratio (`float`, *optional*, defaults to `0.5`): Minimum value of the density ratio. The estimated density ratio is clamped to this value. max_density_ratio (`float`, *optional*, defaults to `10.0`): Maximum value of the density ratio. The estimated density ratio is clamped to this value. model_init_kwargsref_model_init_kwargs 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.bf16izMaximum length of the sequences (prompt + completion) in the batch. This argument is required if you want to use the default data collator. max_lengthizeMaximum length of the prompt. This argument is required if you want to use the default data collator.max_prompt_lengthzMaximum length of the completion. This argument is required if you want to use the default data collator and your model is an encoder-decoder.max_completion_lengthg?uvParameter controlling the deviation from the reference model. Higher β means less deviation from the reference model.betaiz[Label pad token id. This argument is required if you want to use the default data collator.label_pad_token_idzLPadding value to use. If `None`, the padding value of the tokenizer is used. padding_valuekeep_endzTruncation mode to use when the prompt is too long. Possible values are `keep_end` or `keep_start`. This argument is required if you want to use the default data collator.truncation_modeTzs