o Ti[#@sDddlmZmZddlmZmZddlmZeGdddeZdS)) dataclassfield)AnyOptional)TrainingArgumentscs*eZdZUdZejdgZedddidZee d<eddd idZ ee d <ed dd idZ e e e d <edddidZe ee d<edddidZe ee d<ed ddidZe ee d<edddidZee d<edddidZee d<eddgdddZee d <ed!dd"idZe e d#<ed$dd%idZee d&<ed'dd(idZee d)<ed*dd+idZee d,<ed dd-idZe ee d.<ed/d0d/d1gddZee d2<ed3dd4idZe e d5<ed dd6idZe e e d7<ed dd8idZe eee fe d<ed dd9idZ!e ee d:<fd;d<Z"Z#S)= CPOConfiguo Configuration class for the [`CPOTrainer`]. This class includes only the parameters that are specific to CPO 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. For the IPO loss (`loss_type="ipo"`), β is the regularization parameter denoted by τ in the [paper](https://huggingface.co/papers/2310.12036). label_smoothing (`float`, *optional*, defaults to `0.0`): Label smoothing factor. This argument is required if you want to use the default data collator. loss_type (`str`, *optional*, defaults to `"sigmoid"`): Type of loss to use. Possible values are: - `"sigmoid"`: sigmoid loss from the original [DPO](https://huggingface.co/papers/2305.18290) paper. - `"hinge"`: hinge loss on the normalized likelihood from the [SLiC](https://huggingface.co/papers/2305.10425) paper. - `"ipo"`: IPO loss from the [IPO](https://huggingface.co/papers/2310.12036) paper. - `"simpo"`: SimPO loss from the [SimPO](https://huggingface.co/papers/2405.14734) paper. disable_dropout (`bool`, *optional*, defaults to `True`): Whether to disable dropout in the model. cpo_alpha (`float`, *optional*, defaults to `1.0`): Weight of the BC regularizer in CPO training. simpo_gamma (`float`, *optional*, defaults to `0.5`): Target reward margin for the SimPO loss, used only when the `loss_type="simpo"`. 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. generate_during_eval (`bool`, *optional*, defaults to `False`): If `True`, generates and logs completions from the 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. 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. dataset_num_proc (`int` or `None`, *optional*, defaults to `None`): Number of processes to use for processing the dataset. model_init_kwargsgư>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.bf16izCMaximum length of the sequences (prompt + completion) in the batch. max_lengthizMaximum 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_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.betagzLabel smoothing factor.label_smoothingsigmoidzType of loss to use.)rhingeiposimpo)r choices loss_typeTz(Whether to disable dropout in the model.disable_dropoutg?z-Weight of the BC regularizer in CPO training. cpo_alphag?zPTarget reward margin for the SimPO loss, used only when the `loss_type='simpo'`. simpo_gammaizLabel pad token id.label_pad_token_idzLPadding value to use. If `None`, the padding value of the tokenizer is used. padding_valuekeep_endz3Truncation mode to use when the prompt is too long. keep_starttruncation_modeFzRIf `True`, generates and logs completions from the model to W&B during evaluation.generate_during_evalz.Whether the model is an encoder-decoder model.is_encoder_decoderzoKeyword arguments to pass to `AutoModelForCausalLM.from_pretrained` when instantiating the model from a string.z6Number of processes to use for processing the dataset.dataset_num_proccs(|jdur |j n|j|_tdS)N)rfp16super __post_init__)self __class__J/home/ubuntu/.local/lib/python3.10/site-packages/trl/trainer/cpo_config.pyr(szCPOConfig.__post_init__)$__name__ __module__ __qualname____doc__r_VALID_DICT_FIELDSrr float__annotations__rrrboolrintrrrrrstrrrrrrr"r#r$rdictrr%r( __classcell__r,r,r*r-rs  < rN) dataclassesrrtypingrr transformersrrr,r,r,r-s