bi3XddlZddlmZmZddlmZmZddlmZeGddeZ y)N) dataclassfield)AnyOptional)TrainingArgumentscjeZdZUdZej dgzZedddiZee d<eddd iZ ee d <ed dd iZ e e e d <edddiZe e d<ed ddiZe eeefe d<ed ddiZe ee d<edddiZee d<ed ddiZe eeefe d<ed ddiZe ee d<ed ddiZe ee d<ed ddiZe ee d<eddd iZe ee d!<ed"dd#iZe e d$<ed%dd&iZee d'<ed"dd(iZe e d)<ed dd*iZe ee d+<ed dd,iZe e e d-<ed dd.iZ e e e d/<ed"dd0iZ!e e d1<ed"dd2iZ"e e d3<ed dd4iZ#e ee d5<fd6Z$xZ%S)7 SFTConfigaC Configuration class for the [`SFTTrainer`]. This class includes only the parameters that are specific to SFT 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: > Parameters that control the model model_init_kwargs (`dict[str, Any]` or `None`, *optional*, defaults to `None`): Keyword arguments for [`~transformers.AutoModelForCausalLM.from_pretrained`], used when the `model` argument of the [`SFTTrainer`] is provided as a string. chat_template_path (`str` or `None`, *optional*, defaults to `None`): If specified, sets the model's chat template. This can either be the path to a tokenizer (local directory or Hugging Face Hub model) or a direct path to a Jinja template file. When using a Jinja file, you must ensure that any special tokens referenced in the template are added to the tokenizer and that the model's embedding layer is resized accordingly. > Parameters that control the data preprocessing dataset_text_field (`str`, *optional*, defaults to `"text"`): Name of the column that contains text data in the dataset. dataset_kwargs (`dict[str, Any]` or `None`, *optional*, defaults to `None`): Dictionary of optional keyword arguments for the dataset preparation. The only supported key is `skip_prepare_dataset`. dataset_num_proc (`int` or `None`, *optional*, defaults to `None`): Number of processes to use for processing the dataset. eos_token (`str` or `None`, *optional*, defaults to `None`): Token used to indicate the end of a turn or sequence. If `None`, it defaults to `processing_class.eos_token`. pad_token (`int` or `None`, *optional*, defaults to `None`): Token used for padding. If `None`, it defaults to `processing_class.pad_token`, or if that is also `None`, it falls back to `processing_class.eos_token`. max_length (`int` or `None`, *optional*, defaults to `1024`): Maximum length of the tokenized sequence. Sequences longer than `max_length` are truncated from the right. If `None`, no truncation is applied. When packing is enabled, this value sets the sequence length. packing (`bool`, *optional*, defaults to `False`): Whether to group multiple sequences into fixed-length blocks to improve computational efficiency and reduce padding. Uses `max_length` to define sequence length. packing_strategy (`str`, *optional*, defaults to `"ffd"`): Strategy for packing sequences. Can be either `"ffd"` (first-fit decreasing, default), or `"wrapped"`. padding_free (`bool`, *optional*, defaults to `False`): Whether to perform forward passes without padding by flattening all sequences in the batch into a single continuous sequence. This reduces memory usage by eliminating padding overhead. Currently, this is only supported with the `flash_attention_2` attention implementation, which can efficiently handle the flattened batch structure. When packing is enabled with strategy `"ffd"`, padding-free is enabled, regardless of the value of this parameter. pad_to_multiple_of (`int` or `None`, *optional*, defaults to `None`): If set, the sequences will be padded to a multiple of this value. eval_packing (`bool` or `None`, *optional*, defaults to `None`): Whether to pack the eval dataset. If `None`, uses the same value as `packing`. > Parameters that control the training completion_only_loss (`bool` or `None`, *optional*, defaults to `None`): Whether to compute loss only on the completion part of the sequence. If set to `True`, loss is computed only on the completion, which is supported only for [prompt-completion](#prompt-completion) datasets. If `False`, loss is computed on the entire sequence. If `None` (default), the behavior depends on the dataset: loss is computed on the completion for [prompt-completion](#prompt-completion) datasets, and on the full sequence for [language modeling](#language-modeling) datasets. assistant_only_loss (`bool`, *optional*, defaults to `False`): Whether to compute loss only on the assistant part of the sequence. If set to `True`, loss is computed only on the assistant responses, which is supported only for [conversational](#conversational) datasets. If `False`, loss is computed on the entire sequence. activation_offloading (`bool`, *optional*, defaults to `False`): Whether to offload the activations to the CPU. model_init_kwargsgh㈵>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_deviceszKeyword arguments for `AutoModelForCausalLM.from_pretrained`, used when the `model` argument of the `SFTTrainer` is provided as a string.acIf specified, sets the model's chat template. This can either be the path to a tokenizer (local directory or Hugging Face Hub model) or a direct path to a Jinja template file. When using a Jinja file, you must ensure that any special tokens referenced in the template are added to the tokenizer and that the model's embedding layer is resized accordingly.chat_template_pathtextz:Name of the column that contains text data in the dataset.dataset_text_fieldzwDictionary of optional keyword arguments for the dataset preparation. The only supported key is `skip_prepare_dataset`.dataset_kwargsz6Number of processes to use for processing the dataset.dataset_num_proczmToken used to indicate the end of a turn or sequence. If `None`, it defaults to `processing_class.eos_token`. eos_tokenzToken used for padding. If `None`, it defaults to `processing_class.pad_token`, or if that is also `None`, it falls back to `processing_class.eos_token`. pad_tokenizMaximum length of the tokenized sequence. Sequences longer than `max_length` are truncated fromthe right. If `None`, no truncation is applied. When packing is enabled, this value sets the sequence length. max_lengthFzWhether to group multiple sequences into fixed-length blocks to improve computational efficiency and reduce padding. Uses `max_length` to define sequence length.packingffdzfStrategy for packing sequences. Can be either `'ffd'` (first-fit decreasing, default), or `'wrapped'`.packing_strategyaWhether to perform forward passes without padding by flattening all sequences in the batch into a single continuous sequence. This reduces memory usage by eliminating padding overhead. Currently, this is only supported with the `flash_attention_2` attention implementation, which can efficiently handle the flattened batch structure. When packing is enabled with strategy `'ffd'`, padding-free is enabled, regardless of the value of this parameter. padding_freezAIf set, the sequences will be padded to a multiple of this value.pad_to_multiple_ofzNWhether to pack the eval dataset. If `None`, uses the same value as `packing`. eval_packingaWhether to compute loss only on the completion part of the sequence. If set to `True`, loss is computed only on the completion, which is supported only for prompt-completion datasets. If `False`, loss is computed on the entire sequence. If `None` (default), the behavior depends on the dataset: loss is computed on the completion for prompt-completion datasets, and on the full sequence for language modeling datasets.completion_only_losszWhether to compute loss only on the assistant part of the sequence. If set to `True`, loss is computed only on the assistant responses, which is supported only for conversational datasets. If `False`, loss is computed on the entire sequence.assistant_only_lossz.Whether to offload the activations to the CPU.activation_offloadingz]This parameter is deprecated and will be removed in version 0.20.0. Use `max_length` instead.max_seq_lengthc|j |j n |j|_t| |j,t j dt|j|_yy)Nz_`max_seq_length` is deprecated and will be removed in version 0.20.0. Use `max_length` instead.) rfp16super __post_init__r$warningswarnDeprecationWarningr)self __class__s Q/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/trl/trainer/sft_config.pyr(zSFTConfig.__post_init__s\'+yy'8Odii      * MMq" #11DO +)&__name__ __module__ __qualname____doc__r_VALID_DICT_FIELDSrrfloat__annotations__rrrboolrr dictstrrrrrrintrrrrrrrr r!r"r#r$r( __classcell__)r-s@r.r r sCGR+==AT@UU!@AM5! D M5! ! D(4.+0 E +!438 8 3xS#X/). G ) $VW05 & 0NHT#s(^,',RS'hsm % D  Ix} % M  Ix}!&  !J  O GT"  c B  L$ ).]^) $)jk$L(4. ,1 .  ,(4. !& ;  ! #(JK#4 %* s %NHSM 2 2r/r ) r) dataclassesrrtypingrr transformersrr r/r.r@s2( * n2!n2 n2r/