siddlZddlmZmZddlmZddlmZddl m Z ddl m Z ej eZGdde ZGd d e ZeGd d eZdS) N) dataclassfield)Union)TrainingArguments) ParallelMode) ExplicitEnumceZdZdZdZdZdZdS) BatchSamplersa Stores the acceptable string identifiers for batch samplers. The batch sampler is responsible for determining how samples are grouped into batches during training. Valid options are: - ``BatchSamplers.BATCH_SAMPLER``: The default PyTorch batch sampler. - ``BatchSamplers.NO_DUPLICATES``: Ensures no duplicate samples in a batch. - ``BatchSamplers.GROUP_BY_LABEL``: Ensures each batch has 2+ samples from the same label. batch_sampler no_duplicatesgroup_by_labelN)__name__ __module__ __qualname____doc__ BATCH_SAMPLER NO_DUPLICATESGROUP_BY_LABELV/var/www/icac/venv/lib/python3.11/site-packages/sentence_transformers/training_args.pyr r s)  $M#M%NNNrr ceZdZdZdZdZdS)MultiDatasetBatchSamplersa Stores the acceptable string identifiers for multi-dataset batch samplers. The multi-dataset batch sampler is responsible for determining in what order batches are sampled from multiple datasets during training. Valid options are: - ``MultiDatasetBatchSamplers.ROUND_ROBIN``: Round-robin sampling from each dataset until one is exhausted. With this strategy, it's likely that not all samples from each dataset are used, but each dataset is sampled from equally. - ``MultiDatasetBatchSamplers.PROPORTIONAL``: Sample from each dataset in proportion to its size [default]. With this strategy, all samples from each dataset are used and larger datasets are sampled from more frequently. round_robin proportionalN)rrrr ROUND_ROBIN PROPORTIONALrrrrrs$   K!LLLrrceZdZUdZeejddiZeee fe d<ee j ddiZ ee e fe d<fdZxZS) $SentenceTransformerTrainingArgumentsa SentenceTransformerTrainingArguments extends :class:`~transformers.TrainingArguments` with additional arguments specific to Sentence Transformers. See :class:`~transformers.TrainingArguments` for the complete list of available arguments. Args: output_dir (`str`): The output directory where the model checkpoints will be written. batch_sampler (Union[:class:`~sentence_transformers.training_args.BatchSamplers`, `str`], *optional*): The batch sampler to use. See :class:`~sentence_transformers.training_args.BatchSamplers` for valid options. Defaults to ``BatchSamplers.BATCH_SAMPLER``. multi_dataset_batch_sampler (Union[:class:`~sentence_transformers.training_args.MultiDatasetBatchSamplers`, `str`], *optional*): The multi-dataset batch sampler to use. See :class:`~sentence_transformers.training_args.MultiDatasetBatchSamplers` for valid options. Defaults to ``MultiDatasetBatchSamplers.PROPORTIONAL``. helpzThe batch sampler to use.)defaultmetadatar z'The multi-dataset batch sampler to use.multi_dataset_batch_samplerctt|j|_t |j|_d|_d|_|jtj kr)|j dkrt ddSdS|jtjkr5|js0|j dkrt dd|_dSdSdS)NTFunusedzCurrently using DataParallel (DP) for multi-gpu training, while DistributedDataParallel (DDP) is recommended for faster training. See https://sbert.net/docs/sentence_transformer/training/distributed.html for more information.zWhen using DistributedDataParallel (DDP), it is recommended to set `dataloader_drop_last=True` to avoid hanging issues with an uneven last batch. Setting `dataloader_drop_last=True`.)super __post_init__r r rr#prediction_loss_onlyddp_broadcast_buffers parallel_moderNOT_DISTRIBUTED output_dirloggerwarning DISTRIBUTEDdataloader_drop_last)self __class__s rr'z2SentenceTransformerTrainingArguments.__post_init__Hs *4+=>>+DTEe+f+f(%)!&+"  != = =(**v+*  <#; ; ;DD] ;(**;)-D % % %< ; ; ;r)rrrrrr rr rstr__annotations__rrr#r' __classcell__)r2s@rrr/s 05u+v?Z6[000M5+,JO)6&JsAtJJJ'@#'E!F---------rr)logging dataclassesrrtypingr transformersrTransformersTrainingArgumentstransformers.training_argsrtransformers.utilsr getLoggerrr-r rrrrrr>s((((((((KKKKKK333333++++++  8 $ $&&&&&L&&&"""""" """$ 7-7-7-7-7-+H7-7- 7-7-7-r