l^(hbddlmZddlmZmZddlmZddlmZGddejZ y)) annotations)Tensornn) CrossEncoder)fullnamecbeZdZejfdfd ZddZdZeddZ xZ S) MarginMSELossc t|||_||_t j di||_t|jts8t|jjdt|jd|jjdk7r9t|jjd|jjdy)a Computes the MSE loss between ``|sim(Query, Pos) - sim(Query, Neg)|`` and ``|gold_sim(Query, Pos) - gold_sim(Query, Neg)|``. This loss is often used to distill a cross-encoder model from a teacher cross-encoder model or gold labels. In contrast to :class:`~sentence_transformers.cross_encoder.losses.MultipleNegativesRankingLoss`, the two passages do not have to be strictly positive and negative, both can be relevant or not relevant for a given query. This can be an advantage of MarginMSELoss over MultipleNegativesRankingLoss. .. note:: Be mindful of the magnitude of both the labels and what the model produces. If the teacher model produces logits with Sigmoid to bound them to [0, 1], then you may wish to use a Sigmoid activation function in the loss. Args: model (:class:`~sentence_transformers.cross_encoder.CrossEncoder`): A CrossEncoder model to be trained. activation_fn (:class:`~torch.nn.Module`): Activation function applied to the logits before computing the loss. **kwargs: Additional keyword arguments passed to the underlying :class:`torch.nn.MSELoss`. References: - Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation: https://arxiv.org/abs/2010.02666 - `Cross Encoder > Training Examples > Distillation <../../../examples/cross_encoder/training/distillation/README.html>`_ Requirements: 1. Your model must be initialized with `num_labels = 1` (a.k.a. the default) to predict one class. 2. Usually uses a finetuned CrossEncoder teacher M in a knowledge distillation setup. Inputs: +--------------------------------------------+-------------------------------------------------------------+-------------------------------+ | Texts | Labels | Number of Model Output Labels | +============================================+=============================================================+===============================+ | (query, passage_one, passage_two) triplets | gold_sim(query, passage_one) - gold_sim(query, passage_two) | 1 | +--------------------------------------------+-------------------------------------------------------------+-------------------------------+ Relations: - :class:`MSELoss` is similar to this loss, but without a margin through the negative pair. Example: :: from sentence_transformers.cross_encoder import CrossEncoder, CrossEncoderTrainer, losses from datasets import Dataset student_model = CrossEncoder("microsoft/mpnet-base") teacher_model = CrossEncoder("cross-encoder/ms-marco-MiniLM-L12-v2") train_dataset = Dataset.from_dict({ "query": ["What are pandas?", "What is the capital of France?"], "positive": ["Pandas are a kind of bear.", "The capital of France is Paris."], "negative": ["Pandas are a kind of fish.", "The capital of France is Berlin."], }) def compute_labels(batch): positive_scores = teacher_model.predict(list(zip(batch["query"], batch["positive"]))) negative_scores = teacher_model.predict(list(zip(batch["query"], batch["negative"]))) return { "label": positive_scores - negative_scores } train_dataset = train_dataset.map(compute_labels, batched=True) loss = losses.MarginMSELoss(student_model) trainer = CrossEncoderTrainer( model=student_model, train_dataset=train_dataset, loss=loss, ) trainer.train() z? expects a model of type CrossEncoder, but got a model of type .z; expects a model with 1 output label, but got a model with z output labels.N)super__init__model activation_fnrMSELossloss_fct isinstancer ValueError __class____name__type num_labels)selfrrkwargsrs v/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/sentence_transformers/cross_encoder/losses/MarginMSELoss.pyrzMarginMSELoss.__init__ sH  * ,V, $**l3>>**+,++/ +;*>**+,((, (=(='>oO  &ct|dk7rtdt|dtt|d|d}|jj |ddd}|j |jj|jd i|djd }|j|}tt|d|d }|jj |ddd}|j |jj|jd i|djd }|j|}||z }|j||j} | S) NzOMSELoss expects a dataset with three non-label columns, but got a dataset with z columns.rr Tpt)padding truncationreturn_tensorsr ) lenrlistzipr tokenizertodeviceviewrrfloat) rinputslabelspositive_pairstokenspositive_logitsnegative_pairsnegative_logits margin_logitslosss rforwardzMarginMSELoss.forward_si v;! abeflbmannwx c&)VAY78%%  &   $**##$$$**.v.q166r:,,_=c&)VAY78%%  &   $**##$$$**.v.q166r:,,_='/9 }}]FLLN; rc0dt|jiS)Nr)rrrs rget_config_dictzMarginMSELoss.get_config_dicts Xd&8&89  rcy)NuY @misc{hofstätter2021improving, title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation}, author={Sebastian Hofstätter and Sophia Althammer and Michael Schröder and Mete Sertkan and Allan Hanbury}, year={2021}, eprint={2010.02666}, archivePrefix={arXiv}, primaryClass={cs.IR} } r r9s rcitationzMarginMSELoss.citations r)rrrz nn.ModulereturnNone)r.zlist[list[str]]r/rr=r)r=str) r __module__ __qualname__rIdentityrr7r:propertyr< __classcell__)rs@rr r s4GRr{{}Sj@   rr N) __future__rtorchrr0sentence_transformers.cross_encoder.CrossEncoderrsentence_transformers.utilrModuler r rrrJs#"I/FBIIFr