l^(h-ddlmZddlmZddlmZddlZddlmZmZddl m Z ddl m Z Gdd ejZy) ) annotations)Iterable)AnyN)Tensornn)util)SentenceTransformerc\eZdZdejfdfd ZddZddZed dZ xZ S) CoSENTLossg4@cLt|||_||_||_y)a This class implements CoSENT (Cosine Sentence) loss. It expects that each of the InputExamples consists of a pair of texts and a float valued label, representing the expected similarity score between the pair. It computes the following loss function: ``loss = logsum(1+exp(s(i,j)-s(k,l))+exp...)``, where ``(i,j)`` and ``(k,l)`` are any of the input pairs in the batch such that the expected similarity of ``(i,j)`` is greater than ``(k,l)``. The summation is over all possible pairs of input pairs in the batch that match this condition. Anecdotal experiments show that this loss function produces a more powerful training signal than :class:`CosineSimilarityLoss`, resulting in faster convergence and a final model with superior performance. Consequently, CoSENTLoss may be used as a drop-in replacement for :class:`CosineSimilarityLoss` in any training script. Args: model: SentenceTransformerModel similarity_fct: Function to compute the PAIRWISE similarity between embeddings. Default is ``util.pairwise_cos_sim``. scale: Output of similarity function is multiplied by scale value. Represents the inverse temperature. References: - For further details, see: https://kexue.fm/archives/8847 Requirements: - Sentence pairs with corresponding similarity scores in range of the similarity function. Default is [-1,1]. Inputs: +--------------------------------+------------------------+ | Texts | Labels | +================================+========================+ | (sentence_A, sentence_B) pairs | float similarity score | +--------------------------------+------------------------+ Relations: - :class:`AnglELoss` is CoSENTLoss with ``pairwise_angle_sim`` as the metric, rather than ``pairwise_cos_sim``. - :class:`CosineSimilarityLoss` seems to produce a weaker training signal than CoSENTLoss. In our experiments, CoSENTLoss is recommended. Example: :: from sentence_transformers import SentenceTransformer, SentenceTransformerTrainer, losses from datasets import Dataset model = SentenceTransformer("microsoft/mpnet-base") train_dataset = Dataset.from_dict({ "sentence1": ["It's nice weather outside today.", "He drove to work."], "sentence2": ["It's so sunny.", "She walked to the store."], "score": [1.0, 0.3], }) loss = losses.CoSENTLoss(model) trainer = SentenceTransformerTrainer( model=model, train_dataset=train_dataset, loss=loss, ) trainer.train() N)super__init__modelsimilarity_fctscale)selfrrr __class__s e/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/sentence_transformers/losses/CoSENTLoss.pyrzCoSENTLoss.__init__s'|  , c|Dcgc]}|j|d}}|j|d|d}||jz}|dddf|dddfz }|dddf|dddfk}|j}|d|z dzz }t j t j dj|j|jdfd}t j|d}|Scc}w)Nsentence_embeddingrgmB)dim) rrrfloattorchcatzerostodeviceview logsumexp)rsentence_featureslabelssentence_feature embeddingsscoreslosss rforwardzCoSENTLoss.forwardQsarsM]djj!123GHs s$$Z]JqMB$**$46$'?246$'?21v:--EKKN--fmmr?s,"$ &Ieer