l^(h8ddlmZddlZddlmZddlmZddlZddlZddl m Z ddlm Z m Z ddl mZejeZGdd e j$Zy) ) annotationsN)Iterable)Callable)version)Tensornn)SentenceTransformerceZdZdddejf dfd Z ddZeddZxZ S) SoftmaxLossTFct |||_||_||_||_||_d}|r|dz }|r|dz }|r|dz }tjd|tj||z||j|_ ||_ tjt j"tjdkrtj%dyy) at This loss was used in our SBERT publication (https://arxiv.org/abs/1908.10084) to train the SentenceTransformer model on NLI data. It adds a softmax classifier on top of the output of two transformer networks. :class:`MultipleNegativesRankingLoss` is an alternative loss function that often yields better results, as per https://arxiv.org/abs/2004.09813. Args: model (SentenceTransformer): The SentenceTransformer model. sentence_embedding_dimension (int): The dimension of the sentence embeddings. num_labels (int): The number of different labels. concatenation_sent_rep (bool): Whether to concatenate vectors u,v for the softmax classifier. Defaults to True. concatenation_sent_difference (bool): Whether to add abs(u-v) for the softmax classifier. Defaults to True. concatenation_sent_multiplication (bool): Whether to add u*v for the softmax classifier. Defaults to False. loss_fct (Callable): Custom pytorch loss function. If not set, uses nn.CrossEntropyLoss(). Defaults to nn.CrossEntropyLoss(). References: - Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks: https://arxiv.org/abs/1908.10084 - `Training Examples > Natural Language Inference <../../../examples/sentence_transformer/training/nli/README.html>`_ Requirements: 1. sentence pairs with a class label Inputs: +---------------------------------------+--------+ | Texts | Labels | +=======================================+========+ | (sentence_A, sentence_B) pairs | class | +---------------------------------------+--------+ Example: :: from sentence_transformers import SentenceTransformer, SentenceTransformerTrainer, losses from datasets import Dataset model = SentenceTransformer("microsoft/mpnet-base") train_dataset = Dataset.from_dict({ "sentence1": [ "A person on a horse jumps over a broken down airplane.", "A person on a horse jumps over a broken down airplane.", "A person on a horse jumps over a broken down airplane.", "Children smiling and waving at camera", ], "sentence2": [ "A person is training his horse for a competition.", "A person is at a diner, ordering an omelette.", "A person is outdoors, on a horse.", "There are children present.", ], "label": [1, 2, 0, 0], }) loss = losses.SoftmaxLoss(model, model.get_sentence_embedding_dimension(), num_labels=3) trainer = SentenceTransformerTrainer( model=model, train_dataset=train_dataset, loss=loss, ) trainer.train() rz%Softmax loss: #Vectors concatenated: )devicez4.43.0zSoftmaxLoss requires transformers >= 4.43.0 to work correctly. Otherwise, the classifier layer that maps embeddings to the labels cannot be updated. Consider updating transformers with `pip install transformers>=4.43.0`.N)super__init__model num_labelsconcatenation_sent_repconcatenation_sent_difference!concatenation_sent_multiplicationloggerinforLinearr classifierloss_fctrparse transformers __version__warning) selfrsentence_embedding_dimensionrrrrrnum_vectors_concatenated __class__s f/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/sentence_transformers/losses/SoftmaxLoss.pyrzSoftmaxLoss.__init__sN  $&<#-J*1R.#$ ! $ ) $ ( $ ) $ , $ ) $ ;zTensor | tuple[Tensor, Tensor])r>str) __name__ __module__ __qualname__rCrossEntropyLossrr8propertyr; __classcell__)r#s@r$r r s (,.2270R002`"`'*` ` !% ` (, `,0`` `D !< FL ' 6  r%r ) __future__rloggingcollections.abcrtypingrr*r packagingrrr)sentence_transformers.SentenceTransformerr getLoggerrArModuler r:r%r$rOsD"$ I   8 $J"))Jr%