NjddlmZddlZddlZddlZddlmZddlm Z ddl m Z ddl m Z ejeZGdde Zy) ) annotationsN) Tokenizer)BaseFinetuneable)StaticLightningModule)_DEFAULT_RANDOM_SEEDc eZdZdZdZdddddddd dd dfd Zd ddd ddddddef ddZxZS)StaticModelForSimilarityval_lossminirNFT) n_layers hidden_dimout_dimpad_id token_mappingweightsfreeze normalizefreeze_weightsc :t |||||||| ||| |  y)z'Initialize a standard similarity model.) vectorsrr tokenizerrrrrrrrN)super__init__) selfrrrrrrrrrrr __class__s k/Users/ahmed/devFolder/Ultron/claude-voice/.venv/lib/python3.12/site-packages/model2vec/train/similarity.pyrz!StaticModelForSimilarity.__init__s8 '!)  gMbP?g?autoc jtj| tjd|j ||| | |\}}|j |t |}|jjd|_ |jt||}|j|||||||| |  |S)aFit a model. This function creates a Lightning Trainer object and fits the model to the data. We use early stopping. After training, the weights of the best model are loaded back into the model. This function seeds everything with a seed of 42, so the results are reproducible. It also splits the data into a train and validation set, again with a random seed. If `X_val` and `y_val` are not provided, the function will automatically split the training data into a train and validation set using `test_size`. :param X: The texts to train on. :param y: The vectors to train on. :param learning_rate: The learning rate. :param batch_size: The batch size. If None, a good batch size is chosen automatically. :param min_epochs: The minimum number of epochs to train for. :param max_epochs: The maximum number of epochs to train for. If this is -1, the model trains until early stopping is triggered. :param early_stopping_patience: The patience for early stopping. If this is None, early stopping is disabled. :param test_size: The test size for the train-test split. :param device: The device to train on. If this is "auto", the device is chosen automatically. :param X_val: The texts to be used for validation. :param y_val: The vectors to be used for validation. :param validation_steps: The number of steps to run validation for. If None, validation steps are estimated from the data. :param random_seed: The random seed to use. Defaults to 42. :return: The fitted model. zRe-initializing model.r ) learning_rate) module train_dataset val_dataset batch_sizeearly_stopping_patience min_epochs max_epochsdevicevalidation_steps) plseed_everythingloggerinfo_create_datasets_determine_batch_sizelentargetsshaper _initializer_train)rXyr$r(r*r+r) test_sizer,X_valy_valr- random_seedr&r'cs rfitzStaticModelForSimilarity.fit2sX ;' ,-%)%:%:1ay%Y" {// C rBrEr ) __name__ __module__ __qualname__ val_metricearly_stopping_directionrrr@ __classcell__)rs@rr r sjJ$*.'+$          ( %      D $!%!%!#./"&%)'+/C C C C  C  CC",CCC C#C%CC "Crr ) __future__rlogging lightningr.torch tokenizersrmodel2vec.train.baser!model2vec.train.lightning_modulesrmodel2vec.train.utilsr getLoggerrJr0r rrrZs>" 1C6   8 $e/er