## init siamese lstm
    siamese_lstm = SiameseLSTM(
        batch_size=batch_size,
        output_size=output_size,
        hidden_size=hidden_size,
        vocab_size=vocab_size,
        embedding_size=embedding_size,
        embedding_weights=embedding_weights,
        lstm_layers=lstm_layers,
        device=device,
    )

    ## define optimizer
    optimizer = torch.optim.Adam(params=siamese_lstm.parameters())
   
   ## train model
    train_model(
        model=siamese_lstm,
        optimizer=optimizer,
        dataloader=sick_dataloaders,
        data=sick_data,
        max_epochs=max_epochs,
        config_dict={"device": device, "model_name": "siamese_lstm"},
    )

     ## init siamese lstm
     siamese_lstm_attention = SiameseBiLSTMAttention(
        batch_size=batch_size,
        output_size=output_size,
        hidden_size=hidden_size,
        vocab_size=vocab_size,
        embedding_size=embedding_size,
        embedding_weights=embedding_weights,
        lstm_layers=lstm_layers,
        self_attention_config=self_attention_config,
        fc_hidden_size=fc_hidden_size,
        device=device,
        bidirectional=bidirectional,
    )
    
    ## define optimizer
    optimizer = torch.optim.Adam(params=siamese_lstm_attention.parameters())
   
   ## train model
    train_model(
        model=siamese_lstm_attention,
        optimizer=optimizer,
        dataloader=sick_dataloaders,
        data=sick_data,
        max_epochs=max_epochs,
        config_dict={
            "device": device,
            "model_name": "siamese_lstm_attention",
            "self_attention_config": self_attention_config,
        },
    )

    ## init siamese bilstm with attention
    siamese_transformer = SiameseTransformer(
        batch_size=batch_size,
        vocab_size=vocab_size,
        embedding_size=embedding_size,
        nhead=attention_heads,
        hidden_size=hidden_size,
        transformer_layers=transformer_layers,
        embedding_weights=embedding_weights,
        device=device,
        dropout=dropout,
        max_sequence_len=max_sequence_len,
    )

    ## define optimizer
    optimizer = torch.optim.Adam(params=siamese_transformer.parameters())
   
   ## train model
    train_model(
        model=siamese_transformer,
        optimizer=optimizer,
        dataloader=sick_dataloaders,
        data=sick_data,
        max_epochs=max_epochs,
        config_dict={"device": device, "model_name": "siamese_transformer"},
    )

    from siamese_sts.siamese_net.siamese_bert import BertForSequenceClassification
    ## init siamese bert
    siamese_bert = BertForSequenceClassification.from_pretrained(model_name)

    ## train model
    trainer = transformers.Trainer(
        model=siamese_bert,
        args=transformers.TrainingArguments(
            output_dir="./output",
            overwrite_output_dir=True,
            learning_rate=1e-5,
            do_train=True,
            num_train_epochs=num_epochs,
            # Adjust batch size if this doesn't fit on the Colab GPU
            per_device_train_batch_size=batch_size,
            save_steps=3000,
        ),
        train_dataset=sick_dataloader,
    )
    trainer.train()