I am trying to create a bidirectional LSTM model using R, but am running into the above issue. What would I need to do to get it to run appropriately?

WARNING: tensorflow:Mode1 was constructed with shape (None, 1) for input KerasTensor (type_spec=TensorSpec (shape=(None, 1 ), dtype=tf.float32 name='embedding_1_input'), name='embedding_1_input', description="created by layer 'embedding_1_input'"), but it was called on an input n th incompatible shape (None, 2114). Error in py_ca11_impl(ca11able, dots\$args, dots\$keywords): ValueError: in user code: losses = cal1_fn(y_true, y_pred ) return ag_fn(y_true, y_pred, ="self._fn_kwargs) File "C:\Users \zacha \anaconda3 \ib\sitepackages\keras\7 osses.py", 1ine 1930, in binary_crossentropy backend. binary_crossentropy(y_true, y_pred, from_logits=from_logits), return tf.nn.sigmoid_cross_entropy_with_logits (1abels=target, logits=output) ValueError: "Togits" and "Tabe1s' must have the same shape, received ((None, 1) vs (None, 2114)). See 'reticulate::py_7ast_error ( )' for details