diff --git a/beginner_source/transformer_tutorial.py b/beginner_source/transformer_tutorial.py
deleted file mode 100644
index 437f6345241..00000000000
--- a/beginner_source/transformer_tutorial.py
+++ /dev/null
@@ -1,384 +0,0 @@
-"""
-Language Modeling with ``nn.Transformer`` and torchtext
-===============================================================
-
-This is a tutorial on training a model to predict the next word in a sequence using the
-`nn.Transformer <https://pytorch.org/docs/stable/generated/torch.nn.Transformer.html>`__ module.
-
-The PyTorch 1.2 release includes a standard transformer module based on the
-paper `Attention is All You Need <https://arxiv.org/pdf/1706.03762.pdf>`__.
-Compared to Recurrent Neural Networks (RNNs), the transformer model has proven
-to be superior in quality for many sequence-to-sequence tasks while being more
-parallelizable. The ``nn.Transformer`` module relies entirely on an attention
-mechanism (implemented as
-`nn.MultiheadAttention <https://pytorch.org/docs/stable/generated/torch.nn.MultiheadAttention.html>`__)
-to draw global dependencies between input and output. The ``nn.Transformer``
-module is highly modularized such that a single component (e.g.,
-`nn.TransformerEncoder <https://pytorch.org/docs/stable/generated/torch.nn.TransformerEncoder.html>`__)
-can be easily adapted/composed.
-
-.. image:: ../_static/img/transformer_architecture.jpg
-
-"""
-
-######################################################################
-# Define the model
-# ----------------
-#
-
-
-######################################################################
-# In this tutorial, we train a ``nn.TransformerEncoder`` model on a
-# causal language modeling task. Please note that this tutorial does not cover
-# the training of `nn.TransformerDecoder <https://pytorch.org/docs/stable/generated/torch.nn.TransformerDecoder.html#torch.nn.TransformerDecoder>`__, as depicted in
-# the right half of the diagram above. The language modeling task is to assign a
-# probability for the likelihood of a given word (or a sequence of words)
-# to follow a sequence of words. A sequence of tokens are passed to the embedding
-# layer first, followed by a positional encoding layer to account for the order
-# of the word (see the next paragraph for more details). The
-# ``nn.TransformerEncoder`` consists of multiple layers of
-# `nn.TransformerEncoderLayer <https://pytorch.org/docs/stable/generated/torch.nn.TransformerEncoderLayer.html>`__.
-# Along with the input sequence, a square attention mask is required because the
-# self-attention layers in ``nn.TransformerDecoder`` are only allowed to attend
-# the earlier positions in the sequence. For the language modeling task, any
-# tokens on the future positions should be masked.  This masking, combined with fact that 
-# the output embeddings are offset with later positions ensures that the
-# predictions for position i can depend only on the known outputs at positions less than i.
-# To produce a probability  distribution over output words, the output of the ``nn.TransformerEncoder``
-# model is passed through a linear layer to output unnormalized logits.
-# The log-softmax function isn't applied here due to the later use of
-# `CrossEntropyLoss <https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html>`__,
-# which requires the inputs to be unnormalized logits.
-#
-
-import math
-import os
-from tempfile import TemporaryDirectory
-from typing import Tuple
-
-import torch
-from torch import nn, Tensor
-from torch.nn import TransformerEncoder, TransformerEncoderLayer
-from torch.utils.data import dataset
-
-class TransformerModel(nn.Module):
-
-    def __init__(self, ntoken: int, d_model: int, nhead: int, d_hid: int,
-                 nlayers: int, dropout: float = 0.5):
-        super().__init__()
-        self.model_type = 'Transformer'
-        self.pos_encoder = PositionalEncoding(d_model, dropout)
-        encoder_layers = TransformerEncoderLayer(d_model, nhead, d_hid, dropout)
-        self.transformer_encoder = TransformerEncoder(encoder_layers, nlayers)
-        self.embedding = nn.Embedding(ntoken, d_model)
-        self.d_model = d_model
-        self.linear = nn.Linear(d_model, ntoken)
-
-        self.init_weights()
-
-    def init_weights(self) -> None:
-        initrange = 0.1
-        self.embedding.weight.data.uniform_(-initrange, initrange)
-        self.linear.bias.data.zero_()
-        self.linear.weight.data.uniform_(-initrange, initrange)
-
-    def forward(self, src: Tensor, src_mask: Tensor = None) -> Tensor:
-        """
-        Arguments:
-            src: Tensor, shape ``[seq_len, batch_size]``
-            src_mask: Tensor, shape ``[seq_len, seq_len]``
-
-        Returns:
-            output Tensor of shape ``[seq_len, batch_size, ntoken]``
-        """
-        src = self.embedding(src) * math.sqrt(self.d_model)
-        src = self.pos_encoder(src)
-        if src_mask is None:
-            """Generate a square causal mask for the sequence. The masked positions are filled with float('-inf').
-            Unmasked positions are filled with float(0.0).
-            """
-            src_mask = nn.Transformer.generate_square_subsequent_mask(len(src)).to(device)
-        output = self.transformer_encoder(src, src_mask)
-        output = self.linear(output)
-        return output
-
-
-######################################################################
-# ``PositionalEncoding`` module injects some information about the
-# relative or absolute position of the tokens in the sequence. The
-# positional encodings have the same dimension as the embeddings so that
-# the two can be summed. Here, we use ``sine`` and ``cosine`` functions of
-# different frequencies.
-#
-
-class PositionalEncoding(nn.Module):
-
-    def __init__(self, d_model: int, dropout: float = 0.1, max_len: int = 5000):
-        super().__init__()
-        self.dropout = nn.Dropout(p=dropout)
-
-        position = torch.arange(max_len).unsqueeze(1)
-        div_term = torch.exp(torch.arange(0, d_model, 2) * (-math.log(10000.0) / d_model))
-        pe = torch.zeros(max_len, 1, d_model)
-        pe[:, 0, 0::2] = torch.sin(position * div_term)
-        pe[:, 0, 1::2] = torch.cos(position * div_term)
-        self.register_buffer('pe', pe)
-
-    def forward(self, x: Tensor) -> Tensor:
-        """
-        Arguments:
-            x: Tensor, shape ``[seq_len, batch_size, embedding_dim]``
-        """
-        x = x + self.pe[:x.size(0)]
-        return self.dropout(x)
-
-
-######################################################################
-# Load and batch data
-# -------------------
-#
-
-
-######################################################################
-# This tutorial uses ``torchtext`` to generate Wikitext-2 dataset.
-# To access torchtext datasets, please install torchdata following instructions at https://github.com/pytorch/data.
-# %%
-#  .. code-block:: bash
-#
-#      %%bash
-#      pip install portalocker
-#      pip install torchdata
-#
-# The vocab object is built based on the train dataset and is used to numericalize
-# tokens into tensors. Wikitext-2 represents rare tokens as `<unk>`.
-#
-# Given a 1-D vector of sequential data, ``batchify()`` arranges the data
-# into ``batch_size`` columns. If the data does not divide evenly into
-# ``batch_size`` columns, then the data is trimmed to fit. For instance, with
-# the alphabet as the data (total length of 26) and ``batch_size=4``, we would
-# divide the alphabet into sequences of length 6, resulting in 4 of such sequences.
-#
-# .. math::
-#   \begin{bmatrix}
-#   \text{A} & \text{B} & \text{C} & \ldots & \text{X} & \text{Y} & \text{Z}
-#   \end{bmatrix}
-#   \Rightarrow
-#   \begin{bmatrix}
-#   \begin{bmatrix}\text{A} \\ \text{B} \\ \text{C} \\ \text{D} \\ \text{E} \\ \text{F}\end{bmatrix} &
-#   \begin{bmatrix}\text{G} \\ \text{H} \\ \text{I} \\ \text{J} \\ \text{K} \\ \text{L}\end{bmatrix} &
-#   \begin{bmatrix}\text{M} \\ \text{N} \\ \text{O} \\ \text{P} \\ \text{Q} \\ \text{R}\end{bmatrix} &
-#   \begin{bmatrix}\text{S} \\ \text{T} \\ \text{U} \\ \text{V} \\ \text{W} \\ \text{X}\end{bmatrix}
-#   \end{bmatrix}
-#
-# Batching enables more parallelizable processing. However, batching means that
-# the model treats each column independently; for example, the dependence of
-# ``G`` and ``F`` can not be learned in the example above.
-#
-
-from torchtext.datasets import WikiText2
-from torchtext.data.utils import get_tokenizer
-from torchtext.vocab import build_vocab_from_iterator
-
-train_iter = WikiText2(split='train')
-tokenizer = get_tokenizer('basic_english')
-vocab = build_vocab_from_iterator(map(tokenizer, train_iter), specials=['<unk>'])
-vocab.set_default_index(vocab['<unk>'])
-
-def data_process(raw_text_iter: dataset.IterableDataset) -> Tensor:
-    """Converts raw text into a flat Tensor."""
-    data = [torch.tensor(vocab(tokenizer(item)), dtype=torch.long) for item in raw_text_iter]
-    return torch.cat(tuple(filter(lambda t: t.numel() > 0, data)))
-
-# ``train_iter`` was "consumed" by the process of building the vocab,
-# so we have to create it again
-train_iter, val_iter, test_iter = WikiText2()
-train_data = data_process(train_iter)
-val_data = data_process(val_iter)
-test_data = data_process(test_iter)
-
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-
-def batchify(data: Tensor, bsz: int) -> Tensor:
-    """Divides the data into ``bsz`` separate sequences, removing extra elements
-    that wouldn't cleanly fit.
-
-    Arguments:
-        data: Tensor, shape ``[N]``
-        bsz: int, batch size
-
-    Returns:
-        Tensor of shape ``[N // bsz, bsz]``
-    """
-    seq_len = data.size(0) // bsz
-    data = data[:seq_len * bsz]
-    data = data.view(bsz, seq_len).t().contiguous()
-    return data.to(device)
-
-batch_size = 20
-eval_batch_size = 10
-train_data = batchify(train_data, batch_size)  # shape ``[seq_len, batch_size]``
-val_data = batchify(val_data, eval_batch_size)
-test_data = batchify(test_data, eval_batch_size)
-
-
-######################################################################
-# Functions to generate input and target sequence
-# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-#
-
-
-######################################################################
-# ``get_batch()`` generates a pair of input-target sequences for
-# the transformer model. It subdivides the source data into chunks of
-# length ``bptt``. For the language modeling task, the model needs the
-# following words as ``Target``. For example, with a ``bptt`` value of 2,
-# we’d get the following two Variables for ``i`` = 0:
-#
-# .. image:: ../_static/img/transformer_input_target.png
-#
-# It should be noted that the chunks are along dimension 0, consistent
-# with the ``S`` dimension in the Transformer model. The batch dimension
-# ``N`` is along dimension 1.
-#
-
-bptt = 35
-def get_batch(source: Tensor, i: int) -> Tuple[Tensor, Tensor]:
-    """
-    Args:
-        source: Tensor, shape ``[full_seq_len, batch_size]``
-        i: int
-
-    Returns:
-        tuple (data, target), where data has shape ``[seq_len, batch_size]`` and
-        target has shape ``[seq_len * batch_size]``
-    """
-    seq_len = min(bptt, len(source) - 1 - i)
-    data = source[i:i+seq_len]
-    target = source[i+1:i+1+seq_len].reshape(-1)
-    return data, target
-
-
-######################################################################
-# Initiate an instance
-# --------------------
-#
-
-
-######################################################################
-# The model hyperparameters are defined below. The ``vocab`` size is
-# equal to the length of the vocab object.
-#
-
-ntokens = len(vocab)  # size of vocabulary
-emsize = 200  # embedding dimension
-d_hid = 200  # dimension of the feedforward network model in ``nn.TransformerEncoder``
-nlayers = 2  # number of ``nn.TransformerEncoderLayer`` in ``nn.TransformerEncoder``
-nhead = 2  # number of heads in ``nn.MultiheadAttention``
-dropout = 0.2  # dropout probability
-model = TransformerModel(ntokens, emsize, nhead, d_hid, nlayers, dropout).to(device)
-
-
-######################################################################
-# Run the model
-# -------------
-#
-
-
-######################################################################
-# We use `CrossEntropyLoss <https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html>`__
-# with the `SGD <https://pytorch.org/docs/stable/generated/torch.optim.SGD.html>`__
-# (stochastic gradient descent) optimizer. The learning rate is initially set to
-# 5.0 and follows a `StepLR <https://pytorch.org/docs/stable/generated/torch.optim.lr_scheduler.StepLR.html>`__
-# schedule. During training, we use `nn.utils.clip_grad_norm\_ <https://pytorch.org/docs/stable/generated/torch.nn.utils.clip_grad_norm_.html>`__
-# to prevent gradients from exploding.
-#
-
-import time
-
-criterion = nn.CrossEntropyLoss()
-lr = 5.0  # learning rate
-optimizer = torch.optim.SGD(model.parameters(), lr=lr)
-scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1.0, gamma=0.95)
-
-def train(model: nn.Module) -> None:
-    model.train()  # turn on train mode
-    total_loss = 0.
-    log_interval = 200
-    start_time = time.time()
-
-    num_batches = len(train_data) // bptt
-    for batch, i in enumerate(range(0, train_data.size(0) - 1, bptt)):
-        data, targets = get_batch(train_data, i)
-        output = model(data)
-        output_flat = output.view(-1, ntokens)
-        loss = criterion(output_flat, targets)
-
-        optimizer.zero_grad()
-        loss.backward()
-        torch.nn.utils.clip_grad_norm_(model.parameters(), 0.5)
-        optimizer.step()
-
-        total_loss += loss.item()
-        if batch % log_interval == 0 and batch > 0:
-            lr = scheduler.get_last_lr()[0]
-            ms_per_batch = (time.time() - start_time) * 1000 / log_interval
-            cur_loss = total_loss / log_interval
-            ppl = math.exp(cur_loss)
-            print(f'| epoch {epoch:3d} | {batch:5d}/{num_batches:5d} batches | '
-                  f'lr {lr:02.2f} | ms/batch {ms_per_batch:5.2f} | '
-                  f'loss {cur_loss:5.2f} | ppl {ppl:8.2f}')
-            total_loss = 0
-            start_time = time.time()
-
-def evaluate(model: nn.Module, eval_data: Tensor) -> float:
-    model.eval()  # turn on evaluation mode
-    total_loss = 0.
-    with torch.no_grad():
-        for i in range(0, eval_data.size(0) - 1, bptt):
-            data, targets = get_batch(eval_data, i)
-            seq_len = data.size(0)
-            output = model(data)
-            output_flat = output.view(-1, ntokens)
-            total_loss += seq_len * criterion(output_flat, targets).item()
-    return total_loss / (len(eval_data) - 1)
-
-######################################################################
-# Loop over epochs. Save the model if the validation loss is the best
-# we've seen so far. Adjust the learning rate after each epoch.
-
-best_val_loss = float('inf')
-epochs = 3
-
-with TemporaryDirectory() as tempdir:
-    best_model_params_path = os.path.join(tempdir, "best_model_params.pt")
-
-    for epoch in range(1, epochs + 1):
-        epoch_start_time = time.time()
-        train(model)
-        val_loss = evaluate(model, val_data)
-        val_ppl = math.exp(val_loss)
-        elapsed = time.time() - epoch_start_time
-        print('-' * 89)
-        print(f'| end of epoch {epoch:3d} | time: {elapsed:5.2f}s | '
-            f'valid loss {val_loss:5.2f} | valid ppl {val_ppl:8.2f}')
-        print('-' * 89)
-
-        if val_loss < best_val_loss:
-            best_val_loss = val_loss
-            torch.save(model.state_dict(), best_model_params_path)
-
-        scheduler.step()
-    model.load_state_dict(torch.load(best_model_params_path)) # load best model states
-
-
-######################################################################
-# Evaluate the best model on the test dataset
-# -------------------------------------------
-#
-
-test_loss = evaluate(model, test_data)
-test_ppl = math.exp(test_loss)
-print('=' * 89)
-print(f'| End of training | test loss {test_loss:5.2f} | '
-      f'test ppl {test_ppl:8.2f}')
-print('=' * 89)
diff --git a/index.rst b/index.rst
index e5f0d1eaaa8..ab98379303b 100644
--- a/index.rst
+++ b/index.rst
@@ -233,13 +233,6 @@ What's new in PyTorch tutorials?
    :link: beginner/bettertransformer_tutorial.html
    :tags: Production,Text
 
-.. customcarditem::
-   :header: Sequence-to-Sequence Modeling with nn.Transformer and torchtext
-   :card_description: Learn how to train a sequence-to-sequence model that uses the nn.Transformer module.
-   :image: _static/img/thumbnails/cropped/Sequence-to-Sequence-Modeling-with-nnTransformer-andTorchText.png
-   :link: beginner/transformer_tutorial.html
-   :tags: Text
-
 .. customcarditem::
    :header: NLP from Scratch: Classifying Names with a Character-level RNN
    :card_description: Build and train a basic character-level RNN to classify word from scratch without the use of torchtext. First in a series of three tutorials.
@@ -745,13 +738,6 @@ What's new in PyTorch tutorials?
    :link: advanced/rpc_ddp_tutorial.html
    :tags: Parallel-and-Distributed-Training
 
-.. customcarditem::
-   :header: Training Transformer models using Pipeline Parallelism
-   :card_description: Walk through a through a simple example of how to train a transformer model using pipeline parallelism.
-   :image: _static/img/thumbnails/cropped/Training-Transformer-models-using-Pipeline-Parallelism.png
-   :link: intermediate/pipeline_tutorial.html
-   :tags: Parallel-and-Distributed-Training
-
 .. customcarditem::
    :header: Training Transformer models using Distributed Data Parallel and Pipeline Parallelism
    :card_description: Walk through a through a simple example of how to train a transformer model using Distributed Data Parallel and Pipeline Parallelism
@@ -964,7 +950,6 @@ Additional Resources
    :hidden:
    :caption: Text
 
-   beginner/transformer_tutorial
    beginner/bettertransformer_tutorial
    intermediate/char_rnn_classification_tutorial
    intermediate/char_rnn_generation_tutorial
@@ -1102,7 +1087,6 @@ Additional Resources
    intermediate/dist_pipeline_parallel_tutorial
    intermediate/rpc_async_execution
    advanced/rpc_ddp_tutorial
-   intermediate/pipeline_tutorial
    advanced/ddp_pipeline
    advanced/generic_join
 
diff --git a/intermediate_source/pipeline_tutorial.py b/intermediate_source/pipeline_tutorial.py
deleted file mode 100644
index 4cebeba63a9..00000000000
--- a/intermediate_source/pipeline_tutorial.py
+++ /dev/null
@@ -1,420 +0,0 @@
-"""
-Training Transformer models using Pipeline Parallelism
-======================================================
-
-**Author**: `Pritam Damania <https://github.com/pritamdamania87>`_
-
-This tutorial demonstrates how to train a large Transformer model across
-multiple GPUs using pipeline parallelism. This tutorial is an extension of the
-`Sequence-to-Sequence Modeling with nn.Transformer and TorchText <https://pytorch.org/tutorials/beginner/transformer_tutorial.html>`__ tutorial
-and scales up the same model to demonstrate how pipeline parallelism can be
-used to train Transformer models.
-
-Prerequisites:
-
-    * `Pipeline Parallelism <https://pytorch.org/docs/stable/pipeline.html>`__
-    * `Sequence-to-Sequence Modeling with nn.Transformer and TorchText <https://pytorch.org/tutorials/beginner/transformer_tutorial.html>`__
-"""
-
-
-######################################################################
-# Define the model
-# ----------------
-#
-
-
-######################################################################
-# In this tutorial, we will split a Transformer model across two GPUs and use
-# pipeline parallelism to train the model. The model is exactly the same model
-# used in the `Sequence-to-Sequence Modeling with nn.Transformer and TorchText
-# <https://pytorch.org/tutorials/beginner/transformer_tutorial.html>`__ tutorial,
-# but is split into two stages. The largest number of parameters belong to the
-# `nn.TransformerEncoder <https://pytorch.org/docs/stable/generated/torch.nn.TransformerEncoder.html>`__ layer.
-# The `nn.TransformerEncoder <https://pytorch.org/docs/stable/generated/torch.nn.TransformerEncoder.html>`__
-# itself consists of ``nlayers`` of `nn.TransformerEncoderLayer <https://pytorch.org/docs/stable/generated/torch.nn.TransformerEncoderLayer.html>`__.
-# As a result, our focus is on ``nn.TransformerEncoder`` and we split the model
-# such that half of the ``nn.TransformerEncoderLayer`` are on one GPU and the
-# other half are on another. To do this, we pull out the ``Encoder`` and
-# ``Decoder`` sections into separate modules and then build an ``nn.Sequential``
-# representing the original Transformer module.
-
-import sys
-import math
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-import tempfile
-from torch.nn import TransformerEncoder, TransformerEncoderLayer
-
-if sys.platform == 'win32':
-    print('Windows platform is not supported for pipeline parallelism')
-    sys.exit(0)
-if torch.cuda.device_count() < 2:
-    print('Need at least two GPU devices for this tutorial')
-    sys.exit(0)
-
-class Encoder(nn.Module):
-    def __init__(self, ntoken, ninp, dropout=0.5):
-        super(Encoder, self).__init__()
-        self.pos_encoder = PositionalEncoding(ninp, dropout)
-        self.encoder = nn.Embedding(ntoken, ninp)
-        self.ninp = ninp
-        self.init_weights()
-
-    def init_weights(self):
-        initrange = 0.1
-        self.encoder.weight.data.uniform_(-initrange, initrange)
-
-    def forward(self, src):
-        # Need (S, N) format for encoder.
-        src = src.t()
-        src = self.encoder(src) * math.sqrt(self.ninp)
-        return self.pos_encoder(src)
-
-class Decoder(nn.Module):
-    def __init__(self, ntoken, ninp):
-        super(Decoder, self).__init__()
-        self.decoder = nn.Linear(ninp, ntoken)
-        self.init_weights()
-
-    def init_weights(self):
-        initrange = 0.1
-        self.decoder.bias.data.zero_()
-        self.decoder.weight.data.uniform_(-initrange, initrange)
-
-    def forward(self, inp):
-        # Need batch dimension first for output of pipeline.
-        return self.decoder(inp).permute(1, 0, 2)
-
-
-######################################################################
-# ``PositionalEncoding`` module injects some information about the
-# relative or absolute position of the tokens in the sequence. The
-# positional encodings have the same dimension as the embeddings so that
-# the two can be summed. Here, we use ``sine`` and ``cosine`` functions of
-# different frequencies.
-
-
-class PositionalEncoding(nn.Module):
-
-    def __init__(self, d_model, dropout=0.1, max_len=5000):
-        super(PositionalEncoding, self).__init__()
-        self.dropout = nn.Dropout(p=dropout)
-
-        pe = torch.zeros(max_len, d_model)
-        position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
-        div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
-        pe[:, 0::2] = torch.sin(position * div_term)
-        pe[:, 1::2] = torch.cos(position * div_term)
-        pe = pe.unsqueeze(0).transpose(0, 1)
-        self.register_buffer('pe', pe)
-
-    def forward(self, x):
-        x = x + self.pe[:x.size(0), :]
-        return self.dropout(x)
-
-
-
-######################################################################
-# Load and batch data
-# -------------------
-#
-
-
-######################################################################
-# The training process uses Wikitext-2 dataset from ``torchtext``. 
-# To access torchtext datasets, please install torchdata following instructions at https://github.com/pytorch/data.
-#
-# The vocab object is built based on the train dataset and is used to numericalize
-# tokens into tensors. Starting from sequential data, the ``batchify()``
-# function arranges the dataset into columns, trimming off any tokens remaining
-# after the data has been divided into batches of size ``batch_size``.
-# For instance, with the alphabet as the sequence (total length of 26)
-# and a batch size of 4, we would divide the alphabet into 4 sequences of
-# length 6:
-#
-# .. math::
-#
-#    \begin{bmatrix}
-#    \text{A} & \text{B} & \text{C} & \ldots & \text{X} & \text{Y} & \text{Z}
-#    \end{bmatrix}
-#    \Rightarrow
-#    \begin{bmatrix}
-#    \begin{bmatrix}\text{A} \\ \text{B} \\ \text{C} \\ \text{D} \\ \text{E} \\ \text{F}\end{bmatrix} &
-#    \begin{bmatrix}\text{G} \\ \text{H} \\ \text{I} \\ \text{J} \\ \text{K} \\ \text{L}\end{bmatrix} &
-#    \begin{bmatrix}\text{M} \\ \text{N} \\ \text{O} \\ \text{P} \\ \text{Q} \\ \text{R}\end{bmatrix} &
-#    \begin{bmatrix}\text{S} \\ \text{T} \\ \text{U} \\ \text{V} \\ \text{W} \\ \text{X}\end{bmatrix}
-#    \end{bmatrix}
-#
-# These columns are treated as independent by the model, which means that
-# the dependence of ``G`` and ``F`` can not be learned, but allows more
-# efficient batch processing.
-#
-
-import torch
-from torchtext.datasets import WikiText2
-from torchtext.data.utils import get_tokenizer
-from torchtext.vocab import build_vocab_from_iterator
-
-train_iter = WikiText2(split='train')
-tokenizer = get_tokenizer('basic_english')
-vocab = build_vocab_from_iterator(map(tokenizer, train_iter), specials=["<unk>"])
-vocab.set_default_index(vocab["<unk>"]) 
-
-def data_process(raw_text_iter):
-  data = [torch.tensor(vocab(tokenizer(item)), dtype=torch.long) for item in raw_text_iter]
-  return torch.cat(tuple(filter(lambda t: t.numel() > 0, data)))
-
-train_iter, val_iter, test_iter = WikiText2()
-train_data = data_process(train_iter)
-val_data = data_process(val_iter)
-test_data = data_process(test_iter)
-
-device = torch.device("cuda")
-
-def batchify(data, bsz):
-    # Divide the dataset into ``bsz`` parts.
-    nbatch = data.size(0) // bsz
-    # Trim off any extra elements that wouldn't cleanly fit (remainders).
-    data = data.narrow(0, 0, nbatch * bsz)
-    # Evenly divide the data across the ``bsz` batches.
-    data = data.view(bsz, -1).t().contiguous()
-    return data.to(device)
-
-batch_size = 20
-eval_batch_size = 10
-train_data = batchify(train_data, batch_size)
-val_data = batchify(val_data, eval_batch_size)
-test_data = batchify(test_data, eval_batch_size)
-
-
-######################################################################
-# Functions to generate input and target sequence
-# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-#
-
-
-######################################################################
-# ``get_batch()`` function generates the input and target sequence for
-# the transformer model. It subdivides the source data into chunks of
-# length ``bptt``. For the language modeling task, the model needs the
-# following words as ``Target``. For example, with a ``bptt`` value of 2,
-# we'd get the following two Variables for ``i`` = 0:
-#
-# .. image:: ../_static/img/transformer_input_target.png
-#
-# It should be noted that the chunks are along dimension 0, consistent
-# with the ``S`` dimension in the Transformer model. The batch dimension
-# ``N`` is along dimension 1.
-#
-
-bptt = 25
-def get_batch(source, i):
-    seq_len = min(bptt, len(source) - 1 - i)
-    data = source[i:i+seq_len]
-    target = source[i+1:i+1+seq_len].view(-1)
-    # Need batch dimension first for pipeline parallelism.
-    return data.t(), target
-
-######################################################################
-# Model scale and Pipe initialization
-# -----------------------------------
-#
-
-
-######################################################################
-# To demonstrate training large Transformer models using pipeline parallelism,
-# we scale up the Transformer layers appropriately. We use an embedding
-# dimension of 4096, hidden size of 4096, 16 attention heads and 12 total
-# transformer layers (``nn.TransformerEncoderLayer``). This creates a model with
-# **~1.4 billion** parameters.
-#
-# We need to initialize the `RPC Framework <https://pytorch.org/docs/stable/rpc.html>`__
-# since Pipe depends on the RPC framework via `RRef <https://pytorch.org/docs/stable/rpc.html#rref>`__
-# which allows for future expansion to cross host pipelining. We need to
-# initialize the RPC framework with only a single worker since we're using a
-# single process to drive multiple GPUs.
-#
-# The pipeline is then initialized with 8 transformer layers on one GPU and 8
-# transformer layers on the other GPU.
-#
-# .. note::
-#    For efficiency purposes we ensure that the ``nn.Sequential`` passed to
-#    ``Pipe`` only consists of two elements (corresponding to two GPUs), this
-#    allows the Pipe to work with only two partitions and avoid any
-#    cross-partition overheads.
-
-ntokens = len(vocab) # the size of vocabulary
-emsize = 4096 # embedding dimension
-nhid = 4096 # the dimension of the feedforward network model in ``nn.TransformerEncoder``
-nlayers = 12 # the number of ``nn.TransformerEncoderLayer`` in ``nn.TransformerEncoder``
-nhead = 16 # the number of heads in the Multihead Attention models
-dropout = 0.2 # the dropout value
-
-from torch.distributed import rpc
-tmpfile = tempfile.NamedTemporaryFile()
-rpc.init_rpc(
-    name="worker",
-    rank=0,
-    world_size=1,
-    rpc_backend_options=rpc.TensorPipeRpcBackendOptions(
-        init_method="file://{}".format(tmpfile.name),
-        # Specifying _transports and _channels is a workaround and we no longer
-        # will have to specify _transports and _channels for PyTorch
-        # versions >= 1.8.1
-        _transports=["ibv", "uv"],
-        _channels=["cuda_ipc", "cuda_basic"],
-    )
-)
-
-num_gpus = 2
-partition_len = ((nlayers - 1) // num_gpus) + 1
-
-# Add encoder in the beginning.
-tmp_list = [Encoder(ntokens, emsize, dropout).cuda(0)]
-module_list = []
-
-# Add all the necessary transformer blocks.
-for i in range(nlayers):
-    transformer_block = TransformerEncoderLayer(emsize, nhead, nhid, dropout)
-    if i != 0 and i % (partition_len) == 0:
-        module_list.append(nn.Sequential(*tmp_list))
-        tmp_list = []
-    device = i // (partition_len)
-    tmp_list.append(transformer_block.to(device))
-
-# Add decoder in the end.
-tmp_list.append(Decoder(ntokens, emsize).cuda(num_gpus - 1))
-module_list.append(nn.Sequential(*tmp_list))
-
-from torch.distributed.pipeline.sync import Pipe
-
-# Build the pipeline.
-chunks = 8
-model = Pipe(torch.nn.Sequential(*module_list), chunks = chunks)
-
-
-def get_total_params(module: torch.nn.Module):
-    total_params = 0
-    for param in module.parameters():
-        total_params += param.numel()
-    return total_params
-
-print ('Total parameters in model: {:,}'.format(get_total_params(model)))
-
-######################################################################
-# Run the model
-# -------------
-#
-
-
-######################################################################
-# `CrossEntropyLoss <https://pytorch.org/docs/master/nn.html?highlight=crossentropyloss#torch.nn.CrossEntropyLoss>`__
-# is applied to track the loss and
-# `SGD <https://pytorch.org/docs/master/optim.html?highlight=sgd#torch.optim.SGD>`__
-# implements stochastic gradient descent method as the optimizer. The initial
-# learning rate is set to 5.0. `StepLR <https://pytorch.org/docs/master/optim.html?highlight=steplr#torch.optim.lr_scheduler.StepLR>`__ is
-# applied to adjust the learn rate through epochs. During the
-# training, we use
-# `nn.utils.clip_grad_norm\_ <https://pytorch.org/docs/master/nn.html?highlight=nn%20utils%20clip_grad_norm#torch.nn.utils.clip_grad_norm_>`__
-# function to scale all the gradient together to prevent exploding.
-#
-
-criterion = nn.CrossEntropyLoss()
-lr = 5.0 # learning rate
-optimizer = torch.optim.SGD(model.parameters(), lr=lr)
-scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1.0, gamma=0.95)
-
-import time
-def train():
-    model.train() # Turn on the train mode
-    total_loss = 0.
-    start_time = time.time()
-    ntokens = len(vocab)
-
-    # Train only for 50 batches to keep script execution time low.
-    nbatches = min(50 * bptt, train_data.size(0) - 1)
-
-    for batch, i in enumerate(range(0, nbatches, bptt)):
-        data, targets = get_batch(train_data, i)
-        optimizer.zero_grad()
-        # Since the Pipe is only within a single host and process the ``RRef``
-        # returned by forward method is local to this node and can simply
-        # retrieved via ``RRef.local_value()``.
-        output = model(data).local_value()
-        # Need to move targets to the device where the output of the
-        # pipeline resides.
-        loss = criterion(output.view(-1, ntokens), targets.cuda(1))
-        loss.backward()
-        torch.nn.utils.clip_grad_norm_(model.parameters(), 0.5)
-        optimizer.step()
-
-        total_loss += loss.item()
-        log_interval = 10
-        if batch % log_interval == 0 and batch > 0:
-            cur_loss = total_loss / log_interval
-            elapsed = time.time() - start_time
-            print('| epoch {:3d} | {:5d}/{:5d} batches | '
-                  'lr {:02.2f} | ms/batch {:5.2f} | '
-                  'loss {:5.2f} | ppl {:8.2f}'.format(
-                    epoch, batch, nbatches // bptt, scheduler.get_lr()[0],
-                    elapsed * 1000 / log_interval,
-                    cur_loss, math.exp(cur_loss)))
-            total_loss = 0
-            start_time = time.time()
-
-def evaluate(eval_model, data_source):
-    eval_model.eval() # Turn on the evaluation mode
-    total_loss = 0.
-    ntokens = len(vocab)
-    # Evaluate only for 50 batches to keep script execution time low.
-    nbatches = min(50 * bptt, data_source.size(0) - 1)
-    with torch.no_grad():
-        for i in range(0, nbatches, bptt):
-            data, targets = get_batch(data_source, i)
-            output = eval_model(data).local_value()
-            output_flat = output.view(-1, ntokens)
-            # Need to move targets to the device where the output of the
-            # pipeline resides.
-            total_loss += len(data) * criterion(output_flat, targets.cuda(1)).item()
-    return total_loss / (len(data_source) - 1)
-
-######################################################################
-# Loop over epochs. Save the model if the validation loss is the best
-# we've seen so far. Adjust the learning rate after each epoch.
-
-best_val_loss = float("inf")
-epochs = 3 # The number of epochs
-best_model = None
-
-for epoch in range(1, epochs + 1):
-    epoch_start_time = time.time()
-    train()
-    val_loss = evaluate(model, val_data)
-    print('-' * 89)
-    print('| end of epoch {:3d} | time: {:5.2f}s | valid loss {:5.2f} | '
-          'valid ppl {:8.2f}'.format(epoch, (time.time() - epoch_start_time),
-                                     val_loss, math.exp(val_loss)))
-    print('-' * 89)
-
-    if val_loss < best_val_loss:
-        best_val_loss = val_loss
-        best_model = model
-
-    scheduler.step()
-
-
-######################################################################
-# Evaluate the model with the test dataset
-# ----------------------------------------
-#
-
-
-######################################################################
-# Apply the best model to check the result with the test dataset.
-
-test_loss = evaluate(best_model, test_data)
-print('=' * 89)
-print('| End of training | test loss {:5.2f} | test ppl {:8.2f}'.format(
-    test_loss, math.exp(test_loss)))
-print('=' * 89)