Skip to content

GitLab

Commit 1016e98a authored by zhuww's avatar zhuww
Browse files

megatron-lm0.3.2 based on dtk-22.10

parent 6c3f6c7b
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 1661 additions and 1 deletion
.gitignore 0 → 100644
View file @ 1016e98a
__pycache__
.gitlab-ci.yml 0 → 100644
View file @ 1016e98a
image: gitlab-master.nvidia.com/dl/dgx/pytorch:20.12-py3-devel
test:
script:
- pytest --junitxml=report.xml tests
artifacts:
when: always
reports:
junit: report.xml
\ No newline at end of file
LICENSE 0 → 100644
View file @ 1016e98a
The following applies to all files unless otherwise noted:
# Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
# * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
# * Neither the name of NVIDIA CORPORATION nor the names of its
# contributors may be used to endorse or promote products derived
# from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
--
This repository also contains code from Hugging Face Inc., Google Research,
Facebook (from their Fairseq and Dino projects), Microsoft(from their
Swin-Transformer project)and Philip Popien. Files from these
organizations have notices at the top of each file. Below are
licenses used in those files, as indicated.
------------- LICENSE FOR Facebook, huggingface and Google Research code --------------
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
------------- LICENSE FOR Facebook Fairseq code --------------
MIT License
Copyright (c) Facebook, Inc. and its affiliates.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
------------- LICENSE FOR Mircrosoft Swin transformer code --------------
MIT License
Copyright (c) Microsoft Corporation.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE
--------------- NVIDIA Source Code License for SegFormer -----------------
1. Definitions
“Licensor” means any person or entity that distributes its Work.
“Software” means the original work of authorship made available under this
License.
“Work” means the Software and any additions to or derivative works of the
Software that are made available under this License.
The terms “reproduce,” “reproduction,” “derivative works,” and
“distribution” have the meaning as provided under U.S. copyright law;
provided, however, that for the purposes of this License, derivative works
shall not include works that remain separable from, or merely link
(or bind by name) to the interfaces of, the Work.
Works, including the Software, are “made available” under this License by
including in or with the Work either (a) a copyright notice referencing
the applicability of this License to the Work, or (b) a copy of this License.
2. License Grant
2.1 Copyright Grant. Subject to the terms and conditions of this License,
each Licensor grants to you a perpetual, worldwide, non-exclusive,
royalty-free, copyright license to reproduce, prepare derivative works of,
publicly display, publicly perform, sublicense and distribute its Work
and any resulting derivative works in any form.
3. Limitations
3.1 Redistribution. You may reproduce or distribute the Work only if
(a) you do so under this License, (b) you include a complete copy of this
License with your distribution, and (c) you retain without modification any
copyright, patent, trademark, or attribution notices that are present
in the Work.
3.2 Derivative Works. You may specify that additional or different terms
apply to the use, reproduction, and distribution of your derivative works
of the Work (“Your Terms”) only if (a) Your Terms provide that the use
limitation in Section 3.3 applies to your derivative works, and (b) you
identify the specific derivative works that are subject to Your Terms.
Notwithstanding Your Terms, this License (including the redistribution
requirements in Section 3.1) will continue to apply to the Work itself.
3.3 Use Limitation. The Work and any derivative works thereof only may
be used or intended for use non-commercially. Notwithstanding the
foregoing, NVIDIA and its affiliates may use the Work and any derivative
works commercially. As used herein, “non-commercially” means for research
or evaluation purposes only.
3.4 Patent Claims. If you bring or threaten to bring a patent claim against
any Licensor (including any claim, cross-claim or counterclaim in a lawsuit)
to enforce any patents that you allege are infringed by any Work, then
your rights under this License from such Licensor (including the grant
in Section 2.1) will terminate immediately.
3.5 Trademarks. This License does not grant any rights to use any Licensor’s
or its affiliates’ names, logos, or trademarks, except as necessary to
reproduce the notices described in this License.
3.6 Termination. If you violate any term of this License, then your rights
under this License (including the grant in Section 2.1) will terminate
immediately.
4. Disclaimer of Warranty.
THE WORK IS PROVIDED “AS IS” WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
EITHER EXPRESS OR IMPLIED, INCLUDING WARRANTIES OR CONDITIONS OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE OR NON-INFRINGEMENT.
YOU BEAR THE RISK OF UNDERTAKING ANY ACTIVITIES UNDER THIS LICENSE.
5. Limitation of Liability.
EXCEPT AS PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL
THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE
SHALL ANY LICENSOR BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY DIRECT,
INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT
OF OR RELATED TO THIS LICENSE, THE USE OR INABILITY TO USE THE WORK
(INCLUDING BUT NOT LIMITED TO LOSS OF GOODWILL, BUSINESS INTERRUPTION,
LOST PROFITS OR DATA, COMPUTER FAILURE OR MALFUNCTION, OR ANY OTHER
COMMERCIAL DAMAGES OR LOSSES), EVEN IF THE LICENSOR HAS BEEN
ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
README.md
View file @ 1016e98a
This diff is collapsed.
examples/evaluate_retriever_nq.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
# Evaluate natural question test data given Wikipedia embeddings and pretrained
# ICT model or a finetuned model for Natural Question task
# Datasets can be downloaded from the following link:
# https://github.com/facebookresearch/DPR/blob/master/data/download_data.py
EVIDENCE_DATA_DIR=<Specify path of Wikipedia dataset>
EMBEDDING_PATH=<Specify path of the embeddings>
CHECKPOINT_PATH=<Specify path of pretrained ICT model or finetuned model>
QA_FILE=<Path of the natural question dev or test dataset>
python tasks/main.py \
--task RETRIEVER-EVAL \
--tokenizer-type BertWordPieceLowerCase \
--num-layers 12 \
--hidden-size 768 \
--num-attention-heads 12 \
--tensor-model-parallel-size 1 \
--micro-batch-size 128 \
--activations-checkpoint-method uniform \
--seq-length 512 \
--max-position-embeddings 512 \
--load ${CHECKPOINT_PATH} \
--evidence-data-path ${EVIDENCE_DATA_DIR} \
--embedding-path ${EMBEDDING_PATH} \
--retriever-seq-length 256 \
--vocab-file bert-vocab.txt\
--qa-data-test ${QA_FILE} \
--faiss-use-gpu \
--retriever-report-topk-accuracies 1 5 20 100 \
--fp16 \
--indexer-log-interval 1000 \
--indexer-batch-size 128
examples/evaluate_zeroshot_gpt.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
WORLD_SIZE=8
DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
--nnodes 1 \
--node_rank 0 \
--master_addr localhost \
--master_port 6000"
TASK="LAMBADA"
VALID_DATA=<lambada path>
VOCAB_FILE=gpt2-vocab.json
MERGE_FILE=gpt2-merges.txt
CHECKPOINT=checkpoints/gpt2_345m
python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/main.py \
--task $TASK \
--valid-data $VALID_DATA \
--tokenizer-type GPT2BPETokenizer \
--strict-lambada \
--vocab-file $VOCAB_FILE \
--merge-file $MERGE_FILE \
--load $CHECKPOINT \
--tensor-model-parallel-size 1 \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--batch-size 8 \
--activations-checkpoint-method uniform \
--seq-length 1024 \
--max-position-embeddings 1024 \
--log-interval 10 \
--fp16 \
--no-load-optim \
--no-load-rng
examples/finetune_mnli_distributed.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
WORLD_SIZE=8
DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
--nnodes 1 \
--node_rank 0 \
--master_addr localhost \
--master_port 6000"
TRAIN_DATA="data/glue_data/MNLI/train.tsv"
VALID_DATA="data/glue_data/MNLI/dev_matched.tsv \
data/glue_data/MNLI/dev_mismatched.tsv"
PRETRAINED_CHECKPOINT=checkpoints/bert_345m
VOCAB_FILE=bert-vocab.txt
CHECKPOINT_PATH=checkpoints/bert_345m_mnli
python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/main.py \
--task MNLI \
--seed 1234 \
--train-data $TRAIN_DATA \
--valid-data $VALID_DATA \
--tokenizer-type BertWordPieceLowerCase \
--vocab-file $VOCAB_FILE \
--epochs 5 \
--pretrained-checkpoint $PRETRAINED_CHECKPOINT \
--tensor-model-parallel-size 1 \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--micro-batch-size 8 \
--activations-checkpoint-method uniform \
--lr 5.0e-5 \
--lr-decay-style linear \
--lr-warmup-fraction 0.065 \
--seq-length 512 \
--max-position-embeddings 512 \
--save-interval 500000 \
--save $CHECKPOINT_PATH \
--log-interval 10 \
--eval-interval 100 \
--eval-iters 50 \
--weight-decay 1.0e-1 \
--fp16
examples/finetune_race_distributed.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
WORLD_SIZE=8
DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
--nnodes 1 \
--node_rank 0 \
--master_addr localhost \
--master_port 6000"
TRAIN_DATA="data/RACE/train/middle"
VALID_DATA="data/RACE/dev/middle \
data/RACE/dev/high"
VOCAB_FILE=bert-vocab.txt
PRETRAINED_CHECKPOINT=checkpoints/bert_345m
CHECKPOINT_PATH=checkpoints/bert_345m_race
python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/main.py \
--task RACE \
--seed 1234 \
--train-data $TRAIN_DATA \
--valid-data $VALID_DATA \
--tokenizer-type BertWordPieceLowerCase \
--vocab-file $VOCAB_FILE \
--epochs 3 \
--pretrained-checkpoint $PRETRAINED_CHECKPOINT \
--tensor-model-parallel-size 1 \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--micro-batch-size 4 \
--activations-checkpoint-method uniform \
--lr 1.0e-5 \
--lr-decay-style linear \
--lr-warmup-fraction 0.06 \
--seq-length 512 \
--max-position-embeddings 512 \
--save-interval 100000 \
--save $CHECKPOINT_PATH \
--log-interval 10 \
--eval-interval 100 \
--eval-iters 50 \
--weight-decay 1.0e-1 \
--clip-grad 1.0 \
--hidden-dropout 0.1 \
--attention-dropout 0.1 \
--fp16
examples/finetune_retriever_distributed.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
# Finetune a BERT or pretrained ICT model using Google natural question data
# Datasets can be downloaded from the following link:
# https://github.com/facebookresearch/DPR/blob/master/data/download_data.py
WORLD_SIZE=8
DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
--nnodes 1 \
--node_rank 0 \
--master_addr localhost \
--master_port 6000"
CHECKPOINT_PATH=<Specify path for the finetuned retriever model>
# Load either of the below
BERT_LOAD_PATH=<Path of BERT pretrained model>
PRETRAINED_CHECKPOINT=<Path of Pretrained ICT model>
python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/main.py \
--task RET-FINETUNE-NQ \
--train-with-neg \
--train-hard-neg 1 \
--pretrained-checkpoint ${PRETRAINED_CHECKPOINT} \
--num-layers 12 \
--hidden-size 768 \
--num-attention-heads 12 \
--tensor-model-parallel-size 1 \
--tokenizer-type BertWordPieceLowerCase \
--train-data nq-train.json \
--valid-data nq-dev.json \
--save ${CHECKPOINT_PATH} \
--load ${CHECKPOINT_PATH} \
--vocab-file bert-vocab.txt \
--bert-load ${BERT_LOAD_PATH} \
--save-interval 5000 \
--log-interval 10 \
--eval-interval 20000 \
--eval-iters 100 \
--indexer-log-interval 1000 \
--faiss-use-gpu \
--DDP-impl torch \
--fp16 \
--retriever-report-topk-accuracies 1 5 10 20 100 \
--seq-length 512 \
--retriever-seq-length 256 \
--max-position-embeddings 512 \
--retriever-score-scaling \
--epochs 80 \
--micro-batch-size 8 \
--eval-micro-batch-size 16 \
--indexer-batch-size 128 \
--lr 2e-5 \
--lr-warmup-fraction 0.01 \
--weight-decay 1e-1
examples/merge_mp_bert.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
TENSOR_MODEL_PARALLEL_SIZE=2
VOCAB_FILE=bert-vocab.txt
CHECKPOINT_PATH=checkpoints/bert_345m
WORLD_SIZE=$TENSOR_MODEL_PARALLEL_SIZE python tools/merge_mp_partitions.py \
--model-type BERT \
--tensor-model-parallel-size $TENSOR_MODEL_PARALLEL_SIZE \
--tokenizer-type BertWordPieceLowerCase \
--vocab-file $VOCAB_FILE \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--seq-length 512 \
--max-position-embeddings 512 \
--load $CHECKPOINT_PATH
examples/msdp/README.md 0 → 100644
View file @ 1016e98a
# Multi-Stage Prompting for Knowledgeable Dialogue Generation
This directory contains all the scripts of multi-stage prompting for knowledgeable dialogue generation that includes data preparation, and knowledge and response generations. More details are available on [`knowledgeable task directory`](../../tasks/msdp).
examples/msdp/data_processing.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
# Data preparation for our framework: preprocessing the WoW and WoI datasets
# The datasets can be downloaded through the following links:
# WoW: https://parl.ai/projects/wizard_of_wikipedia/
# WoI: https://parl.ai/projects/sea/
DIR=`pwd`
# Before running the preprocessing, please download
# the wizard of wikipedia and wizard datasets
WOW_DATA_FOLDER=<PATH_OF_WIZARD_OF_WIKIPEDIA_DATA_FOLDER>
WOI_DATA_FOLDER=<PATH_OF_WIZARD_OF_INTERNET_DATA_FOLDER>
# We provide examples for processing the raw data from Wizard of Wikipedia
# Processing the train dataset (train.json)
python ${DIR}/tasks/msdp/preprocessing.py \
--func process_wow_dataset \
--raw_file ${WOW_DATA_FOLDER}/train.json \
--processed_file ${WOW_DATA_FOLDER}/train_processed.txt
# Processing test seen dataset (test_random_split.json)
python ${DIR}/tasks/msdp/preprocessing.py \
--func process_wow_dataset \
--raw_file ${WOW_DATA_FOLDER}/test_random_split.json \
--processed_file ${WOW_DATA_FOLDER}/testseen_processed.txt \
--knwl_ref_file ${WOW_DATA_FOLDER}/output_testseen_knowledge_reference.txt \
--resp_ref_file ${WOW_DATA_FOLDER}/output_testseen_response_reference.txt
# processing test unseen dataset (test_topic_split.json)
python ${DIR}/tasks/msdp/preprocessing.py \
--func process_wow_dataset \
--raw_file ${WOW_DATA_FOLDER}/test_topic_split.json \
--processed_file ${WOW_DATA_FOLDER}/testunseen_processed.txt \
--knwl_ref_file ${WOW_DATA_FOLDER}/output_testunseen_knowledge_reference.txt \
--resp_ref_file ${WOW_DATA_FOLDER}/output_testunseen_response_reference.txt
# We provide the following script to process the raw data from Wizard of Internet
# Processing the test dataset (test.jsonl)
python ${DIR}/tasks/msdp/preprocessing.py \
--func process_woi_dataset \
--raw_file ${WOI_DATA_FOLDER}/test.jsonl \
--processed_file ${WOI_DATA_FOLDER}/test_processed.txt \
--knwl_ref_file ${WOI_DATA_FOLDER}/output_test_knowledge_reference.txt \
--resp_ref_file ${WOI_DATA_FOLDER}/output_test_response_reference.txt
# Get the knowledge generation prompts for the each test dataset in WoW and WoI
MODEL_FILE=<PATH_OF_THE_FINETUNED_DPR_MODEL>
# WoW test seen
python ${DIR}/tasks/msdp/preprocessing.py \
--func get_knwl_gen_prompts \
--test_file ${WOW_DATA_FOLDER}/testseen_processed.txt \
--train_file ${WOW_DATA_FOLDER}/train_processed.txt \
--model_file ${MODEL_FILE} \
--processed_file ${WOW_DATA_FOLDER}/output_testseen_knowledge_prompts.json \
--data_type wow_seen
# WoW test unseen
python ${DIR}/tasks/msdp/preprocessing.py \
--func get_knwl_gen_prompts \
--test_file ${WOW_DATA_FOLDER}/testunseen_processed.txt \
--train_file ${WOW_DATA_FOLDER}/train_processed.txt \
--model_file ${MODEL_FILE} \
--processed_file ${WOW_DATA_FOLDER}/output_testunseen_knowledge_prompts.json \
--data_type wow_unseen
# WoI
python ${DIR}/tasks/msdp/preprocessing.py \
--func get_knwl_gen_prompts \
--test_file ${WOI_DATA_FOLDER}/test_processed.txt \
--train_file ${WOW_DATA_FOLDER}/train_processed.txt \
--model_file ${MODEL_FILE} \
--processed_file ${WOI_DATA_FOLDER}/output_test_knowledge_prompts.json \
--data_type woi
# Get the response generation prompts (can be applied for all the test datasets)
python ${DIR}/tasks/msdp/preprocessing.py \
--func get_resp_gen_prompts \
--train_file ${WOW_DATA_FOLDER}/train_processed.txt \
--processed_file ${WOW_DATA_FOLDER}/output_response_prompts.txt
examples/msdp/eval_knwl_generation.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
#########################
# Evaluate the F1 scores.
#########################
WORLD_SIZE=1
DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
--nnodes 1 \
--node_rank 0 \
--master_addr localhost \
--master_port 6000"
MODEL_GEN_PATH=<PATH_OF_THE_KNOWLEDGE_GENERATION> \
(e.g., /testseen_knowledge_generations.txt)
GROUND_TRUTH_PATH=<PATH_OF_THE_GROUND_TRUTH_KNOWLEDGE> \
(e.g., /testseen_knowledge_reference.txt)
python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/msdp/main.py \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--seq-length 2048 \
--max-position-embeddings 2048 \
--micro-batch-size 4 \
--task MSDP-EVAL-F1 \
--guess-file ${MODEL_GEN_PATH} \
--answer-file ${GROUND_TRUTH_PATH}
############################################
# Evaluate BLEU, METEOR, and ROUGE-L scores.
############################################
# We follow the nlg-eval (https://github.com/Maluuba/nlg-eval) to
# evaluate the BLEU, METEOR, and ROUGE-L scores.
# To evaluate on these metrics, please setup the environments based on
# the nlg-eval github, and run the corresponding evaluation commands.
nlg-eval \
--hypothesis=<PATH_OF_THE_KNOWLEDGE_GENERATION> \
--references=<PATH_OF_THE_GROUND_TRUTH_KNOWLEDGE>
examples/msdp/eval_resp_generation.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
#########################
# Evaluate the F1 scores.
#########################
WORLD_SIZE=1
DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
--nnodes 1 \
--node_rank 0 \
--master_addr localhost \
--master_port 6000"
MODEL_GEN_PATH=<PATH_OF_THE_RESPONSE_GENERATION> \
(e.g., /testseen_response_generations.txt)
GROUND_TRUTH_PATH=<PATH_OF_THE_GROUND_TRUTH_RESPONSE> \
(e.g., /testseen_response_reference.txt)
python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/msdp/main.py \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--seq-length 2048 \
--max-position-embeddings 2048 \
--micro-batch-size 4 \
--task MSDP-EVAL-F1 \
--guess-file ${MODEL_GEN_PATH} \
--answer-file ${GROUND_TRUTH_PATH}
##########################
# Evaluate the KF1 scores.
##########################
MODEL_GEN_PATH=<PATH_OF_THE_RESPONSE_GENERATION> \
(e.g., /testseen_response_generations.txt)
GROUND_TRUTH_PATH=<PATH_OF_THE_GROUND_TRUTH_KNOWLEDGE> \
(e.g., /testseen_knowledge_reference.txt)
python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/msdp/main.py \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--seq-length 2048 \
--max-position-embeddings 2048 \
--micro-batch-size 4 \
--task MSDP-EVAL-F1 \
--guess-file ${MODEL_GEN_PATH} \
--answer-file ${GROUND_TRUTH_PATH}
############################################
# Evaluate BLEU, METEOR, and ROUGE-L scores.
############################################
# We follow the nlg-eval (https://github.com/Maluuba/nlg-eval) to
# evaluate the BLEU, METEOR, and ROUGE-L scores.
# To evaluate on these metrics, please setup the environments based on
# the nlg-eval github, and run the corresponding evaluation commands.
nlg-eval \
--hypothesis=<PATH_OF_THE_RESPONSE_GENERATION> \
--references=<PATH_OF_THE_GROUND_TRUTH_RESPONSE>
examples/msdp/prep_resp_gen.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
# Preparing the input file for the response generation (second-stage prompting)
DIR=`pwd`
TEST_FILE=<PATH_OF_PROCESSED_TEST_DATA> \
(e.g., /testseen_processed.txt)
KNOWLEDGE_FILE=<PATH_OF_GENERATED_KNOWLEDGE_DATA> \
(e.g., /testseen_knowledge_generations.txt)
PROCESSED_FILE=<PATH_OF_INPUT_FILE_FOR_RESPONSE_GENERATION> \
(e.g., /testseen_processed_with_generated_knowledge.txt)
python ${DIR}/tasks/msdp/preprocessing.py \
--func prepare_input \
--test_file ${TEST_FILE} \
--knwl_gen_file ${KNOWLEDGE_FILE} \
--processed_file ${PROCESSED_FILE}
examples/msdp/prompt_knwl_gen.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
# Stage-1: Prompt a pretrained language model to generate the context-relevant knowledge
# The input contains prompts and current dialogue context, the output is the relevant knowledge
# The size of the pretrained language model is 357M
WORLD_SIZE=8
DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
--nnodes 1 \
--node_rank 0 \
--master_addr localhost \
--master_port 6000"
CHECKPOINT_PATH=<PATH_OF_LANGUAGE_MODEL> (e.g., /357m)
VOCAB_PATH=<PATH_OF_VOCAB_FILE> (e.g., /gpt2-vocab.json)
MERGE_PATH=<PATH_OF_MERGE_FILE> (e.g., /gpt2-merges.txt)
INPUT_PATH=<PATH_OF_PROCESSED_TEST_DATA_FILE> \
(e.g., /testseen_processed.txt)
PROMPT_PATH=<PATH_OF_KNOWLEDGE_GENERATION_PROMPTS> \
(e.g., /testseen_knowledge_prompts.json)
OUTPUT_PATH=<PATH_OF_OUTPUT_GENERATION_FILE> \
(e.g., /testseen_knowledge_generations.txt)
python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/msdp/main.py \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--seq-length 2048 \
--max-position-embeddings 2048 \
--micro-batch-size 1 \
--vocab-file ${VOCAB_PATH} \
--merge-file ${MERGE_PATH} \
--load ${CHECKPOINT_PATH} \
--fp16 \
--DDP-impl torch \
--tokenizer-type GPT2BPETokenizer \
--sample-input-file ${INPUT_PATH} \
--sample-output-file ${OUTPUT_PATH} \
--prompt-file ${PROMPT_PATH} \
--prompt-type knowledge \
--num-prompt-examples 10 \
--task MSDP-PROMPT
# NOTE: If you use api for the model generation, please use
# the "--api-prompt" flag (setting this value as True).
examples/msdp/prompt_resp_gen.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
# Stage-2: Prompt a pretrained language model to generate the corresponding response
# The input contains prompts, current dialogue context, and generated knowledge in Stage-1
# The output is the corresponding response.
# The size of the pretrained language model is 357M
WORLD_SIZE=8
DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
--nnodes 1 \
--node_rank 0 \
--master_addr localhost \
--master_port 6000"
CHECKPOINT_PATH=<PATH_OF_LANGUAGE_MODEL> (e.g., /357m)
VOCAB_PATH=<PATH_OF_VOCAB_FILE> (e.g., /gpt2-vocab.json)
MERGE_PATH=<PATH_OF_MERGE_FILE> (e.g., /gpt2-merges.txt)
INPUT_PATH=<PATH_OF_INPUT_TEST_DATA_FILE> (e.g., /testseen_processed.txt)
PROMPT_PATH=<PATH_OF_RESPONSE_GENERATION_PROMPTS> \
(e.g., /response_prompts.txt)
OUTPUT_PATH=<PATH_OF_OUTPUT_GENERATION_FILE> \
(e.g., /output_testseen_response_generations.txt)
python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/msdp/main.py \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--seq-length 2048 \
--max-position-embeddings 2048 \
--micro-batch-size 1 \
--vocab-file ${VOCAB_PATH} \
--merge-file ${MERGE_PATH} \
--load ${CHECKPOINT_PATH} \
--fp16 \
--DDP-impl torch \
--tokenizer-type GPT2BPETokenizer \
--sample-input-file ${INPUT_PATH} \
--sample-output-file ${OUTPUT_PATH} \
--prompt-file ${PROMPT_PATH} \
--prompt-type response \
--num-prompt-examples 20 \
--task MSDP-PROMPT
# NOTE: If you use api for the model generation, please use
# the "--api-prompt" flag (setting this value as True).
examples/pretrain_bert.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
RANK=0
WORLD_SIZE=1
DATA_PATH=<Specify path and file prefix>_text_sentence
CHECKPOINT_PATH=<Specify path>
python pretrain_bert.py \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--micro-batch-size 4 \
--global-batch-size 8 \
--seq-length 512 \
--max-position-embeddings 512 \
--train-iters 2000000 \
--lr-decay-iters 990000 \
--save $CHECKPOINT_PATH \
--load $CHECKPOINT_PATH \
--data-path $DATA_PATH \
--vocab-file bert-vocab.txt \
--data-impl mmap \
--split 949,50,1 \
--lr 0.0001 \
--min-lr 0.00001 \
--lr-decay-style linear \
--lr-warmup-fraction .01 \
--weight-decay 1e-2 \
--clip-grad 1.0 \
--log-interval 100 \
--save-interval 10000 \
--eval-interval 1000 \
--eval-iters 10 \
--fp16
examples/pretrain_bert_distributed.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
GPUS_PER_NODE=8
# Change for multinode config
MASTER_ADDR=localhost
MASTER_PORT=6000
NNODES=1
NODE_RANK=0
WORLD_SIZE=$(($GPUS_PER_NODE*$NNODES))
DATA_PATH=<Specify path and file prefix>_text_sentence
CHECKPOINT_PATH=<Specify path>
DISTRIBUTED_ARGS="--nproc_per_node $GPUS_PER_NODE --nnodes $NNODES --node_rank $NODE_RANK --master_addr $MASTER_ADDR --master_port $MASTER_PORT"
python -m torch.distributed.launch $DISTRIBUTED_ARGS \
pretrain_bert.py \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--micro-batch-size 4 \
--global-batch-size 32 \
--seq-length 512 \
--max-position-embeddings 512 \
--train-iters 1000000 \
--save $CHECKPOINT_PATH \
--load $CHECKPOINT_PATH \
--data-path $DATA_PATH \
--vocab-file bert-vocab.txt \
--data-impl mmap \
--split 949,50,1 \
--distributed-backend nccl \
--lr 0.0001 \
--lr-decay-style linear \
--min-lr 1.0e-5 \
--lr-decay-iters 990000 \
--weight-decay 1e-2 \
--clip-grad 1.0 \
--lr-warmup-fraction .01 \
--log-interval 100 \
--save-interval 10000 \
--eval-interval 1000 \
--eval-iters 10 \
--fp16
examples/pretrain_bert_distributed_with_mp.sh 0 → 100644
View file @ 1016e98a
#!/bin/bash
GPUS_PER_NODE=8
# Change for multinode config
MASTER_ADDR=localhost
MASTER_PORT=6000
NNODES=1
NODE_RANK=0
WORLD_SIZE=$(($GPUS_PER_NODE*$NNODES))
DATA_PATH=<Specify path and file prefix>_text_sentence
VOCAB_FILE=<Specify path to vocab.txt>
CHECKPOINT_PATH=<Specify path>
DISTRIBUTED_ARGS="--nproc_per_node $GPUS_PER_NODE --nnodes $NNODES --node_rank $NODE_RANK --master_addr $MASTER_ADDR --master_port $MASTER_PORT"
python -m torch.distributed.launch $DISTRIBUTED_ARGS \
pretrain_bert.py \
--tensor-model-parallel-size 2 \
--pipeline-model-parallel-size 2 \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--micro-batch-size 2 \
--global-batch-size 16 \
--seq-length 512 \
--max-position-embeddings 512 \
--train-iters 1000000 \
--save $CHECKPOINT_PATH \
--load $CHECKPOINT_PATH \
--data-path $DATA_PATH \
--vocab-file $VOCAB_FILE \
--data-impl mmap \
--split 949,50,1 \
--distributed-backend nccl \
--lr 0.0001 \
--lr-decay-style linear \
--min-lr 1.0e-5 \
--lr-decay-iters 990000 \
--weight-decay 1e-2 \
--clip-grad 1.0 \
--lr-warmup-fraction .01 \
--log-interval 100 \
--save-interval 10000 \
--eval-interval 1000 \
--eval-iters 10 \
--fp16
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment