Skip to content

GitLab

Commit 230156c4 authored by yangzhong's avatar yangzhong
Browse files

bert-large training

parents
Pipeline #3006 failed with stages
in 0 seconds
Expand all Show whitespace changes
Inline Side-by-side
Showing with 828 additions and 0 deletions
2node-run-pre/2nodes_single_process_pre1.sh 0 → 100644
View file @ 230156c4
#!/bin/bash
export MIOPEN_DEBUG_DISABLE_FIND_DB=1
export NCCL_SOCKET_IFNAME=eno1
export HSA_USERPTR_FOR_PAGED_MEM=0
export HIP_LAUNCH_BLOCKING=1
lrank=$OMPI_COMM_WORLD_LOCAL_RANK
comm_rank=$OMPI_COMM_WORLD_RANK
comm_size=$OMPI_COMM_WORLD_SIZE
export PATH_PHRASE1=/public/DL_DATA/wikicorpus_en/lower_case_1_seq_len_128_max_pred_20_masked_lm_prob_0.15_random_seed_12345_dupe_factor_5_shard_1472_test_split_10/wikicorpus_en/training
APP="python3 ${HOME}/torch/bert-pretrain/run_pretraining_v4.py \
--input_dir=${PATH_PHRASE1} \
--output_dir=${HOME}/outdir/torch/pre_wiki/phrase1 \
--config_file=${HOME}/model/uncased_L-24_H-1024_A-16/bert_config.json \
--bert_model=bert-large-uncased \
--train_batch_size=16 \
--max_seq_length=128 \
--max_predictions_per_seq=20 \
--max_steps=100000 \
--warmup_proportion=0.0 \
--num_steps_per_checkpoint=20000 \
--learning_rate=4.0e-4 \
--seed=12439 \
--gradient_accumulation_steps=1 \
--allreduce_post_accumulation \
--gpus_per_node ${2} \
--do_train \
--local_rank ${comm_rank} \
--world_size ${comm_size} \
--dist_url tcp://${1}:34567 \
--json-summary ${HOME}/outdir/torch/pre_wiki/phrase1/dllogger.json
"
case ${lrank} in
[0])
export HIP_VISIBLE_DEVICES=0
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[1])
export HIP_VISIBLE_DEVICES=1
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[2])
export HIP_VISIBLE_DEVICES=2
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[3])
export HIP_VISIBLE_DEVICES=3
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[4])
export HIP_VISIBLE_DEVICES=4
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
[5])
export HIP_VISIBLE_DEVICES=5
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
[6])
export HIP_VISIBLE_DEVICES=6
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
[7])
export HIP_VISIBLE_DEVICES=7
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
esac
2node-run-pre/2nodes_single_process_pre2.sh 0 → 100644
View file @ 230156c4
#!/bin/bash
export MIOPEN_DEBUG_DISABLE_FIND_DB=1
export NCCL_SOCKET_IFNAME=eno1
export HSA_USERPTR_FOR_PAGED_MEM=0
export HIP_LAUNCH_BLOCKING=1
lrank=$OMPI_COMM_WORLD_LOCAL_RANK
comm_rank=$OMPI_COMM_WORLD_RANK
comm_size=$OMPI_COMM_WORLD_SIZE
export PATH_PHRASE2=/public/DL_DATA/wikicorpus_en/lower_case_1_seq_len_512_max_pred_80_masked_lm_prob_0.15_random_seed_12345_dupe_factor_5_shard_1472_test_split_10/wikicorpus_en/training
APP="python3 ${HOME}/torch/bert-pretrain/run_pretraining_v4.py \
--input_dir=${PATH_PHRASE2} \
--output_dir=${HOME}/outdir/torch/pre_wiki/phrase2 \
--config_file=${HOME}/model/uncased_L-24_H-1024_A-16/bert_config.json \
--bert_model=bert-large-uncased \
--train_batch_size=2 \
--max_seq_length=512 \
--max_predictions_per_seq=80 \
--max_steps=400000 \
--warmup_proportion=0.128 \
--num_steps_per_checkpoint=20000 \
--learning_rate=4.0e-3 \
--seed=12439 \
--gradient_accumulation_steps=1 \
--allreduce_post_accumulation \
--gpus_per_node ${2} \
--do_train \
--phase2 \
--phase1_end_step=0 \
--local_rank ${comm_rank} \
--world_size ${comm_size} \
--dist_url tcp://${1}:34567 \
--json-summary ${HOME}/outdir/torch/pre_wiki4/phrase2/dllogger.json
"
case ${lrank} in
[0])
export HIP_VISIBLE_DEVICES=0
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[1])
export HIP_VISIBLE_DEVICES=1
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[2])
export HIP_VISIBLE_DEVICES=2
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[3])
export HIP_VISIBLE_DEVICES=3
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[4])
export HIP_VISIBLE_DEVICES=4
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
[5])
export HIP_VISIBLE_DEVICES=5
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
[6])
export HIP_VISIBLE_DEVICES=6
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
[7])
export HIP_VISIBLE_DEVICES=7
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
esac
2node-run-pre/env.sh 0 → 100644
View file @ 230156c4
source $ROCM_PATH/env.sh
\ No newline at end of file
2node-run-pre/hostfile 0 → 100644
View file @ 230156c4
j20r4n01 slots=8
j20r4n02 slots=8
2node-run-pre/run_bert_pre1_4dcus.sh 0 → 100644
View file @ 230156c4
#!/usr/bin/env bash
HOME_PATH=/work/home/hepj
WORK_PATH=${HOME_PATH}/bert-pytorch/2node-run-pre
which python3
source env.sh
hostfile=./hostfile
node=$(cat $hostfile|sort|uniq |wc -l)
np=$(($node*8))
nodename=$(cat $hostfile |sed -n "1p")
dist_url=`echo $nodename | awk '{print $1}'`
mpirun -np ${np} --hostfile hostfile-$SLURM_JOB_ID --bind-to none --mca btl_tcp_if_include $dist_url ${WORK_PATH}/2nodes_single_process_pre1.sh $dist_url $node
2node-run-pre/run_bert_pre2_4dcus.sh 0 → 100644
View file @ 230156c4
#!/usr/bin/env bash
HOME_PATH=/work/home/hepj
WORK_PATH=${HOME_PATH}/bert-pytorch/2node-run-pre
which python3
source env.sh
hostfile=./hostfile
node=$(cat $hostfile|sort|uniq |wc -l)
np=$(($node*8))
nodename=$(cat $hostfile |sed -n "1p")
dist_url=`echo $nodename | awk '{print $1}'`
mpirun -np ${np} --hostfile hostfile-$SLURM_JOB_ID --bind-to none --mca btl_tcp_if_include $dist_url ${WORK_PATH}/2nodes_single_process_pre2.sh $dist_url $node
2node-run-squad/2nodes_single_process.sh 0 → 100644
View file @ 230156c4
#!/bin/bash
export MIOPEN_DEBUG_DISABLE_FIND_DB=1
export HSA_USERPTR_FOR_PAGED_MEM=0
lrank=$OMPI_COMM_WORLD_LOCAL_RANK
comm_rank=$OMPI_COMM_WORLD_RANK
comm_size=$OMPI_COMM_WORLD_SIZE
APP="python3 /work/home/hepj/torch/bert-squad/run_squad_v4.py \
--train_file ${HOME}/data/sq1.1/train-v1.1.json \
--predict_file ${HOME}/data/sq1.1/dev-v1.1.json \
--init_checkpoint ${HOME}/model/pytorch_bert/model.ckpt-28252.pt \
--vocab_file ${HOME}/model/pytorch_bert/vocab.txt \
--output_dir ${HOME}/outdir/torch/SQUAD4 \
--config_file ${HOME}/model/pytorch_bert/bert_config.json \
--json-summary ${HOME}/outdir/torch/SQUAD4/results.json \
--bert_model bert-large-uncased \
--do_train \
--do_predict \
--train_batch_size 4 \
--predict_batch_size 4 \
--gpus_per_node 2 \
--local_rank ${comm_rank} \
--world_size ${comm_size} \
--use_env \
--dist_url tcp://${1}:34567 \
"
case ${lrank} in
[0])
export HIP_VISIBLE_DEVICES=0
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[1])
export HIP_VISIBLE_DEVICES=1
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[2])
export HIP_VISIBLE_DEVICES=2
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[3])
export HIP_VISIBLE_DEVICES=3
echo numactl --cpunodebind=0 --membind=0 ${APP}
numactl --cpunodebind=0 --membind=0 ${APP}
;;
[4])
export HIP_VISIBLE_DEVICES=4
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
[5])
export HIP_VISIBLE_DEVICES=5
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
[6])
export HIP_VISIBLE_DEVICES=6
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
[7])
export HIP_VISIBLE_DEVICES=7
echo numactl --cpunodebind=3 --membind=3 ${APP}
numactl --cpunodebind=3 --membind=3 ${APP}
;;
esac
2node-run-squad/env.sh 0 → 100644
View file @ 230156c4
source $ROCM_PATH/env.sh
\ No newline at end of file
2node-run-squad/hostfile 0 → 100644
View file @ 230156c4
j20r4n01 slots=8
j20r4n02 slots=8
2node-run-squad/run_bert_squad_4dcus.sh 0 → 100644
View file @ 230156c4
#!/usr/bin/env bash
HOME_PATH=/public/home/hepj
WORK_PATH=${HOME_PATH}/bert-pytorch/2node-run-squad
which python3
source env.sh
hostfile=./hostfile
np=$(cat $hostfile|sort|uniq |wc -l)
np=$(($np*8))
nodename=$(cat $hostfile |sed -n "1p")
dist_url=`echo $nodename | awk '{print $1}'`
mpirun -np ${np} --hostfile hostfile-$SLURM_JOB_ID --bind-to none --mca btl_tcp_if_include $dist_url ${WORK_PATH}/2nodes_single_process.sh $dist_url
2node-run-squad/slurm-37908748.out 0 → 100644
View file @ 230156c4
+ HOME_PATH=/public/home/hepj
+ WORK_PATH=/public/home/hepj/torch/BERT/2node-run-squad
+ source /public/home/hepj/env22.10.sh
/opt/gridview/slurm/spool_slurmd/job37908748/slurm_script: line 13: /public/home/hepj/env22.10.sh: No such file or directory
+ which python3
/public/home/hepj/job_env/dtk22.10-torch-1.10-py3.7/bin/python3
+ hostfile=./37908748
+ scontrol show hostnames 'j20r4n[01-02]'
++ cat ./37908748
+ for i in '`cat $hostfile`'
+ echo j20r4n01 slots=4
++ pwd
+ (( num_node=+1 ))
+ for i in '`cat $hostfile`'
+ echo j20r4n02 slots=4
++ pwd
+ (( num_node=1+1 ))
+ num_dcu=8
+ echo 8
8
++ cat ./37908748
++ sed -n 1p
+ nodename=j20r4n01
+ echo j20r4n01
j20r4n01
++ echo j20r4n01
++ awk '{print $1}'
+ dist_url=j20r4n01
+ export HSA_USERPTR_FOR_PAGED_MEM=0
+ HSA_USERPTR_FOR_PAGED_MEM=0
+ mpirun -np 8 --hostfile hostfile-37908748 /public/home/hepj/torch/BERT/2node-run-squad/2nodes_single_process.sh j20r4n01
NCCL_SOCKET_IFNAME=eno1 numactl --cpunodebind=0 --membind=0 python3 /work/home/hepj/torch/bert-squad/run_squad_v4.py --train_file /public/home/hepj/data/sq1.1/train-v1.1.json --predict_file /public/home/hepj/data/sq1.1/dev-v1.1.json --init_checkpoint /public/home/hepj/model/pytorch_bert/model.ckpt-28252.pt --vocab_file /public/home/hepj/model/pytorch_bert/vocab.txt --output_dir /public/home/hepj/outdir/torch/SQUAD4 --config_file /public/home/hepj/model/pytorch_bert/bert_config.json --json-summary /public/home/hepj/outdir/torch/SQUAD4/results.json --bert_model bert-large-uncased --do_train --do_predict --train_batch_size 4 --predict_batch_size 4 --gpus_per_node 2 --local_rank 0 --world_size 8 --use_env --dist_url tcp://j20r4n01:34567
NCCL_SOCKET_IFNAME=eno1 numactl --cpunodebind=1 --membind=1 python3 /work/home/hepj/torch/bert-squad/run_squad_v4.py --train_file /public/home/hepj/data/sq1.1/train-v1.1.json --predict_file /public/home/hepj/data/sq1.1/dev-v1.1.json --init_checkpoint /public/home/hepj/model/pytorch_bert/model.ckpt-28252.pt --vocab_file /public/home/hepj/model/pytorch_bert/vocab.txt --output_dir /public/home/hepj/outdir/torch/SQUAD4 --config_file /public/home/hepj/model/pytorch_bert/bert_config.json --json-summary /public/home/hepj/outdir/torch/SQUAD4/results.json --bert_model bert-large-uncased --do_train --do_predict --train_batch_size 4 --predict_batch_size 4 --gpus_per_node 2 --local_rank 1 --world_size 8 --use_env --dist_url tcp://j20r4n01:34567
NCCL_SOCKET_IFNAME=eno1 numactl --cpunodebind=2 --membind=2 python3 /work/home/hepj/torch/bert-squad/run_squad_v4.py --train_file /public/home/hepj/data/sq1.1/train-v1.1.json --predict_file /public/home/hepj/data/sq1.1/dev-v1.1.json --init_checkpoint /public/home/hepj/model/pytorch_bert/model.ckpt-28252.pt --vocab_file /public/home/hepj/model/pytorch_bert/vocab.txt --output_dir /public/home/hepj/outdir/torch/SQUAD4 --config_file /public/home/hepj/model/pytorch_bert/bert_config.json --json-summary /public/home/hepj/outdir/torch/SQUAD4/results.json --bert_model bert-large-uncased --do_train --do_predict --train_batch_size 4 --predict_batch_size 4 --gpus_per_node 2 --local_rank 2 --world_size 8 --use_env --dist_url tcp://j20r4n01:34567
NCCL_SOCKET_IFNAME=eno1 numactl --cpunodebind=3 --membind=3 python3 /work/home/hepj/torch/bert-squad/run_squad_v4.py --train_file /public/home/hepj/data/sq1.1/train-v1.1.json --predict_file /public/home/hepj/data/sq1.1/dev-v1.1.json --init_checkpoint /public/home/hepj/model/pytorch_bert/model.ckpt-28252.pt --vocab_file /public/home/hepj/model/pytorch_bert/vocab.txt --output_dir /public/home/hepj/outdir/torch/SQUAD4 --config_file /public/home/hepj/model/pytorch_bert/bert_config.json --json-summary /public/home/hepj/outdir/torch/SQUAD4/results.json --bert_model bert-large-uncased --do_train --do_predict --train_batch_size 4 --predict_batch_size 4 --gpus_per_node 2 --local_rank 3 --world_size 8 --use_env --dist_url tcp://j20r4n01:34567
NCCL_SOCKET_IFNAME=eno1 numactl --cpunodebind=0 --membind=0 python3 /work/home/hepj/torch/bert-squad/run_squad_v4.py --train_file /public/home/hepj/data/sq1.1/train-v1.1.json --predict_file /public/home/hepj/data/sq1.1/dev-v1.1.json --init_checkpoint /public/home/hepj/model/pytorch_bert/model.ckpt-28252.pt --vocab_file /public/home/hepj/model/pytorch_bert/vocab.txt --output_dir /public/home/hepj/outdir/torch/SQUAD4 --config_file /public/home/hepj/model/pytorch_bert/bert_config.json --json-summary /public/home/hepj/outdir/torch/SQUAD4/results.json --bert_model bert-large-uncased --do_train --do_predict --train_batch_size 4 --predict_batch_size 4 --gpus_per_node 2 --local_rank 4 --world_size 8 --use_env --dist_url tcp://j20r4n01:34567
NCCL_SOCKET_IFNAME=eno1 numactl --cpunodebind=1 --membind=1 python3 /work/home/hepj/torch/bert-squad/run_squad_v4.py --train_file /public/home/hepj/data/sq1.1/train-v1.1.json --predict_file /public/home/hepj/data/sq1.1/dev-v1.1.json --init_checkpoint /public/home/hepj/model/pytorch_bert/model.ckpt-28252.pt --vocab_file /public/home/hepj/model/pytorch_bert/vocab.txt --output_dir /public/home/hepj/outdir/torch/SQUAD4 --config_file /public/home/hepj/model/pytorch_bert/bert_config.json --json-summary /public/home/hepj/outdir/torch/SQUAD4/results.json --bert_model bert-large-uncased --do_train --do_predict --train_batch_size 4 --predict_batch_size 4 --gpus_per_node 2 --local_rank 5 --world_size 8 --use_env --dist_url tcp://j20r4n01:34567
NCCL_SOCKET_IFNAME=eno1 numactl --cpunodebind=2 --membind=2 python3 /work/home/hepj/torch/bert-squad/run_squad_v4.py --train_file /public/home/hepj/data/sq1.1/train-v1.1.json --predict_file /public/home/hepj/data/sq1.1/dev-v1.1.json --init_checkpoint /public/home/hepj/model/pytorch_bert/model.ckpt-28252.pt --vocab_file /public/home/hepj/model/pytorch_bert/vocab.txt --output_dir /public/home/hepj/outdir/torch/SQUAD4 --config_file /public/home/hepj/model/pytorch_bert/bert_config.json --json-summary /public/home/hepj/outdir/torch/SQUAD4/results.json --bert_model bert-large-uncased --do_train --do_predict --train_batch_size 4 --predict_batch_size 4 --gpus_per_node 2 --local_rank 6 --world_size 8 --use_env --dist_url tcp://j20r4n01:34567
NCCL_SOCKET_IFNAME=eno1 numactl --cpunodebind=3 --membind=3 python3 /work/home/hepj/torch/bert-squad/run_squad_v4.py --train_file /public/home/hepj/data/sq1.1/train-v1.1.json --predict_file /public/home/hepj/data/sq1.1/dev-v1.1.json --init_checkpoint /public/home/hepj/model/pytorch_bert/model.ckpt-28252.pt --vocab_file /public/home/hepj/model/pytorch_bert/vocab.txt --output_dir /public/home/hepj/outdir/torch/SQUAD4 --config_file /public/home/hepj/model/pytorch_bert/bert_config.json --json-summary /public/home/hepj/outdir/torch/SQUAD4/results.json --bert_model bert-large-uncased --do_train --do_predict --train_batch_size 4 --predict_batch_size 4 --gpus_per_node 2 --local_rank 7 --world_size 8 --use_env --dist_url tcp://j20r4n01:34567
(null): can't open file '/work/home/hepj/torch/bert-squad/run_squad_v4.py': [Errno 2] No such file or directory
(null): can't open file '/work/home/hepj/torch/bert-squad/run_squad_v4.py': [Errno 2] No such file or directory
(null): can't open file '/work/home/hepj/torch/bert-squad/run_squad_v4.py': [Errno 2] No such file or directory
(null): can't open file '/work/home/hepj/torch/bert-squad/run_squad_v4.py': [Errno 2] No such file or directory
(null): can't open file '/work/home/hepj/torch/bert-squad/run_squad_v4.py': [Errno 2] No such file or directory
(null): can't open file '/work/home/hepj/torch/bert-squad/run_squad_v4.py': [Errno 2] No such file or directory
(null): can't open file '/work/home/hepj/torch/bert-squad/run_squad_v4.py': [Errno 2] No such file or directory
(null): can't open file '/work/home/hepj/torch/bert-squad/run_squad_v4.py': [Errno 2] No such file or directory
--------------------------------------------------------------------------
Primary job terminated normally, but 1 process returned
a non-zero exit code. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:
Process name: [[60184,1],5]
Exit code: 2
--------------------------------------------------------------------------
Dockerfile 0 → 100644
View file @ 230156c4
FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
COPY requirements.txt requirements.txt
RUN source /opt/dtk-24.04.1/env.sh
RUN cp /usr/share/zoneinfo/Asia/Shanghai /etc/localtime && echo 'Asia/Shanghai' >/etc/timezone
ENV LANG C.UTF-8
RUN pip install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
LICENSE 0 → 100644
View file @ 230156c4
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
Copyright 2019 NVIDIA CORPORATION. All rights reserved.
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.
\ No newline at end of file
NOTICE 0 → 100644
View file @ 230156c4
BERT PyTorch
This repository includes software from https://github.com/huggingface/pytorch-pretrained-BERT
licensed under the Apache License 2.0.
README.md 0 → 100644
View file @ 230156c4
# bert-large 训练
## 论文
`BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding`
[BERT论文pdf地址](https://arxiv.org/pdf/1810.04805.pdf)
## 环境配置
### Docker
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.4.1-ubuntu22.04-dtk25.04.1-py3.10
```
其它依赖库参照requirements.txt安装：
```
pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/
```
## 数据集
pre_train 数据，本项目使用的是wiki20220401的数据，但数据集压缩后近20GB，解压后300GB下载速度慢，解压占大量空间。由于wiki数据集经常更新,官网并不保留旧版数据集，这里提供处理好的seq128和seq512的数据集网盘下载链接。
（seq128对应PHRASE1）链接：https://pan.baidu.com/s/13GA-Jmfr2qXrChjiM2UfFQ?pwd=l30u 提取码：l30u
（seq512对应PHRASE2）链接：https://pan.baidu.com/s/1MBFjYNsGQzlnc8aEb7Pg4w?pwd=6ap2 提取码：6ap2
**这里使用服务器已有的wiki数据集服务器上有已经下载处理好的数据，预训练数据分为PHRASE1、PHRASE2**
`wiki数据集结构`
```
──wikicorpus_en_128
│   ├── training
│    ├── wikicorpus_en_training_0.tfrecord.hdf5
│    ├── wikicorpus_en_training_1000.tfrecord.hdf5
│ └── ...
│   └── test
│    ├── wikicorpus_en_test_99.tfrecord.hdf5
│    ├── wikicorpus_en_test_9.tfrecord.hdf5
│ └── ...
──wikicorpus_en_512
│   ├── training
│    ├── wikicorpus_en_training_0.tfrecord.hdf5
│    ├── wikicorpus_en_training_1000.tfrecord.hdf5
│ └── ...
│   └── test
│    ├── wikicorpus_en_test_99.tfrecord.hdf5
│    ├── wikicorpus_en_test_9.tfrecord.hdf5
│ └── ...
```
问答SQUAD1.1数据：
[train-v1.1](https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v1.1.json)
[dev-v1.1](https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v1.1.json)
`squadv1.1数据结构`
```
├── dev-v1.1.json
└── train-v1.1.json
```
## 训练
#### 1.参数说明
```
--input_dir 输入数据文件夹
--output_dir 输出保存文件夹
--config_file 模型配置文件
--bert_model bert模型类型可选： bert-base-uncased, bert-large-uncased, bert-base-cased, bert-large-cased, bert-base-multilingual-uncased,bert-base-multilingual-cased, bert-base-chinese
--train_batch_size 训练batch_size
--max_seq_length=128 最大长度（需要和训练数据相匹配）
--max_predictions_per_seq 输入序列中屏蔽标记的最大总数
--max_steps 最大步长
--warmup_proportion 进行线性学习率热身的训练比例
--num_steps_per_checkpoint 多少步保存一次模型
--learning_rate 学习率
--seed 随机种子
--gradient_accumulation_steps 在执行向后/更新过程之前，Accumulte的更新步骤数
--allreduce_post_accumulation 是否在梯度累积步骤期间执行所有减少
--do_train 是否训练
--fp16 混合精度训练
--amp 混合精度训练
--json-summary 输出json文件
```
#### 2.PHRASE1
```
#多卡
bash bert_pre1_4.sh #单精度 （按自己路径对single_pre1_4.sh里APP设置进行修改）
bash bert_pre1_4_fp16.sh #半精度 （按自己路径对single_pre1_4_fp16.sh里APP设置进行修改）
```
#### 3.PHRASE2
```
#多卡
bash bert_pre2_4.sh #单精度 （按自己路径对single_pre2_4.sh里APP设置进行修改）
bash bert_pre2_4_fp16.sh #半精度 （按自己路径对single_pre2_4_fp16.sh里APP设置进行修改）
```
README_ORIGIN.md 0 → 100644
View file @ 230156c4
This diff is collapsed.
README_old.md 0 → 100644
View file @ 230156c4
# 简介
使用PyTorch框架计算Bert网络。
* BERT 的训练分为pre-train和fine-tune两种，pre-train训练分为两个phrase。
* BERT 的推理可基于不同数据集进行精度验证
* 数据生成、模型转换相关细节见 [README.md](http://10.0.100.3/dcutoolkit/deeplearing/dlexamples/-/blob/develop/PyTorch/NLP/BERT/scripts/README.md)
# 运行示例
目前提供基于wiki英文数据集 pre-train 两个阶段的训练和基于squad数据集fine-tune 训练的代码示例，
## pre-train phrase1
|参数名|解释|示例|
|:---:|:---:|:---:|
|PATH_PHRASE1|第一阶段训练数据集路径|/workspace/lower_case_1_seq_len_128_max_pred_20_masked_lm_prob_0.<br>15_random_seed_12345_dupe_factor_5_shard_1472_test_split_10
|OUTPUT_DIR|输出路径|/workspace/results
|PATH_CONFIG|confing路径|/workspace/bert_large_uncased
|PATH_PHRASE2|第一阶段训练数据集路径|/workspace/lower_case_1_seq_len_512_max_pred_80_masked_lm_prob_0.<br>15_random_seed_12345_dupe_factor_5_shard_1472_test_split_10
<br>
### 单卡
```
export HIP_VISIBLE_DEVICES=0
python3 run_pretraining_v1.py \
--input_dir=${PATH_PHRASE1} \
--output_dir=${OUTPUT_DIR}/checkpoints1 \
--config_file=${PATH_CONFIG}bert_config.json \
--bert_model=bert-large-uncased \
--train_batch_size=16 \
--max_seq_length=128 \
--max_predictions_per_seq=20 \
--max_steps=100000 \
--warmup_proportion=0.0 \
--num_steps_per_checkpoint=20000 \
--learning_rate=4.0e-4 \
--seed=12439 \
--gradient_accumulation_steps=1 \
--allreduce_post_accumulation \
--do_train \
--json-summary dllogger.json
```
### 多卡
* 方法一
```
export HIP_VISIBLE_DEVICES=0,1,2,3
python3 run_pretraining_v1.py \
--input_dir=${PATH_PHRASE1} \
--output_dir=${OUTPUT_DIR}/checkpoints \
--config_file=${PATH_CONFIG}bert_config.json \
--bert_model=bert-large-uncased \
--train_batch_size=16 \
--max_seq_length=128 \
--max_predictions_per_seq=20 \
--max_steps=100000 \
--warmup_proportion=0.0 \
--num_steps_per_checkpoint=20000 \
--learning_rate=4.0e-4 \
--seed=12439 \
--gradient_accumulation_steps=1 \
--allreduce_post_accumulation \
--do_train \
--json-summary dllogger.json
```
* 方法二
hostfile:
```
node1 slots=4
node2 slots=4
```
```
#scripts/run_pretrain.sh 脚本默认每个节点四块卡
cd scripts; bash run_pretrain.sh
```
## pre-train phrase2
### 单卡
```
HIP_VISIBLE_DEVICES=0
python3 run_pretraining_v1.py
--input_dir=${PATH_PHRASE2} \
--output_dir=${OUTPUT_DIR}/checkpoints2 \
--config_file=${PATH_CONFIG}bert_config.json \
--bert_model=bert-large-uncased \
--train_batch_size=4 \
--max_seq_length=512 \
--max_predictions_per_seq=80 \
--max_steps=400000 \
--warmup_proportion=0.128 \
--num_steps_per_checkpoint=200000 \
--learning_rate=4e-3 \
--seed=12439 \
--gradient_accumulation_steps=1 \
--allreduce_post_accumulation \
--do_train \
--phase2 \
--phase1_end_step=0 \
--json-summary dllogger.json
```
### 多卡
* 方法一
```
export HIP_VISIBLE_DEVICES=0,1,2,3
python3 run_pretraining_v1.py
--input_dir=${PATH_PHRASE2} \
--output_dir=${OUTPUT_DIR}/checkpoints2 \
--config_file=${PATH_CONFIG}bert_config.json \
--bert_model=bert-large-uncased \
--train_batch_size=4 \
--max_seq_length=512 \
--max_predictions_per_seq=80 \
--max_steps=400000 \
--warmup_proportion=0.128 \
--num_steps_per_checkpoint=200000 \
--learning_rate=4e-3 \
--seed=12439 \
--gradient_accumulation_steps=1 \
--allreduce_post_accumulation \
--do_train \
--phase2 \
--phase1_end_step=0 \
--json-summary dllogger.json
```
* 方法二
hostfile:
```
node1 slots=4
node2 slots=4
```
```
#scripts/run_pretrain2.sh 脚本默认每个节点四块卡
cd scripts; bash run_pretrain2.sh
```
## fine-tune 训练
### 单卡
```
python3 run_squad_v1.py \
--train_file squad/v1.1/train-v1.1.json \
--init_checkpoint model.ckpt-28252.pt \
--vocab_file vocab.txt \
--output_dir SQuAD \
--config_file bert_config.json \
--bert_model=bert-large-uncased \
--do_train \
--train_batch_size 1 \
--gpus_per_node 1
```
### 多卡
hostfile:
```
node1 slots=4
node2 slots=4
```
```
#scripts/run_squad_1.sh 脚本默认每个节点四块卡
bash run_squad_1.sh
```
# 参考资料
[https://github.com/mlperf/training_results_v0.7/blob/master/NVIDIA/benchmarks/bert/implementations/pytorch](https://github.com/mlperf/training_results_v0.7/blob/master/NVIDIA/benchmarks/bert/implementations/pytorch)
[https://github.com/NVIDIA/DeepLearningExamples/blob/master/PyTorch/LanguageModeling/BERT](https://github.com/NVIDIA/DeepLearningExamples/blob/master/PyTorch/LanguageModeling/BERT)
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