github
/
InternLM
mirror of https://github.com/InternLM/InternLM
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

change into reserved (#550) 

Co-authored-by: kkscilife <wangmengke@pjlab.org.cn>
pull/565/head
kkscilife 2023-12-20 14:41:09 +08:00 committed by GitHub
parent de53b17506
commit a58bf853db
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
9 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/demo_in_readme.yaml vendored
View File

@ -108,7 +108,7 @@ jobs:
export PYTHONPATH=$PWD:$PYTHONPATH
sh ./ci_scripts/model/convert_to_hf.sh
cd ./hf_ckpt
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --quotatype=spot --job-name=${GITHUB_RUN_ID}-${GITHUB_JOB} --gpus-per-task=2 python ../ci_scripts/model/loaded_as_transformer.py
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=${GITHUB_RUN_ID}-${GITHUB_JOB} --gpus-per-task=2 python ../ci_scripts/model/loaded_as_transformer.py
cd ..
rsync -av --remove-source-files $GITHUB_WORKSPACE/hf_ckpt ${{env.WORKSPACE_PREFIX}}/ci_clean_bak
load-chat-model-in-hf:
@ -125,4 +125,4 @@ jobs:
- name: chat-model-in-hf
run: |
source activate internlm-env-test
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --quotatype=spot --job-name=${GITHUB_RUN_ID}-${GITHUB_JOB} --gpus-per-task=2 python ./ci_scripts/model/demo_load_7B_chat_model.py
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=${GITHUB_RUN_ID}-${GITHUB_JOB} --gpus-per-task=2 python ./ci_scripts/model/demo_load_7B_chat_model.py

2
.github/workflows/e2e_test.yaml vendored
View File

@ -19,4 +19,4 @@ jobs:
- name: training_8GPU
run: |
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=${GITHUB_RUN_ID}-${GITHUB_JOB} --quotatype=spot -n8 --ntasks-per-node=8 --cpus-per-task=4 --gpus-per-task=1 pytest -s -v --color=yes -m "training_8GPU" ./tests/test_training
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=${GITHUB_RUN_ID}-${GITHUB_JOB} -n8 --ntasks-per-node=8 --cpus-per-task=4 --gpus-per-task=1 pytest -s -v --color=yes -m "training_8GPU" ./tests/test_training

2
.github/workflows/pr_before_merge.yaml vendored
View File

@ -49,4 +49,4 @@ jobs:
run: |
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
export PYTHONPATH=$PWD:$PYTHONPATH
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-${GITHUB_RUN_ID}-${GITHUB_JOB} --quotatype=spot -N 1 -n 8 --ntasks-per-node=8 --gpus-per-task=1 python ./tests/test_training/train_CI.py --config ./tests/test_training/7B_check_init.py --seed=1024
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 8 --ntasks-per-node=8 --gpus-per-task=1 python ./tests/test_training/train_CI.py --config ./tests/test_training/7B_check_init.py --seed=1024

2
.github/workflows/pr_merged.yaml vendored
View File

@ -49,7 +49,7 @@ jobs:
run: |
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
export PYTHONPATH=$PWD:$PYTHONPATH
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-acc-test-${GITHUB_RUN_ID}-${GITHUB_JOB} --quotatype=spot -N 1 -n 8 --ntasks-per-node=8 --gpus-per-task=1 python ./tests/test_training/train_CI.py --config ./tests/test_training/7B_check_acc.py
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-acc-test-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 8 --ntasks-per-node=8 --gpus-per-task=1 python ./tests/test_training/train_CI.py --config ./tests/test_training/7B_check_acc.py
check_loss_when_swapping_micro_num_and_micro_bsz:
if: ${{ !cancelled() }}

12
.github/workflows/unit_tests.yaml vendored
View File

@ -56,7 +56,7 @@ jobs:
run: |
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
export PYTHONPATH=$PWD:$PYTHONPATH
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} --quotatype=spot -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_core/test_pipeline.py
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_core/test_pipeline.py
unit_tests_utils_storage_manager:
if: ${{ !cancelled() }}
@ -73,7 +73,7 @@ jobs:
run: |
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
export PYTHONPATH=$PWD:$PYTHONPATH
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} --quotatype=spot -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_utils/test_storage_manager.py
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_utils/test_storage_manager.py
unit_tests_model_fused_precision:
if: ${{ !cancelled() }}
@ -90,7 +90,7 @@ jobs:
run: |
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
export PYTHONPATH=$PWD:$PYTHONPATH
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} --quotatype=spot -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_model/test_fused_precision/test_fused_precision.py
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_model/test_fused_precision/test_fused_precision.py
unit_tests_data_batch_sampler:
if: ${{ !cancelled() }}
@ -107,7 +107,7 @@ jobs:
run: |
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
export PYTHONPATH=$PWD:$PYTHONPATH
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} --quotatype=spot -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_data/test_batch_sampler.py
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:8 python -m pytest -s -v ./tests/test_data/test_batch_sampler.py
unit_tests_utils_timeout:
if: ${{ !cancelled() }}
@ -124,7 +124,7 @@ jobs:
run: |
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
export PYTHONPATH=$PWD:$PYTHONPATH
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} --quotatype=spot -N 1 -n 1 --gres=gpu:1 python -m pytest -s -v ./tests/test_utils/test_timeout.py
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:1 python -m pytest -s -v ./tests/test_utils/test_timeout.py
unit_tests_utils_model_checkpoint:
if: ${{ !cancelled() }}
@ -141,4 +141,4 @@ jobs:
run: |
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
export PYTHONPATH=$PWD:$PYTHONPATH
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} --quotatype=spot -N 1 -n 1 --gres=gpu:2 python -m pytest -s -v ./tests/test_utils/test_model_checkpoint.py
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-ut-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:2 python -m pytest -s -v ./tests/test_utils/test_model_checkpoint.py

2
ci_scripts/data/tokenizer_chinese.sh
View File

@ -23,7 +23,7 @@ if [[ ${num} -gt 0 ]]; then
fi
fi
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --quotatype=spot --job-name=$1 --gpus-per-task=1 python tools/tokenizer.py --text_input_path ${DATA} --bin_output_path ${RESULT}
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=$1 --gpus-per-task=1 python tools/tokenizer.py --text_input_path ${DATA} --bin_output_path ${RESULT}
[[ $? -ne 0 ]] && { echo "test tokenizer.py failed."; exit_code=$(($exit_code + 1)); }
file_list=($RESULT $RESULT_META)

2
ci_scripts/train/load_ckpt.sh
View File

@ -22,7 +22,7 @@ if [[ ! -f ${file} ]]; then
exit_code=$(($exit_code + 1))
fi
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --exclusive --quotatype=spot --job-name=$2 -n 8 --ntasks-per-node=8 --gpus-per-task=1 python train.py --config ${file}
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --exclusive --job-name=$2 -n 8 --ntasks-per-node=8 --gpus-per-task=1 python train.py --config ${file}
[[ $? -ne 0 ]] && { echo "test slurm training failed."; exit_code=$(($exit_code + 1)); }

2
ci_scripts/train/slurm_train.sh
View File

@ -22,7 +22,7 @@ if [[ -d ${CKPTS20_PATH} ]]; then
fi
fi
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --exclusive --quotatype=spot --job-name=$1 -n 8 --ntasks-per-node=8 --gpus-per-task=1 python train.py --config ./ci_scripts/train/ci_7B_sft.py
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --exclusive --job-name=$1 -n 8 --ntasks-per-node=8 --gpus-per-task=1 python train.py --config ./ci_scripts/train/ci_7B_sft.py
[[ $? -ne 0 ]] && { echo "test slurm training failed."; exit_code=$(($exit_code + 1)); }
num=$(num_files "${CKPTS20_OUTPUT}")

2
ci_scripts/train/torchrun.sh
View File

@ -22,7 +22,7 @@ if [[ -d ${CKPTS20_PATH} ]]; then
fi
fi
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --exclusive --quotatype=spot --job-name=$1 -N 1 torchrun --nnodes=1 --nproc_per_node=8 --master_port=29501 train.py --config ./ci_scripts/train/ci_7B_sft.py --launcher torch
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --exclusive --job-name=$1 -N 1 torchrun --nnodes=1 --nproc_per_node=8 --master_port=29501 train.py --config ./ci_scripts/train/ci_7B_sft.py --launcher torch
[[ $? -ne 0 ]] && { echo "test torch training failed."; exit_code=$(($exit_code + 1)); }
num=$(num_files "${CKPTS_OUTPUT}")