mirror of https://github.com/InternLM/InternLM
parent
de53b17506
commit
a58bf853db
|
@ -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
|
||||
|
|
|
@ -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}-${GITHUB_JOB} -n8 --ntasks-per-node=8 --cpus-per-task=4 --gpus-per-task=1 pytest -s -v --color=yes -m "training_8GPU" ./tests/test_training
|
||||
|
|
|
@ -49,4 +49,4 @@ jobs:
|
|||
run: |
|
||||
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
|
||||
export PYTHONPATH=$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}-${GITHUB_JOB} -N 1 -n 8 --ntasks-per-node=8 --gpus-per-task=1 python ./tests/test_training/train_CI.py --config ./tests/test_training/7B_check_init.py --seed=1024
|
||||
|
|
|
@ -49,7 +49,7 @@ jobs:
|
|||
run: |
|
||||
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
|
||||
export PYTHONPATH=$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: ${{ !cancelled() }}
|
||||
|
|
|
@ -56,7 +56,7 @@ jobs:
|
|||
run: |
|
||||
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
|
||||
export PYTHONPATH=$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
|
||||
|
|
|
@ -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)
|
||||
|
|
|
@ -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)); }
|
||||
|
||||
|
||||
|
|
|
@ -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}")
|
||||
|
|
|
@ -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}")
|
||||
|
|
Loading…
Reference in New Issue