Skip to content

Fix(StaticBatchSampler): fix statics of num_consumed_samples_in_epoch… #5

Fix(StaticBatchSampler): fix statics of num_consumed_samples_in_epoch…

Fix(StaticBatchSampler): fix statics of num_consumed_samples_in_epoch… #5

Workflow file for this run

name: pr-merged
on:
push:
branches:
- "develop"
- "main"
paths-ignore:
- "cmds/**"
- "**.md"
env:
WORKSPACE_PREFIX: $(echo $GITHUB_WORKSPACE |cut -d '/' -f 1-4)
SLURM_PARTITION: llm_s
jobs:
check-requirements:
runs-on: [t_cluster]
steps:
- name: mask env
run: |
echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
- uses: actions/checkout@v3
with:
fetch-depth: 2
- name: check-requirements
run: |
changed_files=$(git diff --name-only -r HEAD^1 HEAD)
echo $changed_files
if [[ $changed_files =~ "runtime.txt" ]]; then
pip install -r requirements/runtime.txt
fi
if [[ $changed_files =~ "torch.txt" ]]; then
pip install -r requirements/torch.txt
fi
acc_tests:
if: ${{ !cancelled() }}
needs: check-requirements
runs-on: [t_cluster]
timeout-minutes: 30
steps:
- name: mask env
run: |
echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
- uses: actions/checkout@v3
- name: acc_tests
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} -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: ${{ !cancelled() }}
needs: check-requirements
runs-on: [t_cluster]
timeout-minutes: 40
steps:
- name: mask env
run: |
echo "::add-mask::${{env.WORKSPACE_PREFIX}}"
- uses: actions/checkout@v3
- name: loss_tests
run: |
source /mnt/petrelfs/share_data/llm_env/env/llm-flash2.0
export PYTHONPATH=$PWD:$PYTHONPATH
srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=internlm-loss-test-${GITHUB_RUN_ID}-${GITHUB_JOB} -N 1 -n 1 --gres=gpu:8 python -m pytest -s ./tests/test_training/test_swap_nb_loss_and_gradnorm.py