mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2026-04-26 09:42:27 +00:00
da4f7b855f
* style: rename replay buffer Experience replay is typically for off policy algorithms. Use this name in PPO maybe misleading. * fix: fix wrong zero2 default arg * test: update experience tests * style: rename zero_pad fn * fix: defer init in CycledDataLoader * test: add benchmark test * style: rename internal fn of generation * style: rename internal fn of lora * fix: remove unused loss fn * fix: remove unused utils fn * refactor: remove generate_with_actor fn * fix: fix type annotation * test: add models tests * fix: skip llama due to long execution time * style: modify dataset * style: apply formatter * perf: update reward dataset * fix: fix wrong IGNORE_INDEX in sft dataset * fix: remove DataCollatorForSupervisedDataset * test: add dataset tests * style: apply formatter * style: rename test_ci to test_train * feat: add llama in inference * test: add inference tests * test: change test scripts directory * fix: update ci * fix: fix typo * fix: skip llama due to oom * fix: fix file mod * style: apply formatter * refactor: remove duplicated llama_gptq * style: apply formatter * to: update rm test * feat: add tokenizer arg * feat: add download model script * test: update train tests * fix: modify gemini load and save pretrained * test: update checkpoint io test * to: modify nproc_per_node * fix: do not remove existing dir * fix: modify save path * test: add random choice * fix: fix sft path * fix: enlarge nproc_per_node to avoid oom * fix: add num_retry * fix: make lora config of rm and critic consistent * fix: add warning about lora weights * fix: skip some gpt2 tests * fix: remove grad ckpt in rm and critic due to errors * refactor: directly use Actor in train_sft * test: add more arguments * fix: disable grad ckpt when using lora * fix: fix save_pretrained and related tests * test: enable zero2 tests * revert: remove useless fn * style: polish code * test: modify test args
55 lines
1.6 KiB
YAML
55 lines
1.6 KiB
YAML
name: Run ChatGPT examples
|
|
|
|
on:
|
|
pull_request:
|
|
types: [synchronize, opened, reopened]
|
|
paths:
|
|
- "applications/Chat/coati/**"
|
|
- "applications/Chat/requirements.txt"
|
|
- "applications/Chat/setup.py"
|
|
- "applications/Chat/examples/**"
|
|
|
|
jobs:
|
|
tests:
|
|
name: Run ChatGPT examples
|
|
if: |
|
|
github.event.pull_request.draft == false &&
|
|
github.base_ref == 'main' &&
|
|
github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
|
|
runs-on: [self-hosted, gpu]
|
|
container:
|
|
image: hpcaitech/pytorch-cuda:1.12.0-11.3.0
|
|
options: --gpus all --rm -v /data/scratch/github_actions/chat:/data/scratch/github_actions/chat --shm-size=10.24gb
|
|
timeout-minutes: 30
|
|
defaults:
|
|
run:
|
|
shell: bash
|
|
steps:
|
|
- name: Checkout ColossalAI
|
|
uses: actions/checkout@v2
|
|
|
|
- name: Install ColossalAI and ChatGPT
|
|
run: |
|
|
pip install -e .
|
|
cd applications/Chat
|
|
pip install -v .
|
|
pip install -r examples/requirements.txt
|
|
|
|
- name: Install Transformers
|
|
run: |
|
|
pip install transformers==4.30.2
|
|
|
|
- name: Execute Examples
|
|
run: |
|
|
cd applications/Chat
|
|
rm -rf ~/.cache/colossalai
|
|
./tests/test_inference.sh
|
|
./tests/test_benchmarks.sh
|
|
./tests/test_train.sh
|
|
env:
|
|
NCCL_SHM_DISABLE: 1
|
|
MAX_JOBS: 8
|
|
SFT_DATASET: /data/scratch/github_actions/chat/data.json
|
|
PROMPT_PATH: /data/scratch/github_actions/chat/prompts_en.jsonl
|
|
PRETRAIN_DATASET: /data/scratch/github_actions/chat/alpaca_data.json
|