minor: update gsm8k threshold (#2125)
This commit is contained in:
12
.github/workflows/nightly-eval.yml
vendored
12
.github/workflows/nightly-eval.yml
vendored
@@ -27,14 +27,14 @@ jobs:
|
||||
bash scripts/ci_install_dependency.sh
|
||||
pip install --upgrade "evalplus[vllm] @ git+https://github.com/evalplus/evalplus"
|
||||
|
||||
- name: Test human eval
|
||||
timeout-minutes: 120
|
||||
run: |
|
||||
cd test/srt
|
||||
python3 test_nightly_human_eval.py
|
||||
|
||||
- name: Test gsm8k
|
||||
timeout-minutes: 120
|
||||
run: |
|
||||
cd test/srt
|
||||
python3 test_nightly_gsm8k_eval.py
|
||||
|
||||
- name: Test human eval
|
||||
timeout-minutes: 120
|
||||
run: |
|
||||
cd test/srt
|
||||
python3 test_nightly_human_eval.py
|
||||
|
||||
Reference in New Issue
Block a user