phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-16 06:53:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add eval_id for jobs

Browse source
This commit is contained in:
Xi Yan 2024-11-07 14:30:46 -08:00
parent ea80f623fb
commit f05db9a25c
4 changed files with 30 additions and 41 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/tests/eval/test_eval.py
View file

@ -52,7 +52,7 @@ class Testeval:
response = await eval_impl.evaluate_rows(
input_rows=rows.rows,
scoring_functions=scoring_functions,
eval_task_config=AppEvalTaskConfig(
task_config=AppEvalTaskConfig(
eval_candidate=ModelCandidate(
model="Llama3.2-3B-Instruct",
sampling_params=SamplingParams(),
@ -90,9 +90,13 @@ class Testeval:
),
)
assert response.job_id == "0"
job_status = await eval_impl.job_status(response.job_id)
job_status = await eval_impl.job_status(
response.job_id, "meta-reference::app_eval"
)
assert job_status and job_status.value == "completed"
eval_response = await eval_impl.job_result(response.job_id)
eval_response = await eval_impl.job_result(
response.job_id, "meta-reference::app_eval"
)
assert eval_response is not None
assert len(eval_response.generations) == 5