mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
[Feature] Update BailingLM/OpenAI verbose (#1568)
* [Feature] 1. Update CoreBench Base\n 2. Fix lint issue in BalingAPI * Update * [Feature] Update API * Update
This commit is contained in:
parent
7d50294117
commit
e8437db98f
@ -81,7 +81,7 @@ core_summary_groups = [
|
||||
['drop', 'accuracy'],
|
||||
['math', 'accuracy'],
|
||||
['gsm8k', 'accuracy'],
|
||||
['mathbench-t (average)', 'naive_average']
|
||||
['mathbench-t (average)', 'naive_average'],
|
||||
['GPQA_diamond', 'accuracy'],
|
||||
['openai_humaneval', 'humaneval_pass@1'],
|
||||
['IFEval', 'Prompt-level-strict-accuracy'],
|
||||
@ -101,7 +101,7 @@ summarizer = dict(
|
||||
['drop', 'accuracy'],
|
||||
['math', 'accuracy'],
|
||||
['gsm8k', 'accuracy'],
|
||||
['mathbench-t (average)', 'naive_average']
|
||||
['mathbench-t (average)', 'naive_average'],
|
||||
['GPQA_diamond', 'accuracy'],
|
||||
['openai_humaneval', 'humaneval_pass@1'],
|
||||
['IFEval', 'Prompt-level-strict-accuracy'],
|
||||
@ -185,4 +185,4 @@ eval = dict(
|
||||
# PART 5 Utils Configuaration #
|
||||
#######################################################################
|
||||
base_exp_dir = 'outputs/corebench_2409_objective/'
|
||||
work_dir = osp.join(base_exp_dir, 'chat_objective')
|
||||
work_dir = osp.join(base_exp_dir, 'base_objective')
|
||||
|
@ -13,7 +13,6 @@ try:
|
||||
from retrying import retry
|
||||
except ImportError:
|
||||
retry = None
|
||||
print('please install retrying by `pip install retrying`')
|
||||
|
||||
from opencompass.utils.prompt import PromptList
|
||||
|
||||
|
@ -601,6 +601,10 @@ class OpenAISDK(OpenAI):
|
||||
if self.verbose:
|
||||
self.logger.info(
|
||||
'Successfully get response from OpenAI API')
|
||||
try:
|
||||
self.logger.info(responses)
|
||||
except Exception as e: # noqa F841
|
||||
pass
|
||||
return responses.choices[0].message.content
|
||||
except Exception as e:
|
||||
self.logger.error(e)
|
||||
|
Loading…
Reference in New Issue
Block a user