jiangzhs/OpenCompass
1
0
Fork 0
mirror of https://github.com/open-compass/opencompass.git synced 2025-05-30 16:03:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix

Browse Source
This commit is contained in:
Myhs-phz 2025-04-07 08:56:57 +00:00
parent 802d365a7b
commit a23f95e47b
1 changed files with 12 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
opencompass/summarizers/default.py
View File

@ -111,7 +111,11 @@ class DefaultSummarizer:
_dm = sorted(_dm, key=lambda i: METRIC_WHITELIST.index(i) if i in METRIC_WHITELIST else len(METRIC_WHITELIST))
if dataset_abbr in dataset_metrics:
assert tuple(dataset_metrics[dataset_abbr]) == tuple(_dm), \
if len(_dm) == 1:
if _dm in dataset_metrics[dataset_abbr]:
dataset_metrics[dataset_abbr] = _dm
else:
assert tuple(dataset_metrics[dataset_abbr]) == tuple(_dm) or dataset_metrics[dataset_abbr][0] in _dm, \
f'{dataset_abbr} has different metrics: {dataset_metrics[dataset_abbr]} vs {_dm}'
else:
dataset_metrics[dataset_abbr] = _dm
@ -197,9 +201,12 @@ class DefaultSummarizer:
parsed_results[model_abbr][dataset_abbr][metric_default]
eval_modes.append(dataset_eval_mode.get(dataset_abbr, 'unknown'))
else:
try:
scores.setdefault(metric, {})[dataset_abbr + '@' + metric] = \
parsed_results[model_abbr][dataset_abbr][metric]
eval_modes.append(dataset_eval_mode.get(sg['subsets'][0], 'unknown'))
except:
continue
result = {}
for metric in scores:
if default_metric == 'standard_deviation':