From f0809fe6f62bf66cc1c3ed666c6d796caab2881f Mon Sep 17 00:00:00 2001 From: Junnan Liu Date: Mon, 3 Mar 2025 18:17:15 +0800 Subject: [PATCH] [Update] Fix Hard Configs With General GPassK (#1906) * support dataset repeat and g-pass compute for each evaluator * fix pre-commit errors * delete print * delete gpassk_evaluator and fix potential errors * change `repeat` to `n` * fix `repeat` to `n` in openicl_eval * update doc for multi-run and g-pass * update latex equation in doc * update eng doc for multi-run and g-pass * update datasets.md * update datasets.md * fix multi-line equation * fix multi-line equation * fix multi-line equation * fix multi-line equation * fix multi-line equation * fix multi-line equation * fix multi-line equation in zh_cn user_guides * mmodify pre-commit-zh-cn * recover pre-commit and edit math expr in doc * del [TIP] * del cite tag in doc * del extract_model param in livemathbench config * fix livemathbench hard configs --- .../livemathbench/livemathbench_hard_gen_353ae7.py | 10 ++-------- .../livemathbench_hard_greedy_gen_353ae7.py | 10 ++-------- 2 files changed, 4 insertions(+), 16 deletions(-) diff --git a/opencompass/configs/datasets/livemathbench/livemathbench_hard_gen_353ae7.py b/opencompass/configs/datasets/livemathbench/livemathbench_hard_gen_353ae7.py index e932d3c3..6b2f9f5a 100644 --- a/opencompass/configs/datasets/livemathbench/livemathbench_hard_gen_353ae7.py +++ b/opencompass/configs/datasets/livemathbench/livemathbench_hard_gen_353ae7.py @@ -9,7 +9,7 @@ livemathbench_dataset = dict( type=LiveMathBenchDataset, path='', k=16, - replication=3, + n=48, dataset_splits=['hard'], dataset_languages=['cn', 'en'], cot=True, @@ -37,13 +37,7 @@ livemathbench_dataset = dict( evaluator=dict( type=LiveMathBenchEvaluator, model_name='', - url=[], - use_extract_model=False, - extract_url=[], - extract_model_name='', - k=[4, 8, 16], - replication=3, - thresholds=[0.0, 0.25, 0.5, 0.75, 1.0] + url=[] ) ) ) diff --git a/opencompass/configs/datasets/livemathbench/livemathbench_hard_greedy_gen_353ae7.py b/opencompass/configs/datasets/livemathbench/livemathbench_hard_greedy_gen_353ae7.py index 830e55af..f956f83e 100644 --- a/opencompass/configs/datasets/livemathbench/livemathbench_hard_greedy_gen_353ae7.py +++ b/opencompass/configs/datasets/livemathbench/livemathbench_hard_greedy_gen_353ae7.py @@ -9,7 +9,7 @@ livemathbench_dataset = dict( type=LiveMathBenchDataset, path='', k=1, - replication=1, + n=1, dataset_splits=['hard'], dataset_languages=['cn', 'en'], cot=True, @@ -37,13 +37,7 @@ livemathbench_dataset = dict( evaluator=dict( type=LiveMathBenchEvaluator, model_name='', - url=[], - use_extract_model=False, - extract_url=[], - extract_model_name='', - k=[1], - replication=1, - thresholds=[0.0] + url=[] ) ) )