From 1448be00e2d83b3a3a8eb05a97075c5bbf2f8e6a Mon Sep 17 00:00:00 2001 From: liushz Date: Tue, 21 May 2024 14:45:43 +0800 Subject: [PATCH] Update MathBench (#1176) * Add Math Evaluation with Judge Model Evaluator * Add Math Evaluation with Judge Model Evaluator * Add Math Evaluation with Judge Model Evaluator * Add Math Evaluation with Judge Model Evaluator * Fix Llama-3 meta template * Fix MATH with JudgeLM Evaluation * Fix MATH with JudgeLM Evaluation * Fix MATH with JudgeLM Evaluation * Fix MATH with JudgeLM Evaluation * Update acclerator * Update MathBench --------- Co-authored-by: liuhongwei --- ...athbench_2024_gen_649349.py => mathbench_2024_gen_19e486.py} | 2 +- configs/datasets/MathBench/mathbench_gen.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) rename configs/datasets/MathBench/{mathbench_2024_gen_649349.py => mathbench_2024_gen_19e486.py} (99%) diff --git a/configs/datasets/MathBench/mathbench_2024_gen_649349.py b/configs/datasets/MathBench/mathbench_2024_gen_19e486.py similarity index 99% rename from configs/datasets/MathBench/mathbench_2024_gen_649349.py rename to configs/datasets/MathBench/mathbench_2024_gen_19e486.py index 93238892..6cde6c69 100644 --- a/configs/datasets/MathBench/mathbench_2024_gen_649349.py +++ b/configs/datasets/MathBench/mathbench_2024_gen_19e486.py @@ -91,7 +91,7 @@ for _split in list(mathbench_sets.keys()): ), ), retriever=dict(type=ZeroRetriever), - inferencer=dict(type=GenInferencer, max_out_len=512), + inferencer=dict(type=GenInferencer, max_out_len=2048), ) mathbench_eval_cfg = dict( diff --git a/configs/datasets/MathBench/mathbench_gen.py b/configs/datasets/MathBench/mathbench_gen.py index 942566fa..63478a60 100644 --- a/configs/datasets/MathBench/mathbench_gen.py +++ b/configs/datasets/MathBench/mathbench_gen.py @@ -1,4 +1,4 @@ from mmengine.config import read_base with read_base(): - from .mathbench_2024_gen_649349 import mathbench_datasets # noqa: F401, F403 + from .mathbench_2024_gen_19e486 import mathbench_datasets # noqa: F401, F403