Commit Graph

9 Commits

Author SHA1 Message Date
Junnan Liu
73c80953c6
[Feature] Support Dataset Repeat and G-Pass Compute for Each Evaluator (#1886)
* 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
2025-02-26 19:43:12 +08:00
Junnan Liu
22a33d8759
[Update] Update LiveMathBench Hard Configs (#1826)
* support G-Pass@k and livemathbench

* fix bugs

* fix comments of GPassKEvaluator

* update saved details of GPassKEvaluator

* update saved details of GPassKEvaluator

* fix eval api configs & update openai_api for ease of debugging

* update huggingface path

* fix method name of G-Pass@k

* fix default value of eval_model_name

* refactor G-Pass@k evaluator

* log generation params for each backend

* fix evaluation resume

* add notimplementerror

* update livemathbench-hard configs

* remove max_out_len from livemathbench_hard_greedy_gen_9befbf.py

* remove max_out_len from livemathbench_hard_gen_9befbf.py

* rename livemathbench_hard_gen_9befbf.py to livemathbench_hard_gen_353ae7.py

* rename livemathbench_hard_greedy_gen_9befbf.py to livemathbench_hard_greedy_gen_353ae7.py

* update livemathbench_gen_9befbf.py

* remove whitespace

* upload livemathbench hard configs
2025-02-25 17:24:36 +08:00
Songyang Zhang
8fdb72f567
[Update] Update o1 eval prompt (#1806)
* Update XML prediction post-process

* Update LiveMathBench

* Update LiveMathBench

* Update New O1 Evaluation
2025-01-07 00:14:32 +08:00
Junnan Liu
8e8d4f1c64
[Feature] Support G-Pass@k and LiveMathBench (#1772)
* support G-Pass@k and livemathbench

* fix bugs

* fix comments of GPassKEvaluator

* update saved details of GPassKEvaluator

* update saved details of GPassKEvaluator

* fix eval api configs & update openai_api for ease of debugging

* update huggingface path

* fix method name of G-Pass@k

* fix default value of eval_model_name

* refactor G-Pass@k evaluator

* log generation params for each backend

* fix evaluation resume

* add notimplementerror
2024-12-30 16:59:39 +08:00
Songyang Zhang
0d8df541bc
[Update] Update O1-style Benchmark and Prompts (#1742)
* Update JuderBench

* Support O1-style Prompts

* Update Code

* Update OpenAI

* Update BigCodeBench

* Update BigCodeBench

* Update BigCodeBench

* Update BigCodeBench

* Update BigCodeBench

* Update

* Update

* Update

* Update
2024-12-09 13:48:56 +08:00
Junnan Liu
f333be177c
[Update] Add MATH500 & AIME2024 to LiveMathBench (#1741)
* upload dataset definitions & configs

* add single dataset split specific metrics

* add k-pass@threshold & MATH500

* update std computation & k-pass computation

* add AIME224

* update README
2024-12-06 14:36:49 +08:00
Songyang Zhang
fb43dd1906
[Update] Update Skywork/Qwen-QwQ (#1728)
* Update JuderBench

* Support O1-style Prompts

* Update Code

* Update OpenAI

* Update BigCodeBench

* Update BigCodeBench

* Update BigCodeBench

* Update BigCodeBench

* Update BigCodeBench

* Update
2024-12-05 19:30:43 +08:00
Junnan Liu
6181ac1122
[Update] Update LiveMathBench Evaluation to Support Single Dataset Split Metric Computation (#1730)
* upload dataset definitions & configs

* add single dataset split specific metrics

* add k-pass@threshold & MATH500
2024-12-05 16:54:16 +08:00
Junnan Liu
fe6d76fb13
[Feature] Support LiveMathBench (#1727) 2024-11-30 00:07:19 +08:00