Skip to content

[ci] update baseline and fix lmdeploy version #2098

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
MaiziXiao merged 6 commits into from
May 13, 2025
Merged

[ci] update baseline and fix lmdeploy version #2098

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
c269cc0
update
zhulinJulia24 May 12, 2025
3472ed1
update
zhulinJulia24 May 13, 2025
6dbbd80
update
zhulinJulia24 May 13, 2025
474769c
update
zhulinJulia24 May 13, 2025
4641a28
update
zhulinJulia24 May 13, 2025
1cc8572
update
zhulinJulia24 May 13, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions .github/scripts/oc_score_baseline.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ internlm2_5-7b_hf:
race-high_accuracy: 90.02

internlm2_5-7b-chat-lmdeploy:
demo_gsm8k_accuracy: 87.50
demo_gsm8k_accuracy: 84.38
race-middle_accuracy: 92.76
race-high_accuracy: 90.54

Expand All @@ -24,7 +24,7 @@ internlm3-8b-instruct_hf-lmdeploy:
race-high_accuracy: 90.34

internlm3-8b-instruct_hf-vllm:
demo_gsm8k_accuracy: 81.25
demo_gsm8k_accuracy: 78.12
race-middle_accuracy: 92.20
race-high_accuracy: 89.88

Expand All @@ -34,6 +34,6 @@ internlm2_5-7b-chat_hf:
race-high_accuracy: 90.48

lmdeploy-api-test:
gsm8k_accuracy: 56.25
gsm8k_accuracy: 68.75
race-middle_accuracy: 93.75
race-high_accuracy: 93.75
156 changes: 78 additions & 78 deletions .github/scripts/oc_score_baseline_fullbench.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,27 +39,27 @@ internlm2_5-7b-chat-hf_fullbench:
college_knowledge_naive_average: 87.5
subjective:
alignment_bench_v1_1_总分: 0.66
alpaca_eval_total: 0
arenahard_score: 50
alpaca_eval_total: 20.00
arenahard_score: 56.82
Followbench_naive_average: 1
CompassArena_naive_average: 43
mtbench101_avg: 7.8
wildbench_average: -15.56
simpleqa_accuracy_given_attempted: 0
chinese_simpleqa_given_attempted_accuracy: 1
alignment_bench_v1_1_专业能力: 8.00
mtbench101_avg: 7.60
wildbench_average: -14.58
simpleqa_accuracy_given_attempted: 1.00
chinese_simpleqa_given_attempted_accuracy: 0.90
alignment_bench_v1_1_专业能力: 7.90
alignment_bench_v1_1_数学计算: 0
alignment_bench_v1_1_基本任务: 0
alignment_bench_v1_1_逻辑推理: 0
alignment_bench_v1_1_中文理解: 0
alignment_bench_v1_1_文本写作: 0
alignment_bench_v1_1_角色扮演: 0
alignment_bench_v1_1_综合问答: 0
alpaca_eval_helpful_base: 0
alpaca_eval_helpful_base: 20.00
compassarena_language_naive_average: 35
compassarena_knowledge_naive_average: 55
compassarena_knowledge_naive_average: 60.00
compassarena_reason_v2_naive_average: 40
compassarena_math_v2_naive_average: 55
compassarena_math_v2_naive_average: 50.00
compassarena_creationv2_zh_naive_average: 30
followbench_llmeval_en_HSR_AVG: 1
followbench_llmeval_en_SSR_AVG: 1
Expand All @@ -73,71 +73,71 @@ internlm2_5-7b-chat-hf_fullbench:
followbench_llmeval_en_SSR_L3: 1
followbench_llmeval_en_SSR_L4: 1
followbench_llmeval_en_SSR_L5: 1
simpleqa_f1: 0
simpleqa_f1: 0.12

internlm2_5-7b-chat-turbomind_fullbench:
objective:
race-high_accuracy: 93.75
ARC-c_accuracy: 87.50
BoolQ_accuracy: 68.75
ARC-c_accuracy: 93.75
BoolQ_accuracy: 75.00
triviaqa_wiki_1shot_score: 50
nq_open_1shot_score: 25
IFEval_Prompt-level-strict-accuracy: 56.25
drop_accuracy: 75
GPQA_diamond_accuracy: 31.25
hellaswag_accuracy: 87.5
GPQA_diamond_accuracy: 37.50
hellaswag_accuracy: 81.25
TheoremQA_score: 12.5
musr_average_naive_average: 39.58
korbench_single_naive_average: 40
gsm8k_accuracy: 62.5
math_accuracy: 75
gsm8k_accuracy: 68.75
math_accuracy: 68.75
cmo_fib_accuracy: 6.25
aime2024_accuracy: 6.25
wikibench-wiki-single_choice_cncircular_perf_4: 25
sanitized_mbpp_score: 68.75
ds1000_naive_average: 17.86
ds1000_naive_average: 15.18
lcb_code_generation_pass@1: 12.5
lcb_code_execution_pass@1: 43.75
lcb_test_output_pass@1: 18.75
bbh-logical_deduction_seven_objects_score: 56.25
bbh-multistep_arithmetic_two_score: 75
mmlu-other_accuracy: 72.6
cmmlu-china-specific_accuracy: 78.33
mmlu_pro_math_accuracy: 31.25
ds1000_Pandas_accuracy: 12.5
lcb_test_output_pass@1: 0.00
bbh-logical_deduction_seven_objects_score: 62.50
bbh-multistep_arithmetic_two_score: 62.50
mmlu-other_accuracy: 73.08
cmmlu-china-specific_accuracy: 75.42
mmlu_pro_math_accuracy: 25.00
ds1000_Pandas_accuracy: 0.00
ds1000_Numpy_accuracy: 0
ds1000_Tensorflow_accuracy: 12.5
ds1000_Scipy_accuracy: 25
ds1000_Scipy_accuracy: 18.75
ds1000_Sklearn_accuracy: 18.75
ds1000_Pytorch_accuracy: 6.25
ds1000_Matplotlib_accuracy: 50.00
ds1000_Pytorch_accuracy: 12.50
ds1000_Matplotlib_accuracy: 43.75
openai_mmmlu_lite_AR-XY_accuracy: 37.5
college_naive_average: 12.50
college_knowledge_naive_average: 87.5
subjective:
alignment_bench_v1_1_总分: 0.66
alpaca_eval_total: 0
arenahard_score: 50
alignment_bench_v1_1_总分: 0.72
alpaca_eval_total: 20.00
arenahard_score: 55.77
Followbench_naive_average: 1
CompassArena_naive_average: 40
mtbench101_avg: 8
wildbench_average: -6.81
simpleqa_accuracy_given_attempted: 0
CompassArena_naive_average: 39.00
mtbench101_avg: 7.90
wildbench_average: 0.00
simpleqa_accuracy_given_attempted: 1.00
chinese_simpleqa_given_attempted_accuracy: 1
alignment_bench_v1_1_专业能力: 7.9
alignment_bench_v1_1_专业能力: 8.70
alignment_bench_v1_1_数学计算: 0
alignment_bench_v1_1_基本任务: 0
alignment_bench_v1_1_逻辑推理: 0
alignment_bench_v1_1_中文理解: 0
alignment_bench_v1_1_文本写作: 0
alignment_bench_v1_1_角色扮演: 0
alignment_bench_v1_1_综合问答: 0
alpaca_eval_helpful_base: 0
compassarena_language_naive_average: 35
compassarena_knowledge_naive_average: 45
compassarena_reason_v2_naive_average: 25
compassarena_math_v2_naive_average: 60
compassarena_creationv2_zh_naive_average: 35
alpaca_eval_helpful_base: 20.00
compassarena_language_naive_average: 25.00
compassarena_knowledge_naive_average: 55.00
compassarena_reason_v2_naive_average: 35.00
compassarena_math_v2_naive_average: 55.00
compassarena_creationv2_zh_naive_average: 25.00
followbench_llmeval_en_HSR_AVG: 1
followbench_llmeval_en_SSR_AVG: 1
followbench_llmeval_en_HSR_L1: 1
Expand All @@ -150,7 +150,7 @@ internlm2_5-7b-chat-turbomind_fullbench:
followbench_llmeval_en_SSR_L3: 1
followbench_llmeval_en_SSR_L4: 1
followbench_llmeval_en_SSR_L5: 1
simpleqa_f1: 0
simpleqa_f1: 0.12

internlm2_5-7b-hf_fullbench:
objective:
Expand All @@ -162,7 +162,7 @@ internlm2_5-7b-hf_fullbench:
drop_accuracy: 62.5
GPQA_diamond_accuracy: 62.5
hellaswag_accuracy: 93.75
TheoremQA_score: 12.50
TheoremQA_score: 18.75
winogrande_accuracy: 75
gsm8k_accuracy: 37.5
GaokaoBench_2010-2022_Math_II_MCQs_score: 62.5
Expand All @@ -188,23 +188,23 @@ internlm2_5-7b-turbomind_fullbench:
triviaqa_wiki_1shot_score: 43.75
nq_open_1shot_score: 43.75
drop_accuracy: 62.5
GPQA_diamond_accuracy: 62.5
GPQA_diamond_accuracy: 68.75
hellaswag_accuracy: 93.75
TheoremQA_score: 12.50
TheoremQA_score: 18.75
winogrande_accuracy: 87.5
gsm8k_accuracy: 56.25
GaokaoBench_2010-2022_Math_II_MCQs_score: 68.75
gsm8k_accuracy: 62.50
GaokaoBench_2010-2022_Math_II_MCQs_score: 93.75
GaokaoBench_2010-2022_Math_II_Fill-in-the-Blank_score: 0
math_accuracy: 18.75
wikibench-wiki-single_choice_cncircular_perf_4: 25
math_accuracy: 6.25
wikibench-wiki-single_choice_cncircular_perf_4: 0.00
sanitized_mbpp_score: 62.50
dingo_en_192_score: 50.00
dingo_zh_170_score: 93.75
mmlu-other_accuracy: 76.92
cmmlu-china-specific_accuracy: 84.17
dingo_en_192_score: 37.50
dingo_zh_170_score: 100.00
mmlu-other_accuracy: 78.37
cmmlu-china-specific_accuracy: 83.33
mmlu_pro_math_accuracy: 18.75
bbh-logical_deduction_seven_objects_score: 43.75
bbh-multistep_arithmetic_two_score: 56.25
bbh-logical_deduction_seven_objects_score: 62.50
bbh-multistep_arithmetic_two_score: 50.00
college_naive_average: 12.5
college_knowledge_naive_average: 87.5

Expand All @@ -230,7 +230,7 @@ internlm2_5-7b-turbomind:
mmlu_naive_average: 71.44
mmlu_pro_naive_average: 38.18
openai_humaneval_humaneval_pass@1: 59.76
openai_humaneval_v2_humaneval_pass@1: 51.22
openai_humaneval_v2_humaneval_pass@1: 57.93
sanitized_mbpp_score: 55.25
dingo_en_192_score: 60.94
dingo_zh_170_score: 67.65
Expand All @@ -257,17 +257,17 @@ internlm2_5-7b-turbomind:
mmlu_pro_physics_accuracy: 26.02
mmlu_pro_psychology_accuracy: 52.76
mmlu_pro_other_accuracy: 42.21
college_naive_average: 10.67
college_naive_average: 7.00
high_naive_average: 6.67
middle_naive_average: 26.67
primary_naive_average: 60
primary_naive_average: 64.00
arithmetic_naive_average: 55
mathbench-a (average)_naive_average: 31.8
college_knowledge_naive_average: 62.34
high_knowledge_naive_average: 59.83
college_knowledge_naive_average: 58.23
high_knowledge_naive_average: 52.51
middle_knowledge_naive_average: 71.15
primary_knowledge_naive_average: 66.55
mathbench-t (average)_naive_average: 64.97
primary_knowledge_naive_average: 60.48
mathbench-t (average)_naive_average: 60.19
long_context:
Single-Needle-Retrieval(S-RT)-32000_naive_average: 100
Single-Needle-Retrieval-EN-32000_naive_average: 100
Expand Down Expand Up @@ -309,7 +309,7 @@ internlm2_5-7b-chat-turbomind:
GaokaoBench_weighted_average: 78.6
math_accuracy: 61
cmo_fib_accuracy: 11
aime2024_accuracy: 6.67
aime2024_accuracy: 3.33
Mathbench_naive_average: 64.23
wikibench-wiki-single_choice_cncircular_perf_4: 31.32
cmmlu_naive_average: 74.3
Expand All @@ -322,7 +322,7 @@ internlm2_5-7b-chat-turbomind:
lcb_code_generation_pass@1: 17.75
lcb_code_execution_pass@1: 32.57
lcb_test_output_pass@1: 26.13
bigcodebench_hard_instruct_pass@1: 8.45
bigcodebench_hard_instruct_pass@1: 3.38
bigcodebench_hard_complete_pass@1: 5.06
teval_naive_average: 80
SciCode_sub_accuracy: 5.56
Expand Down Expand Up @@ -384,7 +384,7 @@ internlm2_5-7b-chat-turbomind:
college_knowledge_naive_average: 67.1
high_knowledge_naive_average: 70
middle_knowledge_naive_average: 80
primary_knowledge_naive_average: 87
primary_knowledge_naive_average: 90.12
mathbench-t (average)_naive_average: 76
subjective:
alignment_bench_v1_1_总分: 5.68
Expand All @@ -409,11 +409,11 @@ internlm2_5-7b-chat-turbomind:
alpaca_eval_koala: 28.21
alpaca_eval_oasst: 23.4
alpaca_eval_selfinstruct: 30.95
alpaca_eval_vicuna: 33.75
compassarena_language_naive_average: 58.50
alpaca_eval_vicuna: 25.00
compassarena_language_naive_average: 53.00
compassarena_knowledge_naive_average: 36
compassarena_reason_v2_naive_average: 35
compassarena_math_v2_naive_average: 25.95
compassarena_math_v2_naive_average: 16.07
compassarena_creationv2_zh_naive_average: 43.64
fofo_test_prompts_overall: 0.35
fofo_test_prompts_cn_overall: 0.41
Expand Down Expand Up @@ -524,7 +524,7 @@ qwen2.5-7b-instruct-turbomind:
humanevalx-python_pass@1: 50
humanevalx-cpp_pass@1: 42.07
humanevalx-go_pass@1: 0
humanevalx-java_pass@1: 74.39
humanevalx-java_pass@1: 53.05
humanevalx-js_pass@1: 75
ds1000_Pandas_accuracy: 14.09
ds1000_Numpy_accuracy: 8.18
Expand All @@ -548,7 +548,7 @@ qwen2.5-7b-instruct-turbomind:
openai_mmmlu_lite_SW-KE_accuracy: 36.42
openai_mmmlu_lite_YO-NG_accuracy: 32.14
openai_mmmlu_lite_ZH-CN_accuracy: 69.61
college_naive_average: 48
college_naive_average: 44.33
high_naive_average: 59
middle_naive_average: 78
primary_naive_average: 85.67
Expand Down Expand Up @@ -658,7 +658,7 @@ internlm2_5-7b-chat-pytorch:
college_naive_average: 21
high_naive_average: 47
middle_naive_average: 59.67
primary_naive_average: 76
primary_naive_average: 72.33
arithmetic_naive_average: 62
mathbench-a (average)_naive_average: 53.13
college_knowledge_naive_average: 68.99
Expand Down Expand Up @@ -688,7 +688,7 @@ qwen2.5-7b-instruct-pytorch:
gsm8k_accuracy: 91.66
GaokaoBench_weighted_average: 80.02
math_accuracy: 73.74
cmo_fib_accuracy: 26.44
cmo_fib_accuracy: 22.60
aime2024_accuracy: 13.33
Mathbench_naive_average: 77.08
wikibench-wiki-single_choice_cncircular_perf_4: 34
Expand Down Expand Up @@ -793,8 +793,8 @@ internlm3-8b-instruct-turbomind:
gsm8k_accuracy: 91.28
GaokaoBench_weighted_average: 86.59
math_accuracy: 76.96
cmo_fib_accuracy: 35.1
aime2024_accuracy: 16.67
cmo_fib_accuracy: 38.46
aime2024_accuracy: 13.33
Mathbench_naive_average: 78.96
wikibench-wiki-single_choice_cncircular_perf_4: 37.45
cmmlu_naive_average: 83.33
Expand Down Expand Up @@ -841,7 +841,7 @@ internlm3-8b-instruct-turbomind:
humanevalx-python_pass@1: 43.9
humanevalx-cpp_pass@1: 20.12
humanevalx-go_pass@1: 0
humanevalx-java_pass@1: 74.39
humanevalx-java_pass@1: 40.85
humanevalx-js_pass@1: 65.24
ds1000_Pandas_accuracy: 16.49
ds1000_Numpy_accuracy: 34.09
Expand Down Expand Up @@ -907,7 +907,7 @@ internlm3-8b-instruct-pytorch:
mmlu_pro_naive_average: 58.16
openai_humaneval_humaneval_pass@1: 82.32
sanitized_mbpp_score: 70.04
humanevalx_naive_average: 39.76
humanevalx_naive_average: 25.49
ds1000_naive_average: 27.84
lcb_code_generation_pass@1: 34.5
lcb_code_execution_pass@1: 48.02
Expand Down Expand Up @@ -946,7 +946,7 @@ internlm3-8b-instruct-pytorch:
humanevalx-python_pass@1: 42.68
humanevalx-cpp_pass@1: 19.51
humanevalx-go_pass@1: 0
humanevalx-java_pass@1: 72.56
humanevalx-java_pass@1: 0.00
humanevalx-js_pass@1: 64.02
ds1000_Pandas_accuracy: 14.09
ds1000_Numpy_accuracy: 35
Expand Down
Loading