Unverified Commit 86d5ec3d authored by Leymore's avatar Leymore Committed by GitHub
Browse files

Update configs (#9)

* Update implements

* Update
parent 2d0b184b
...@@ -2,7 +2,7 @@ from opencompass.openicl.icl_prompt_template import PromptTemplate ...@@ -2,7 +2,7 @@ from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import HFDataset from opencompass.datasets import HFDataset, gsm8k_postprocess, gsm8k_dataset_postprocess
gsm8k_reader_cfg = dict(input_columns=['question'], output_column='answer') gsm8k_reader_cfg = dict(input_columns=['question'], output_column='answer')
...@@ -26,8 +26,8 @@ gsm8k_infer_cfg = dict( ...@@ -26,8 +26,8 @@ gsm8k_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512)) inferencer=dict(type=GenInferencer, max_out_len=512))
gsm8k_eval_cfg = dict(evaluator=dict(type=AccEvaluator), gsm8k_eval_cfg = dict(evaluator=dict(type=AccEvaluator),
pred_postprocessor=dict(type='gsm8k'), pred_postprocessor=dict(type=gsm8k_postprocess),
dataset_postprocessor=dict(type='gsm8k_dataset')) dataset_postprocessor=dict(type=gsm8k_dataset_postprocess))
gsm8k_datasets = [ gsm8k_datasets = [
dict( dict(
......
...@@ -2,7 +2,7 @@ from opencompass.openicl.icl_prompt_template import PromptTemplate ...@@ -2,7 +2,7 @@ from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import HFDataset from opencompass.datasets import HFDataset, gsm8k_postprocess, gsm8k_dataset_postprocess
gsm8k_reader_cfg = dict(input_columns=['question'], output_column='answer') gsm8k_reader_cfg = dict(input_columns=['question'], output_column='answer')
...@@ -73,8 +73,8 @@ Question: {question}{answer} ...@@ -73,8 +73,8 @@ Question: {question}{answer}
gsm8k_eval_cfg = dict( gsm8k_eval_cfg = dict(
evaluator=dict(type=AccEvaluator), evaluator=dict(type=AccEvaluator),
pred_postprocessor=dict(type='gsm8k'), pred_postprocessor=dict(type=gsm8k_postprocess),
dataset_postprocessor=dict(type='gsm8k_dataset')) dataset_postprocessor=dict(type=gsm8k_dataset_postprocess))
gsm8k_datasets = [ gsm8k_datasets = [
dict( dict(
......
...@@ -2,7 +2,7 @@ from opencompass.openicl.icl_prompt_template import PromptTemplate ...@@ -2,7 +2,7 @@ from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import HFDataset from opencompass.datasets import HFDataset, gsm8k_postprocess, gsm8k_dataset_postprocess
gsm8k_reader_cfg = dict(input_columns=['question'], output_column='answer') gsm8k_reader_cfg = dict(input_columns=['question'], output_column='answer')
...@@ -36,8 +36,8 @@ gsm8k_infer_cfg = dict( ...@@ -36,8 +36,8 @@ gsm8k_infer_cfg = dict(
gsm8k_eval_cfg = dict(evaluator=dict(type=AccEvaluator), gsm8k_eval_cfg = dict(evaluator=dict(type=AccEvaluator),
pred_role="BOT", pred_role="BOT",
pred_postprocessor=dict(type='gsm8k'), pred_postprocessor=dict(type=gsm8k_postprocess),
dataset_postprocessor=dict(type='gsm8k_dataset')) dataset_postprocessor=dict(type=gsm8k_dataset_postprocess))
gsm8k_datasets = [ gsm8k_datasets = [
dict( dict(
......
...@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import ZeroRetriever ...@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import hellaswagDataset_V2 from opencompass.datasets import hellaswagDataset_V2
from opencompass.utils.text_postprocessors import first_capital_postprocess
hellaswag_reader_cfg = dict( hellaswag_reader_cfg = dict(
input_columns=["ctx", "A", "B", "C", "D"], input_columns=["ctx", "A", "B", "C", "D"],
...@@ -30,7 +31,7 @@ hellaswag_infer_cfg = dict( ...@@ -30,7 +31,7 @@ hellaswag_infer_cfg = dict(
hellaswag_eval_cfg = dict( hellaswag_eval_cfg = dict(
evaluator=dict(type=AccEvaluator), evaluator=dict(type=AccEvaluator),
pred_role="BOT", pred_role="BOT",
pred_postprocessor=dict(type="first-capital"), pred_postprocessor=dict(type=first_capital_postprocess),
) )
hellaswag_datasets = [ hellaswag_datasets = [
......
from opencompass.openicl.icl_prompt_template import PromptTemplate from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import HFDataset, HumanEvaluator from opencompass.datasets import HFDataset, HumanEvaluator, humaneval_postprocess
humaneval_reader_cfg = dict( humaneval_reader_cfg = dict(
input_columns=['prompt'], output_column='task_id', train_split='test') input_columns=['prompt'], output_column='task_id', train_split='test')
...@@ -27,7 +27,7 @@ humaneval_eval_cfg = dict( ...@@ -27,7 +27,7 @@ humaneval_eval_cfg = dict(
evaluator=dict(type=HumanEvaluator), evaluator=dict(type=HumanEvaluator),
pred_role='BOT', pred_role='BOT',
k=[1, 10, 100], # the parameter only for humaneval k=[1, 10, 100], # the parameter only for humaneval
pred_postprocessor=dict(type='humaneval'), pred_postprocessor=dict(type=humaneval_postprocess),
) )
humaneval_datasets = [ humaneval_datasets = [
......
from opencompass.openicl.icl_prompt_template import PromptTemplate from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import HFDataset, HumanEvaluator from opencompass.datasets import HFDataset, HumanEvaluator, humaneval_postprocess
humaneval_reader_cfg = dict( humaneval_reader_cfg = dict(
input_columns=['prompt'], output_column='task_id', train_split='test') input_columns=['prompt'], output_column='task_id', train_split='test')
...@@ -22,7 +22,7 @@ humaneval_eval_cfg = dict( ...@@ -22,7 +22,7 @@ humaneval_eval_cfg = dict(
evaluator=dict(type=HumanEvaluator), evaluator=dict(type=HumanEvaluator),
pred_role='BOT', pred_role='BOT',
k=[1, 10, 100], # the parameter only for humaneval k=[1, 10, 100], # the parameter only for humaneval
pred_postprocessor=dict(type='humaneval'), pred_postprocessor=dict(type=humaneval_postprocess),
) )
humaneval_datasets = [ humaneval_datasets = [
......
from opencompass.openicl.icl_prompt_template import PromptTemplate from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import HFDataset, HumanEvaluator from opencompass.datasets import HFDataset, HumanEvaluator, humaneval_postprocess
humaneval_reader_cfg = dict( humaneval_reader_cfg = dict(
input_columns=['prompt'], output_column='task_id', train_split='test') input_columns=['prompt'], output_column='task_id', train_split='test')
...@@ -17,7 +17,7 @@ humaneval_infer_cfg = dict( ...@@ -17,7 +17,7 @@ humaneval_infer_cfg = dict(
humaneval_eval_cfg = dict( humaneval_eval_cfg = dict(
evaluator=dict(type=HumanEvaluator), evaluator=dict(type=HumanEvaluator),
k=[1, 10, 100], # the parameter only for humaneval k=[1, 10, 100], # the parameter only for humaneval
pred_postprocessor=dict(type='humaneval'), pred_postprocessor=dict(type=humaneval_postprocess),
) )
humaneval_datasets = [ humaneval_datasets = [
......
from opencompass.openicl.icl_prompt_template import PromptTemplate from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import HFDataset, HumanEvaluator from opencompass.datasets import HFDataset, HumanEvaluator, humaneval_postprocess
humaneval_reader_cfg = dict( humaneval_reader_cfg = dict(
input_columns=['prompt'], output_column='task_id', train_split='test') input_columns=['prompt'], output_column='task_id', train_split='test')
...@@ -27,7 +27,7 @@ humaneval_eval_cfg = dict( ...@@ -27,7 +27,7 @@ humaneval_eval_cfg = dict(
evaluator=dict(type=HumanEvaluator), evaluator=dict(type=HumanEvaluator),
pred_role='BOT', pred_role='BOT',
k=[1, 10, 100], # the parameter only for humaneval k=[1, 10, 100], # the parameter only for humaneval
pred_postprocessor=dict(type='humaneval'), pred_postprocessor=dict(type=humaneval_postprocess),
) )
humaneval_datasets = [ humaneval_datasets = [
......
...@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import BM25Retriever ...@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import BM25Retriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import BleuEvaluator from opencompass.openicl.icl_evaluator import BleuEvaluator
from opencompass.datasets import IWSLT2017Dataset from opencompass.datasets import IWSLT2017Dataset
from opencompass.utils.text_postprocessors import general_cn_postprocess
iwslt2017_reader_cfg = dict( iwslt2017_reader_cfg = dict(
input_columns='en', output_column='de', train_split='validation') input_columns='en', output_column='de', train_split='validation')
...@@ -15,10 +16,10 @@ iwslt2017_infer_cfg = dict( ...@@ -15,10 +16,10 @@ iwslt2017_infer_cfg = dict(
inferencer=dict(type=GenInferencer)) inferencer=dict(type=GenInferencer))
iwslt2017_eval_cfg = dict( iwslt2017_eval_cfg = dict(
evaluator=dict(type=BleuEvaluator), evaluator=dict(type=BleuEvaluator),
pred_role='BOT', pred_role='BOT',
pred_postprocessor=dict(type='general_cn'), pred_postprocessor=dict(type=general_cn_postprocess),
dataset_postprocessor=dict(type='general_cn')) dataset_postprocessor=dict(type=general_cn_postprocess))
iwslt2017_datasets = [ iwslt2017_datasets = [
dict( dict(
...@@ -28,4 +29,4 @@ iwslt2017_datasets = [ ...@@ -28,4 +29,4 @@ iwslt2017_datasets = [
reader_cfg=iwslt2017_reader_cfg, reader_cfg=iwslt2017_reader_cfg,
infer_cfg=iwslt2017_infer_cfg, infer_cfg=iwslt2017_infer_cfg,
eval_cfg=iwslt2017_eval_cfg) eval_cfg=iwslt2017_eval_cfg)
] ]
\ No newline at end of file
...@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import BM25Retriever ...@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import BM25Retriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import BleuEvaluator from opencompass.openicl.icl_evaluator import BleuEvaluator
from opencompass.datasets import IWSLT2017Dataset from opencompass.datasets import IWSLT2017Dataset
from opencompass.utils.text_postprocessors import general_cn_postprocess
iwslt2017_reader_cfg = dict( iwslt2017_reader_cfg = dict(
input_columns='en', output_column='de', train_split='validation') input_columns='en', output_column='de', train_split='validation')
...@@ -24,10 +25,10 @@ iwslt2017_infer_cfg = dict( ...@@ -24,10 +25,10 @@ iwslt2017_infer_cfg = dict(
inferencer=dict(type=GenInferencer)) inferencer=dict(type=GenInferencer))
iwslt2017_eval_cfg = dict( iwslt2017_eval_cfg = dict(
evaluator=dict(type=BleuEvaluator), evaluator=dict(type=BleuEvaluator),
pred_role='BOT', pred_role='BOT',
pred_postprocessor=dict(type='general_cn'), pred_postprocessor=dict(type=general_cn_postprocess),
dataset_postprocessor=dict(type='general_cn')) dataset_postprocessor=dict(type=general_cn_postprocess))
iwslt2017_datasets = [ iwslt2017_datasets = [
dict( dict(
...@@ -37,4 +38,4 @@ iwslt2017_datasets = [ ...@@ -37,4 +38,4 @@ iwslt2017_datasets = [
reader_cfg=iwslt2017_reader_cfg, reader_cfg=iwslt2017_reader_cfg,
infer_cfg=iwslt2017_infer_cfg, infer_cfg=iwslt2017_infer_cfg,
eval_cfg=iwslt2017_eval_cfg) eval_cfg=iwslt2017_eval_cfg)
] ]
\ No newline at end of file
...@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import BM25Retriever ...@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import BM25Retriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import BleuEvaluator from opencompass.openicl.icl_evaluator import BleuEvaluator
from opencompass.datasets import IWSLT2017Dataset from opencompass.datasets import IWSLT2017Dataset
from opencompass.utils.text_postprocessors import general_cn_postprocess
iwslt2017_reader_cfg = dict( iwslt2017_reader_cfg = dict(
input_columns='en', output_column='de', train_split='validation') input_columns='en', output_column='de', train_split='validation')
...@@ -22,10 +23,10 @@ iwslt2017_infer_cfg = dict( ...@@ -22,10 +23,10 @@ iwslt2017_infer_cfg = dict(
inferencer=dict(type=GenInferencer)) inferencer=dict(type=GenInferencer))
iwslt2017_eval_cfg = dict( iwslt2017_eval_cfg = dict(
evaluator=dict(type=BleuEvaluator), evaluator=dict(type=BleuEvaluator),
pred_role='BOT', pred_role='BOT',
pred_postprocessor=dict(type='general_cn'), pred_postprocessor=dict(type=general_cn_postprocess),
dataset_postprocessor=dict(type='general_cn')) dataset_postprocessor=dict(type=general_cn_postprocess))
iwslt2017_datasets = [ iwslt2017_datasets = [
dict( dict(
...@@ -35,4 +36,4 @@ iwslt2017_datasets = [ ...@@ -35,4 +36,4 @@ iwslt2017_datasets = [
reader_cfg=iwslt2017_reader_cfg, reader_cfg=iwslt2017_reader_cfg,
infer_cfg=iwslt2017_infer_cfg, infer_cfg=iwslt2017_infer_cfg,
eval_cfg=iwslt2017_eval_cfg) eval_cfg=iwslt2017_eval_cfg)
] ]
\ No newline at end of file
...@@ -33,8 +33,8 @@ for _l in lang: ...@@ -33,8 +33,8 @@ for _l in lang:
dict( dict(
abbr=f'jigsaw_multilingual_{_l}', abbr=f'jigsaw_multilingual_{_l}',
type=JigsawMultilingualDataset, type=JigsawMultilingualDataset,
path='data/test.csv', path='data/jigsawmultilingual/test.csv',
label='data/test_labels.csv', label='data/jigsawmultilingual/test_labels.csv',
lang=_l, lang=_l,
reader_cfg=jigsawmultilingual_reader_cfg, reader_cfg=jigsawmultilingual_reader_cfg,
infer_cfg=jigsawmultilingual_infer_cfg, infer_cfg=jigsawmultilingual_infer_cfg,
......
...@@ -37,8 +37,8 @@ for _l in lang: ...@@ -37,8 +37,8 @@ for _l in lang:
dict( dict(
abbr=f'jigsaw_multilingual_{_l}', abbr=f'jigsaw_multilingual_{_l}',
type=JigsawMultilingualDataset, type=JigsawMultilingualDataset,
path='data/test.csv', path='data/jigsawmultilingual/test.csv',
label='data/test_labels.csv', label='data/jigsawmultilingual/test_labels.csv',
lang=_l, lang=_l,
reader_cfg=jigsawmultilingual_reader_cfg, reader_cfg=jigsawmultilingual_reader_cfg,
infer_cfg=jigsawmultilingual_infer_cfg, infer_cfg=jigsawmultilingual_infer_cfg,
......
...@@ -2,7 +2,7 @@ from opencompass.openicl.icl_prompt_template import PromptTemplate ...@@ -2,7 +2,7 @@ from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import RougeEvaluator from opencompass.openicl.icl_evaluator import RougeEvaluator
from opencompass.datasets import LCSTSDataset from opencompass.datasets import LCSTSDataset, lcsts_postprocess
lcsts_reader_cfg = dict(input_columns=['content'], output_column='abst') lcsts_reader_cfg = dict(input_columns=['content'], output_column='abst')
...@@ -18,7 +18,7 @@ lcsts_infer_cfg = dict( ...@@ -18,7 +18,7 @@ lcsts_infer_cfg = dict(
lcsts_eval_cfg = dict( lcsts_eval_cfg = dict(
evaluator=dict(type=RougeEvaluator), evaluator=dict(type=RougeEvaluator),
pred_role='BOT', pred_role='BOT',
pred_postprocessor=dict(type='lcsts'), pred_postprocessor=dict(type=lcsts_postprocess),
) )
lcsts_datasets = [ lcsts_datasets = [
......
...@@ -2,7 +2,7 @@ from opencompass.openicl.icl_prompt_template import PromptTemplate ...@@ -2,7 +2,7 @@ from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import RougeEvaluator from opencompass.openicl.icl_evaluator import RougeEvaluator
from opencompass.datasets import LCSTSDataset from opencompass.datasets import LCSTSDataset, lcsts_postprocess
lcsts_reader_cfg = dict(input_columns=['content'], output_column='abst') lcsts_reader_cfg = dict(input_columns=['content'], output_column='abst')
...@@ -14,7 +14,7 @@ lcsts_infer_cfg = dict( ...@@ -14,7 +14,7 @@ lcsts_infer_cfg = dict(
lcsts_eval_cfg = dict( lcsts_eval_cfg = dict(
evaluator=dict(type=RougeEvaluator), evaluator=dict(type=RougeEvaluator),
pred_postprocessor=dict(type='lcsts'), pred_postprocessor=dict(type=lcsts_postprocess),
) )
lcsts_datasets = [ lcsts_datasets = [
......
from mmengine.config import read_base from mmengine.config import read_base
with read_base(): with read_base():
from .math_gen_3e92f6 import math_datasets # noqa: F401, F403 from .math_gen_265cce import math_datasets # noqa: F401, F403
from opencompass.openicl.icl_prompt_template import PromptTemplate from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MATHDataset, MATHEvaluator from opencompass.datasets import MATHDataset, MATHEvaluator, math_postprocess
math_reader_cfg = dict(input_columns=['problem'], output_column='solution') math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
...@@ -12,12 +12,12 @@ math_infer_cfg = dict( ...@@ -12,12 +12,12 @@ math_infer_cfg = dict(
dict( dict(
role="HUMAN", role="HUMAN",
prompt= prompt=
"Problem:\nFind the domain of the expression $\frac{{\sqrt{{x-2}}}}{{\sqrt{{5-x}}}}$.}}\nSolution:" "Problem:\nFind the domain of the expression $\\frac{{\sqrt{{x-2}}}}{{\sqrt{{5-x}}}}$.}}\nSolution:"
), ),
dict( dict(
role="BOT", role="BOT",
prompt= prompt=
"The expressions inside each square root must be non-negative. Therefore, $x-2 \ge 0$, so $x\ge2$, and $5 - x \ge 0$, so $x \le 5$. Also, the denominator cannot be equal to zero, so $5-x>0$, which gives $x<5$. Therefore, the domain of the expression is $\boxed{{[2,5)}}$.\nFinal Answer: The final answer is $[2,5)$. I hope it is correct." "The expressions inside each square root must be non-negative. Therefore, $x-2 \ge 0$, so $x\ge2$, and $5 - x \ge 0$, so $x \le 5$. Also, the denominator cannot be equal to zero, so $5-x>0$, which gives $x<5$. Therefore, the domain of the expression is $\\boxed{{[2,5)}}$.\nFinal Answer: The final answer is $[2,5)$. I hope it is correct.\n"
), ),
dict( dict(
role="HUMAN", role="HUMAN",
...@@ -27,7 +27,7 @@ math_infer_cfg = dict( ...@@ -27,7 +27,7 @@ math_infer_cfg = dict(
dict( dict(
role="BOT", role="BOT",
prompt= prompt=
"We have that $\det (\mathbf{{A}} \mathbf{{B}}) = (\det \mathbf{{A}})(\det \mathbf{{B}}) = (2)(12) = \boxed{{24}}.$\nFinal Answer: The final answer is $24$. I hope it is correct." "We have that $\det (\mathbf{{A}} \mathbf{{B}}) = (\det \mathbf{{A}})(\det \mathbf{{B}}) = (2)(12) = \\boxed{{24}}.$\nFinal Answer: The final answer is $24$. I hope it is correct.\n"
), ),
dict( dict(
role="HUMAN", role="HUMAN",
...@@ -37,17 +37,17 @@ math_infer_cfg = dict( ...@@ -37,17 +37,17 @@ math_infer_cfg = dict(
dict( dict(
role="BOT", role="BOT",
prompt= prompt=
"If Terrell lifts two 20-pound weights 12 times, he lifts a total of $2\cdot 12\cdot20=480$ pounds of weight. If he lifts two 15-pound weights instead for $n$ times, he will lift a total of $2\cdot15\cdot n=30n$ pounds of weight. Equating this to 480 pounds, we can solve for $n$: \begin{{align*}} 30n&=480\\ \Rightarrow\qquad n&=480/30=\boxed{{16}} \end{{align*}}\nFinal Answer: The final answer is $16$. I hope it is correct." "If Terrell lifts two 20-pound weights 12 times, he lifts a total of $2\cdot 12\cdot20=480$ pounds of weight. If he lifts two 15-pound weights instead for $n$ times, he will lift a total of $2\cdot15\cdot n=30n$ pounds of weight. Equating this to 480 pounds, we can solve for $n$: \\begin{{align*}} 30n&=480\\\\ \Rightarrow\qquad n&=480/30=\\boxed{{16}} \end{{align*}}\nFinal Answer: The final answer is $16$. I hope it is correct.\n"
), ),
dict( dict(
role="HUMAN", role="HUMAN",
prompt= prompt=
"Problem:\nIf the system of equations: \begin{{align*}} 6x-4y&=a,\\ 6y-9x &=b. \end{{align*}}has a solution $(x, y)$ where $x$ and $y$ are both nonzero, find $\frac{{a}}{{b}},$ assuming $b$ is nonzero.\nSolution:" "Problem:\nIf the system of equations: \\begin{{align*}} 6x-4y&=a,\\\\ 6y-9x &=b. \end{{align*}}has a solution $(x, y)$ where $x$ and $y$ are both nonzero, find $\\frac{{a}}{{b}},$ assuming $b$ is nonzero.\nSolution:"
), ),
dict( dict(
role="BOT", role="BOT",
prompt= prompt=
"If we multiply the first equation by $-\frac{{3}}{{2}}$, we obtain $$6y-9x=-\frac{{3}}{{2}}a.$$Since we also know that $6y-9x=b$, we have $$-\frac{{3}}{{2}}a=b\Rightarrow\frac{{a}}{{b}}=\boxed{{-\frac{{2}}{{3}}}}.$$\nFinal Answer: The final answer is $-\frac{{2}}{{3}}$. I hope it is correct." "If we multiply the first equation by $-\\frac{{3}}{{2}}$, we obtain $$6y-9x=-\\frac{{3}}{{2}}a.$$Since we also know that $6y-9x=b$, we have $$-\\frac{{3}}{{2}}a=b\Rightarrow\\frac{{a}}{{b}}=\\boxed{{-\\frac{{2}}{{3}}}}.$$\nFinal Answer: The final answer is $-\\frac{{2}}{{3}}$. I hope it is correct.\n"
), ),
dict(role="HUMAN", prompt="Problem:\n{problem}\nSolution:\n"), dict(role="HUMAN", prompt="Problem:\n{problem}\nSolution:\n"),
])), ])),
...@@ -55,7 +55,7 @@ math_infer_cfg = dict( ...@@ -55,7 +55,7 @@ math_infer_cfg = dict(
inferencer=dict(type=GenInferencer, max_out_len=512)) inferencer=dict(type=GenInferencer, max_out_len=512))
math_eval_cfg = dict( math_eval_cfg = dict(
evaluator=dict(type=MATHEvaluator), pred_postprocessor=dict(type='math')) evaluator=dict(type=MATHEvaluator), pred_postprocessor=dict(type=math_postprocess))
math_datasets = [ math_datasets = [
dict( dict(
......
from opencompass.openicl.icl_prompt_template import PromptTemplate from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MATHDataset, MATHEvaluator from opencompass.datasets import MATHDataset, MATHEvaluator, math_postprocess
math_reader_cfg = dict(input_columns=['problem'], output_column='solution') math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
...@@ -9,28 +9,28 @@ math_infer_cfg = dict( ...@@ -9,28 +9,28 @@ math_infer_cfg = dict(
prompt_template=dict( prompt_template=dict(
type=PromptTemplate, type=PromptTemplate,
template='''Problem: template='''Problem:
Find the domain of the expression $\frac{{\sqrt{{x-2}}}}{{\sqrt{{5-x}}}}$.}} Find the domain of the expression $\\frac{{\sqrt{{x-2}}}}{{\sqrt{{5-x}}}}$.}}
Solution: Solution:
The expressions inside each square root must be non-negative. Therefore, $x-2 \ge 0$, so $x\ge2$, and $5 - x \ge 0$, so $x \le 5$. Also, the denominator cannot be equal to zero, so $5-x>0$, which gives $x<5$. Therefore, the domain of the expression is $\boxed{{[2,5)}}$. The expressions inside each square root must be non-negative. Therefore, $x-2 \ge 0$, so $x\ge2$, and $5 - x \ge 0$, so $x \le 5$. Also, the denominator cannot be equal to zero, so $5-x>0$, which gives $x<5$. Therefore, the domain of the expression is $\\boxed{{[2,5)}}$.
Final Answer: The final answer is $[2,5)$. I hope it is correct. Final Answer: The final answer is $[2,5)$. I hope it is correct.
Problem: Problem:
If $\det \mathbf{{A}} = 2$ and $\det \mathbf{{B}} = 12,$ then find $\det (\mathbf{{A}} \mathbf{{B}}).$ If $\det \mathbf{{A}} = 2$ and $\det \mathbf{{B}} = 12,$ then find $\det (\mathbf{{A}} \mathbf{{B}}).$
Solution: Solution:
We have that $\det (\mathbf{{A}} \mathbf{{B}}) = (\det \mathbf{{A}})(\det \mathbf{{B}}) = (2)(12) = \boxed{{24}}.$ We have that $\det (\mathbf{{A}} \mathbf{{B}}) = (\det \mathbf{{A}})(\det \mathbf{{B}}) = (2)(12) = \\boxed{{24}}.$
Final Answer: The final answer is $24$. I hope it is correct. Final Answer: The final answer is $24$. I hope it is correct.
Problem: Problem:
Terrell usually lifts two 20-pound weights 12 times. If he uses two 15-pound weights instead, how many times must Terrell lift them in order to lift the same total weight? Terrell usually lifts two 20-pound weights 12 times. If he uses two 15-pound weights instead, how many times must Terrell lift them in order to lift the same total weight?
Solution: Solution:
If Terrell lifts two 20-pound weights 12 times, he lifts a total of $2\cdot 12\cdot20=480$ pounds of weight. If he lifts two 15-pound weights instead for $n$ times, he will lift a total of $2\cdot15\cdot n=30n$ pounds of weight. Equating this to 480 pounds, we can solve for $n$: \begin{{align*}} 30n&=480\\ \Rightarrow\qquad n&=480/30=\boxed{{16}} \end{{align*}} If Terrell lifts two 20-pound weights 12 times, he lifts a total of $2\cdot 12\cdot20=480$ pounds of weight. If he lifts two 15-pound weights instead for $n$ times, he will lift a total of $2\cdot15\cdot n=30n$ pounds of weight. Equating this to 480 pounds, we can solve for $n$: \\begin{{align*}} 30n&=480\\\\ \Rightarrow\qquad n&=480/30=\\boxed{{16}} \end{{align*}}
Final Answer: The final answer is $16$. I hope it is correct. Final Answer: The final answer is $16$. I hope it is correct.
Problem: Problem:
If the system of equations: \begin{{align*}} 6x-4y&=a,\\ 6y-9x &=b. \end{{align*}}has a solution $(x, y)$ where $x$ and $y$ are both nonzero, find $\frac{{a}}{{b}},$ assuming $b$ is nonzero. If the system of equations: \\begin{{align*}} 6x-4y&=a,\\\\ 6y-9x &=b. \end{{align*}}has a solution $(x, y)$ where $x$ and $y$ are both nonzero, find $\\frac{{a}}{{b}},$ assuming $b$ is nonzero.
Solution: Solution:
If we multiply the first equation by $-\frac{{3}}{{2}}$, we obtain $$6y-9x=-\frac{{3}}{{2}}a.$$Since we also know that $6y-9x=b$, we have $$-\frac{{3}}{{2}}a=b\Rightarrow\frac{{a}}{{b}}=\boxed{{-\frac{{2}}{{3}}}}.$$ If we multiply the first equation by $-\\frac{{3}}{{2}}$, we obtain $$6y-9x=-\\frac{{3}}{{2}}a.$$Since we also know that $6y-9x=b$, we have $$-\\frac{{3}}{{2}}a=b\Rightarrow\\frac{{a}}{{b}}=\\boxed{{-\\frac{{2}}{{3}}}}.$$
Final Answer: The final answer is $-\frac{{2}}{{3}}$. I hope it is correct. Final Answer: The final answer is $-\\frac{{2}}{{3}}$. I hope it is correct.
Problem: Problem:
{problem} {problem}
...@@ -40,7 +40,7 @@ Solution: ...@@ -40,7 +40,7 @@ Solution:
inferencer=dict(type=GenInferencer, max_out_len=512)) inferencer=dict(type=GenInferencer, max_out_len=512))
math_eval_cfg = dict( math_eval_cfg = dict(
evaluator=dict(type=MATHEvaluator), pred_postprocessor=dict(type='math')) evaluator=dict(type=MATHEvaluator), pred_postprocessor=dict(type=math_postprocess))
math_datasets = [ math_datasets = [
dict( dict(
......
from opencompass.openicl.icl_prompt_template import PromptTemplate from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MATHDataset, MATHEvaluator from opencompass.datasets import MATHDataset, MATHEvaluator, math_postprocess
math_infer_cfg = dict( math_infer_cfg = dict(
prompt_template=dict( prompt_template=dict(
type=PromptTemplate, type=PromptTemplate,
template='''Problem: template='''Problem:
Find the domain of the expression $\frac{{\sqrt{{x-2}}}}{{\sqrt{{5-x}}}}$.}} Find the domain of the expression $\\frac{{\sqrt{{x-2}}}}{{\sqrt{{5-x}}}}$.}}
Solution: Solution:
The expressions inside each square root must be non-negative. Therefore, $x-2 \ge 0$, so $x\ge2$, and $5 - x \ge 0$, so $x \le 5$. Also, the denominator cannot be equal to zero, so $5-x>0$, which gives $x<5$. Therefore, the domain of the expression is $\boxed{{[2,5)}}$. The expressions inside each square root must be non-negative. Therefore, $x-2 \ge 0$, so $x\ge2$, and $5 - x \ge 0$, so $x \le 5$. Also, the denominator cannot be equal to zero, so $5-x>0$, which gives $x<5$. Therefore, the domain of the expression is $\\boxed{{[2,5)}}$.
Final Answer: The final answer is $[2,5)$. I hope it is correct. Final Answer: The final answer is $[2,5)$. I hope it is correct.
Problem: Problem:
If $\det \mathbf{{A}} = 2$ and $\det \mathbf{{B}} = 12,$ then find $\det (\mathbf{{A}} \mathbf{{B}}).$ If $\det \mathbf{{A}} = 2$ and $\det \mathbf{{B}} = 12,$ then find $\det (\mathbf{{A}} \mathbf{{B}}).$
Solution: Solution:
We have that $\det (\mathbf{{A}} \mathbf{{B}}) = (\det \mathbf{{A}})(\det \mathbf{{B}}) = (2)(12) = \boxed{{24}}.$ We have that $\det (\mathbf{{A}} \mathbf{{B}}) = (\det \mathbf{{A}})(\det \mathbf{{B}}) = (2)(12) = \\boxed{{24}}.$
Final Answer: The final answer is $24$. I hope it is correct. Final Answer: The final answer is $24$. I hope it is correct.
Problem: Problem:
Terrell usually lifts two 20-pound weights 12 times. If he uses two 15-pound weights instead, how many times must Terrell lift them in order to lift the same total weight? Terrell usually lifts two 20-pound weights 12 times. If he uses two 15-pound weights instead, how many times must Terrell lift them in order to lift the same total weight?
Solution: Solution:
If Terrell lifts two 20-pound weights 12 times, he lifts a total of $2\cdot 12\cdot20=480$ pounds of weight. If he lifts two 15-pound weights instead for $n$ times, he will lift a total of $2\cdot15\cdot n=30n$ pounds of weight. Equating this to 480 pounds, we can solve for $n$: \begin{{align*}} 30n&=480\\ \Rightarrow\qquad n&=480/30=\boxed{{16}} \end{{align*}} If Terrell lifts two 20-pound weights 12 times, he lifts a total of $2\cdot 12\cdot20=480$ pounds of weight. If he lifts two 15-pound weights instead for $n$ times, he will lift a total of $2\cdot15\cdot n=30n$ pounds of weight. Equating this to 480 pounds, we can solve for $n$: \\begin{{align*}} 30n&=480\\\\ \Rightarrow\qquad n&=480/30=\\boxed{{16}} \end{{align*}}
Final Answer: The final answer is $16$. I hope it is correct. Final Answer: The final answer is $16$. I hope it is correct.
Problem: Problem:
If the system of equations: \begin{{align*}} 6x-4y&=a,\\ 6y-9x &=b. \end{{align*}}has a solution $(x, y)$ where $x$ and $y$ are both nonzero, find $\frac{{a}}{{b}},$ assuming $b$ is nonzero. If the system of equations: \\begin{{align*}} 6x-4y&=a,\\\\ 6y-9x &=b. \end{{align*}}has a solution $(x, y)$ where $x$ and $y$ are both nonzero, find $\\frac{{a}}{{b}},$ assuming $b$ is nonzero.
Solution: Solution:
If we multiply the first equation by $-\frac{{3}}{{2}}$, we obtain $$6y-9x=-\frac{{3}}{{2}}a.$$Since we also know that $6y-9x=b$, we have $$-\frac{{3}}{{2}}a=b\Rightarrow\frac{{a}}{{b}}=\boxed{{-\frac{{2}}{{3}}}}.$$ If we multiply the first equation by $-\\frac{{3}}{{2}}$, we obtain $$6y-9x=-\\frac{{3}}{{2}}a.$$Since we also know that $6y-9x=b$, we have $$-\\frac{{3}}{{2}}a=b\Rightarrow\\frac{{a}}{{b}}=\\boxed{{-\\frac{{2}}{{3}}}}.$$
Final Answer: The final answer is $-\frac{{2}}{{3}}$. I hope it is correct. Final Answer: The final answer is $-\\frac{{2}}{{3}}$. I hope it is correct.
Problem: Problem:
{problem}Solution: {problem}Solution:
...@@ -37,7 +37,7 @@ Problem: ...@@ -37,7 +37,7 @@ Problem:
inferencer=dict(type=GenInferencer, max_out_len=512)) inferencer=dict(type=GenInferencer, max_out_len=512))
math_eval_cfg = dict( math_eval_cfg = dict(
evaluator=dict(type=MATHEvaluator), pred_postprocessor=dict(type='math')) evaluator=dict(type=MATHEvaluator), pred_postprocessor=dict(type=math_postprocess))
math_datasets = [ math_datasets = [
dict( dict(
......
...@@ -4,7 +4,7 @@ from opencompass.openicl.icl_inferencer import GenInferencer ...@@ -4,7 +4,7 @@ from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MBPPDataset, MBPPEvaluator from opencompass.datasets import MBPPDataset, MBPPEvaluator
mbpp_reader_cfg = dict( mbpp_reader_cfg = dict(
input_columns=['text', 'test_list'], output_column='code') input_columns=['text', 'test_list'], output_column='test_list_2')
mbpp_infer_cfg = dict( mbpp_infer_cfg = dict(
prompt_template=dict( prompt_template=dict(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment