Skip to content

Commit

Permalink
[Sync] Updata dataset cfg for internMath (#837)
Browse files Browse the repository at this point in the history
Co-authored-by: liuhongwei <[email protected]>
  • Loading branch information
Leymore and liuhongwei committed Jan 24, 2024
1 parent f7d7837 commit 0991dd3
Show file tree
Hide file tree
Showing 6 changed files with 473 additions and 0 deletions.
33 changes: 33 additions & 0 deletions configs/datasets/gsm8k/gsm8k_gen_701491.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import GSM8KDataset, gsm8k_postprocess, gsm8k_dataset_postprocess, Gsm8kEvaluator

gsm8k_reader_cfg = dict(input_columns=['question'], output_column='answer')

gsm8k_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[
dict(role='HUMAN', prompt="Question: {question}\nLet's think step by step\nAnswer:")
],
)),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=512))

gsm8k_eval_cfg = dict(evaluator=dict(type=Gsm8kEvaluator),
pred_role="BOT",
pred_postprocessor=dict(type=gsm8k_postprocess),
dataset_postprocessor=dict(type=gsm8k_dataset_postprocess))

gsm8k_datasets = [
dict(
abbr='gsm8k',
type=GSM8KDataset,
path='./data/gsm8k',
reader_cfg=gsm8k_reader_cfg,
infer_cfg=gsm8k_infer_cfg,
eval_cfg=gsm8k_eval_cfg)
]
68 changes: 68 additions & 0 deletions configs/datasets/math/math_gen_0957ff.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,68 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MATHDataset, MATHEvaluator, math_postprocess

math_reader_cfg = dict(input_columns=['problem'], output_column='solution')

math_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(
role="HUMAN",
prompt=
"Problem:\nFind the domain of the expression $\\frac{\sqrt{x-2}}{\sqrt{5-x}}$.}\nSolution:"
),
dict(
role="BOT",
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.\n"
),
dict(
role="HUMAN",
prompt=
"Problem:\nIf $\det \mathbf{A} = 2$ and $\det \mathbf{B} = 12,$ then find $\det (\mathbf{A} \mathbf{B}).$\nSolution:"
),
dict(
role="BOT",
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.\n"
),
dict(
role="HUMAN",
prompt=
"Problem:\nTerrell 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?\nSolution:"
),
dict(
role="BOT",
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.\n"
),
dict(
role="HUMAN",
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:"
),
dict(
role="BOT",
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.\n"
),
dict(role="HUMAN", prompt="Problem:\n{problem}\nSolution:\n"),
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=512))

math_eval_cfg = dict(
evaluator=dict(type=MATHEvaluator), pred_postprocessor=dict(type=math_postprocess))

math_datasets = [
dict(
type=MATHDataset,
abbr='math',
path='./data/math/math.json',
reader_cfg=math_reader_cfg,
infer_cfg=math_infer_cfg,
eval_cfg=math_eval_cfg)
]
28 changes: 28 additions & 0 deletions configs/datasets/math/math_gen_736506.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.datasets import MATHInternDataset, MATHInternEvaluator, math_intern_postprocess

math_reader_cfg = dict(input_columns=['problem'], output_column='solution')

math_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(round=[
dict(role='HUMAN', prompt="Question: {problem}\nLet's think step by step\nAnswer:")
])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=512))

math_eval_cfg = dict(
evaluator=dict(type=MATHInternEvaluator), pred_postprocessor=dict(type=math_intern_postprocess))

math_datasets = [
dict(
type=MATHInternDataset,
abbr='math',
path='./data/math/math.json',
reader_cfg=math_reader_cfg,
infer_cfg=math_infer_cfg,
eval_cfg=math_eval_cfg)
]
1 change: 1 addition & 0 deletions opencompass/datasets/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,7 @@
from .mastermath2024v1 import * # noqa: F401, F403
from .math import * # noqa: F401, F403
from .math401 import * # noqa: F401, F403
from .math_intern import * # noqa: F401, F403
from .mathbench import * # noqa: F401, F403
from .mbpp import * # noqa: F401, F403
from .medbench import * # noqa: F401, F403
Expand Down
Loading

0 comments on commit 0991dd3

Please sign in to comment.