Hugging Face's logo

Datasets:
Lansechen
/
details_Lansechen__Qwen2.5-3B-Open-R1-GRPO-math-selected-cosine-noRW

Modalities:
Tabular
Text
Formats:
parquet
Size:
< 1K
Libraries:
Datasets
pandas
Dataset card Data Studio Files Community
1
Dataset Viewer
Auto-converted to Parquet
choices
sequencelengths
0
0
cont_tokens
sequencelengths
1
1
example
stringlengths
444
1.27k
full_prompt
stringlengths
800
1.62k
gold
sequencelengths
1
1
gold_index
sequencelengths
0
0
input_tokens
sequencelengths
1
1
instruction
stringclasses
1 value
metrics
dict
num_asked_few_shots
int64
0
0
num_effective_few_shots
int64
0
0
padded
sequencelengths
1
1
pred_logits
sequencelengths
0
0
prediction_logits
sequencelengths
0
0
predictions
sequencelengths
1
32
specifics
dict
truncated
sequencelengths
1
1
[]
[[[1249,11625,279,2661,3491,11,582,1191,553,26305,429,1124,11520,32696,57758,374,264,220,16,18,339,3(...TRUNCATED)
"Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED)
"<|im_start|>system\nYou are a helpful AI Assistant that provides well-reasoned and detailed respons(...TRUNCATED)
[ "321" ]
[]
[[151644,8948,198,2610,525,264,10950,15235,21388,429,5707,1632,5504,1497,291,323,11682,14507,13,1446(...TRUNCATED)
{ "extractive_match": null, "math_pass@1:32_samples": 0 }
0
0
[ 0 ]
[]
[]
["To solve the given problem, we start by noting that \\(\\omega\\) is a 13th root of unity, so \\(\(...TRUNCATED)
null
[ 0 ]
[]
[[[1249,11625,279,3491,11,582,1191,553,26305,429,279,17071,65,7924,374,2661,553,1124,11520,37018,453(...TRUNCATED)
"Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED)
"<|im_start|>system\nYou are a helpful AI Assistant that provides well-reasoned and detailed respons(...TRUNCATED)
[ "480" ]
[]
[[151644,8948,198,2610,525,264,10950,15235,21388,429,5707,1632,5504,1497,291,323,11682,14507,13,1446(...TRUNCATED)
{ "extractive_match": null, "math_pass@1:32_samples": 0 }
0
0
[ 0 ]
[]
[]
["To solve the problem, we start by noting that the hyperbola is given by \\(\\frac{x^2}{20} - \\fra(...TRUNCATED)
null
[ 0 ]
[]
[[[1249,11625,369,279,3084,315,17767,2104,59,701,582,1191,553,26305,429,17767,32,11,422,11,472,11,47(...TRUNCATED)
"Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED)
"<|im_start|>system\nYou are a helpful AI Assistant that provides well-reasoned and detailed respons(...TRUNCATED)
[ "104" ]
[]
[[151644,8948,198,2610,525,264,10950,15235,21388,429,5707,1632,5504,1497,291,323,11682,14507,13,1446(...TRUNCATED)
{ "extractive_match": null, "math_pass@1:32_samples": 0 }
0
0
[ 0 ]
[]
[]
["To solve for the length of \\(CE\\), we start by noting that \\(A, D, H, G\\) lie on a circle, whi(...TRUNCATED)
null
[ 0 ]
[]
[[[1249,11625,419,3491,11,582,1184,311,3535,279,5025,1948,279,738,17767,32,57758,323,279,7289,17767,(...TRUNCATED)
"Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED)
"<|im_start|>system\nYou are a helpful AI Assistant that provides well-reasoned and detailed respons(...TRUNCATED)
[ "055" ]
[]
[[151644,8948,198,2610,525,264,10950,15235,21388,429,5707,1632,5504,1497,291,323,11682,14507,13,1446(...TRUNCATED)
{ "extractive_match": null, "math_pass@1:32_samples": 0 }
0
0
[ 0 ]
[]
[]
["To solve this problem, we need to understand the relationship between the set \\(A\\) and the sets(...TRUNCATED)
null
[ 0 ]
[]
[[[1249,11625,279,3491,11,582,1184,311,9245,264,1140,315,6785,25780,429,67901,279,2661,4682,13,6771,(...TRUNCATED)
"Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED)
"<|im_start|>system\nYou are a helpful AI Assistant that provides well-reasoned and detailed respons(...TRUNCATED)
[ "236" ]
[]
[[151644,8948,198,2610,525,264,10950,15235,21388,429,5707,1632,5504,1497,291,323,11682,14507,13,1446(...TRUNCATED)
{ "extractive_match": null, "math_pass@1:32_samples": 0 }
0
0
[ 0 ]
[]
[]
["To solve the problem, we need to construct a list of positive integers that satisfies the given co(...TRUNCATED)
null
[ 0 ]
[]
[[[1249,11625,279,3491,11,582,1191,553,20194,279,15336,315,279,51424,3745,387,17767,64,59,701,17767,(...TRUNCATED)
"Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED)
"<|im_start|>system\nYou are a helpful AI Assistant that provides well-reasoned and detailed respons(...TRUNCATED)
[ "721" ]
[]
[[151644,8948,198,2610,525,264,10950,15235,21388,429,5707,1632,5504,1497,291,323,11682,14507,13,1446(...TRUNCATED)
{ "extractive_match": null, "math_pass@1:32_samples": 0 }
0
0
[ 0 ]
[]
[]
["To solve the problem, we start by letting the dimensions of the rectangular box be \\(a\\), \\(b\\(...TRUNCATED)
null
[ 0 ]
[]
[[[1249,11625,279,3491,11,582,1184,311,1477,279,6010,504,279,1459,17767,40,57758,311,1817,315,279,12(...TRUNCATED)
"Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED)
"<|im_start|>system\nYou are a helpful AI Assistant that provides well-reasoned and detailed respons(...TRUNCATED)
[ "104" ]
[]
[[151644,8948,198,2610,525,264,10950,15235,21388,429,5707,1632,5504,1497,291,323,11682,14507,13,1446(...TRUNCATED)
{ "extractive_match": null, "math_pass@1:32_samples": 0 }
0
0
[ 0 ]
[]
[]
["To solve the problem, we need to find the distance from the point \\(I\\) to each of the faces of (...TRUNCATED)
null
[ 0 ]
[]
[[[1249,1477,279,7772,3204,1931,949,315,279,7493,1124,1188,22,20,10,16,16,22,72,8,89,488,1124,37018,(...TRUNCATED)
"Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED)
"<|im_start|>system\nYou are a helpful AI Assistant that provides well-reasoned and detailed respons(...TRUNCATED)
[ "540" ]
[]
[[151644,8948,198,2610,525,264,10950,15235,21388,429,5707,1632,5504,1497,291,323,11682,14507,13,1446(...TRUNCATED)
{ "extractive_match": null, "math_pass@1:32_samples": 0.4062499999999999 }
0
0
[ 0 ]
[]
[]
["To find the largest possible real part of the expression \\((75+117i)z + \\frac{96+144i}{z}\\) whe(...TRUNCATED)
null
[ 0 ]
[]
[[[1249,11625,279,3491,11,582,1184,311,1760,279,1372,315,12716,315,3084,220,16,21,429,2297,5106,6896(...TRUNCATED)
"Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED)
"<|im_start|>system\nYou are a helpful AI Assistant that provides well-reasoned and detailed respons(...TRUNCATED)
[ "294" ]
[]
[[151644,8948,198,2610,525,264,10950,15235,21388,429,5707,1632,5504,1497,291,323,11682,14507,13,1446(...TRUNCATED)
{ "extractive_match": null, "math_pass@1:32_samples": 0 }
0
0
[ 0 ]
[]
[]
["To solve the problem, we need to count the number of paths of length 16 that change direction exac(...TRUNCATED)
null
[ 0 ]
[]
[[[1249,11625,419,3491,11,582,686,990,279,17508,315,27187,10187,8957,13,6771,594,6979,279,2701,7289,(...TRUNCATED)
"Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED)
"<|im_start|>system\nYou are a helpful AI Assistant that provides well-reasoned and detailed respons(...TRUNCATED)
[ "073" ]
[]
[[151644,8948,198,2610,525,264,10950,15235,21388,429,5707,1632,5504,1497,291,323,11682,14507,13,1446(...TRUNCATED)
{ "extractive_match": null, "math_pass@1:32_samples": 0 }
0
0
[ 0 ]
[]
[]
["To solve this problem, we will use the principle of inclusion-exclusion. Let's define the followin(...TRUNCATED)
null
[ 0 ]
End of preview. Expand in Data Studio

Dataset Card for Evaluation run of Lansechen/Qwen2.5-3B-Open-R1-GRPO-math-selected-cosine-noRW

Dataset automatically created during the evaluation run of model Lansechen/Qwen2.5-3B-Open-R1-GRPO-math-selected-cosine-noRW.

The dataset is composed of 2 configuration, each one coresponding to one of the evaluated task.

The dataset has been created from 3 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.

An additional configuration "results" store all the aggregated results of the run.

To load the details from a run, you can for instance do the following:

from datasets import load_dataset
data = load_dataset("Lansechen/details_Lansechen__Qwen2.5-3B-Open-R1-GRPO-math-selected-cosine-noRW",
    "results",
    split="train")

Latest results

These are the latest results from run 2025-04-14T17:16:52.243804(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):

{
    "all": {
        "extractive_match": 0.31313131313131315,
        "extractive_match_stderr": 0.033042050878136525
    },
    "lighteval|gpqa:diamond|0": {
        "extractive_match": 0.31313131313131315,
        "extractive_match_stderr": 0.033042050878136525
    }
}

Dataset Details

Dataset Description

  • Curated by: [More Information Needed]
  • Funded by [optional]: [More Information Needed]
  • Shared by [optional]: [More Information Needed]
  • Language(s) (NLP): [More Information Needed]
  • License: [More Information Needed]

Dataset Sources [optional]

  • Repository: [More Information Needed]
  • Paper [optional]: [More Information Needed]
  • Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Dataset Structure

[More Information Needed]

Dataset Creation

Curation Rationale

[More Information Needed]

Source Data

Data Collection and Processing

[More Information Needed]

Who are the source data producers?

[More Information Needed]

Annotations [optional]

Annotation process

[More Information Needed]

Who are the annotators?

[More Information Needed]

Personal and Sensitive Information

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Dataset Card Authors [optional]

[More Information Needed]

Dataset Card Contact

[More Information Needed]

Downloads last month
40
Size of downloaded dataset files:
11.7 MB
Size of the auto-converted Parquet files:
11.7 MB
Number of rows:
579