Dataset Viewer
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
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[] | [[[1249,11625,279,2661,3491,11,582,1184,311,15442,279,1985,1124,11520,19748,15159,74,28,15,92,47822,(...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 need to evaluate the product \\(\\prod_{k=0}^{12}(2-2\\omega^k+\\om(...TRUNCATED) | null | [
0
] |
|
[] | [[[1249,11625,279,3491,11,582,1184,311,1477,279,12196,1931,1372,429,374,2686,1091,17767,39310,61,17,(...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": 0.03125
} | 0 | 0 | [
0
] | [] | [] | ["To solve the problem, we need to find the greatest real number that is less than \\( BD^2 \\) for (...TRUNCATED) | null | [
0
] |
|
[] | [[[1249,11625,419,3491,29720,11,1077,594,1438,432,1495,1119,70028,7354,1447,14374,14822,220,16,25,70(...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 this problem efficiently, let's break it down into manageable steps:\n\n### Step 1: Under(...TRUNCATED) | null | [
0
] |
|
[] | [[[1249,11625,419,3491,11,582,1184,311,8253,279,738,17767,362,1124,8,1741,429,279,1372,315,34226,247(...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": 0.12499999999999989
} | 0 | 0 | [
0
] | [] | [] | ["To solve this problem, we need to determine the set \\( A \\) such that the number of finite nonem(...TRUNCATED) | null | [
0
] |
|
[] | [[[1249,11625,419,3491,29720,323,9355,11,1077,594,1438,432,1495,3019,553,3019,382,14374,14822,220,16(...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 this problem efficiently and clearly, let's break it down step by step.\n\n### Step 1: Un(...TRUNCATED) | null | [
0
] |
|
[] | [[[1249,11625,279,3491,11,582,1184,311,1477,279,10578,17767,435,1124,8,315,279,24632,25366,429,646,6(...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 need to find the radius \\( r \\) of the smallest sphere that can contain(...TRUNCATED) | null | [
0
] |
|
[] | [[[1249,11625,419,3491,11,582,1184,311,1477,279,6010,504,279,1459,17767,358,1124,8,4766,279,27853,32(...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 this problem, we need to find the distance from the point \\( I \\) inside the tetrahedro(...TRUNCATED) | null | [
0
] |
|
[] | [[[1249,11625,279,2661,3491,11,582,1184,311,1477,279,7772,3204,1931,949,315,279,7493,1124,1188,22,20(...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
} | 0 | 0 | [
0
] | [] | [] | ["To solve the given problem, we need to find the largest possible real part of the expression \\((7(...TRUNCATED) | null | [
0
] |
|
[] | [[[1249,11625,419,3491,11,582,1184,311,1760,279,1372,315,12716,315,3084,220,16,21,389,458,220,23,87,(...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 this problem, we need to count the number of paths of length 16 on an 8x8 grid that chang(...TRUNCATED) | null | [
0
] |
|
[] | [[[1249,11625,419,3491,11,582,686,990,279,17508,315,27187,10187,8957,13,6771,594,6979,279,7289,438,1(...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 sets as (...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-v2
Dataset automatically created during the evaluation run of model Lansechen/Qwen2.5-3B-Open-R1-GRPO-math-selected-cosine-v2.
The dataset is composed of 3 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 10 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-v2",
"results",
split="train")
Latest results
These are the latest results from run 2025-04-14T15:18:06.982872(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": 0.24242424242424243,
"extractive_match_stderr": 0.030532892233932026
},
"lighteval|gpqa:diamond|0": {
"extractive_match": 0.24242424242424243,
"extractive_match_stderr": 0.030532892233932026
}
}
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
- 61