Hugging Face's logo

Datasets:
lewtun
/
details_deepseek-ai__DeepSeek-R1-Distill-Qwen-7B

Modalities:
Text
Formats:
parquet
Size:
< 1K
Libraries:
Datasets
pandas
Dataset card Viewer Files Community
Dataset Viewer
Auto-converted to Parquet
Full Screen
choices
stringclasses
1 value
cont_tokens
stringlengths
4.56k
93.5k
example
stringlengths
388
5.89k
full_prompt
stringlengths
430
5.94k
gold
stringclasses
4 values
gold_index
stringclasses
1 value
input_tokens
stringlengths
591
4.48k
instruction
stringlengths
388
5.89k
metrics
stringclasses
2 values
num_asked_few_shots
stringclasses
1 value
num_effective_few_shots
stringclasses
1 value
padded
stringclasses
1 value
pred_logits
stringclasses
1 value
predictions
stringlengths
21.9k
447k
specifics
stringclasses
16 values
truncated
stringclasses
1 value
[]
"[[(151648, 198, 32313, 11, 773, 358, 3003, 2684, 419, 17356, 29803, 3491, 1588, 13, 1084, 5868, 264(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
"<｜begin▁of▁sentence｜><｜User｜>Given the following question and four candidate answers (A(...TRUNCATED)
['A']
[]
"[[151646, 151646, 151644, 22043, 279, 2701, 3405, 323, 3040, 9144, 11253, 320, 32, 11, 425, 11, 356(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
{'extractive_match': 0.0}
0
0
[0]
[]
"[([\"<think>\\nOkay, so I've got this organic chemistry problem here. It looks a bit complicated, b(...TRUNCATED)
{'extracted_predictions': ['D', 'D'], 'extracted_golds': ['A', 'A']}
[0]
[]
"[[(151648, 198, 32313, 11, 773, 358, 2776, 3330, 518, 419, 17356, 29803, 3405, 911, 34948, 264, 709(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
"<｜begin▁of▁sentence｜><｜User｜>Given the following question and four candidate answers (A(...TRUNCATED)
['D']
[]
"[[151646, 151646, 151644, 22043, 279, 2701, 3405, 323, 3040, 9144, 11253, 320, 32, 11, 425, 11, 356(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
{'extractive_match': 0.0}
0
0
[0]
[]
"[(['<think>\\nOkay, so I\\'m looking at this organic chemistry question about naming a benzene ring(...TRUNCATED)
{'extracted_predictions': ['C', 'C'], 'extracted_golds': ['D', 'D']}
[0]
[]
"[[(151648, 198, 32313, 11, 358, 3003, 2684, 419, 30128, 29026, 3491, 311, 11625, 13, 6771, 752, 143(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
"<｜begin▁of▁sentence｜><｜User｜>Given the following question and four candidate answers (A(...TRUNCATED)
['A']
[]
"[[151646, 151646, 151644, 22043, 279, 2701, 3405, 323, 3040, 9144, 11253, 320, 32, 11, 425, 11, 356(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
{'extractive_match': 1.0}
0
0
[0]
[]
"[([\"<think>\\nOkay, I've got this quantum mechanics problem to solve. Let me try to break it down (...TRUNCATED)
{'extracted_predictions': ['A', 'A'], 'extracted_golds': ['A', 'A']}
[0]
[]
"[[(151648, 198, 32313, 11, 1077, 752, 1744, 1526, 419, 3019, 553, 3019, 13, 2055, 11, 279, 3405, 37(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
"<｜begin▁of▁sentence｜><｜User｜>Given the following question and four candidate answers (A(...TRUNCATED)
['A']
[]
"[[151646, 151646, 151644, 22043, 279, 2701, 3405, 323, 3040, 9144, 11253, 320, 32, 11, 425, 11, 356(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
{'extractive_match': 1.0}
0
0
[0]
[]
"[(['<think>\\nOkay, let me think through this step by step. So, the question is about designing a m(...TRUNCATED)
{'extracted_predictions': ['A', 'A'], 'extracted_golds': ['A', 'A']}
[0]
[]
"[[(151648, 198, 32313, 11, 1077, 594, 21403, 419, 3491, 13, 1084, 594, 264, 2699, 16965, 448, 678, (...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
"<｜begin▁of▁sentence｜><｜User｜>Given the following question and four candidate answers (A(...TRUNCATED)
['B']
[]
"[[151646, 151646, 151644, 22043, 279, 2701, 3405, 323, 3040, 9144, 11253, 320, 32, 11, 425, 11, 356(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
{'extractive_match': 1.0}
0
0
[0]
[]
"[([\"<think>\\nOkay, let's tackle this problem. It's a bit complicated with all these reactions and(...TRUNCATED)
{'extracted_predictions': ['B', 'B'], 'extracted_golds': ['B', 'B']}
[0]
[]
"[[(151648, 198, 32313, 11, 358, 2776, 4460, 311, 11625, 419, 17356, 29803, 3491, 13, 6771, 752, 134(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
"<｜begin▁of▁sentence｜><｜User｜>Given the following question and four candidate answers (A(...TRUNCATED)
['C']
[]
"[[151646, 151646, 151644, 22043, 279, 2701, 3405, 323, 3040, 9144, 11253, 320, 32, 11, 425, 11, 356(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
{'extractive_match': 0.0}
0
0
[0]
[]
"[([\"<think>\\nOkay, I'm trying to solve this organic chemistry problem. Let me read through it aga(...TRUNCATED)
{'extracted_predictions': ['A', 'A'], 'extracted_golds': ['C', 'C']}
[0]
[]
"[[(151648, 198, 32313, 11, 358, 3003, 2684, 419, 3491, 1588, 11, 323, 358, 2776, 9966, 311, 7071, 7(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
"<｜begin▁of▁sentence｜><｜User｜>Given the following question and four candidate answers (A(...TRUNCATED)
['C']
[]
"[[151646, 151646, 151644, 22043, 279, 2701, 3405, 323, 3040, 9144, 11253, 320, 32, 11, 425, 11, 356(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
{'extractive_match': 0.0}
0
0
[0]
[]
"[(['<think>\\nOkay, I\\'ve got this problem here, and I\\'m supposed to figure out what the algorit(...TRUNCATED)
{'extracted_predictions': ['D', 'D'], 'extracted_golds': ['C', 'C']}
[0]
[]
"[[(151648, 198, 32313, 11, 773, 358, 2776, 4460, 311, 3535, 419, 910, 3298, 7806, 80, 3405, 13, 677(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
"<｜begin▁of▁sentence｜><｜User｜>Given the following question and four candidate answers (A(...TRUNCATED)
['D']
[]
"[[151646, 151646, 151644, 22043, 279, 2701, 3405, 323, 3040, 9144, 11253, 320, 32, 11, 425, 11, 356(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
{'extractive_match': 1.0}
0
0
[0]
[]
"[([\"<think>\\nOkay, so I'm trying to understand this ChIP-seq question. Let's break it down. The q(...TRUNCATED)
{'extracted_predictions': ['D', 'D'], 'extracted_golds': ['D', 'D']}
[0]
[]
"[[(151648, 198, 32313, 11, 773, 358, 3003, 2684, 419, 15552, 8500, 304, 4065, 315, 752, 11, 323, 27(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
"<｜begin▁of▁sentence｜><｜User｜>Given the following question and four candidate answers (A(...TRUNCATED)
['C']
[]
"[[3706, 6029, 1890, 32, 1890, 6029, 1706, 5049, 1162, 22254, 828, 22254, 1890, 32, 828, 21614, 7749(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
{'extractive_match': 0.0}
0
0
[0]
[]
"[([\"<think>\\nOkay, so I've got this DNA sequence in front of me, and the question is asking about(...TRUNCATED)
{'extracted_predictions': ['B', 'B'], 'extracted_golds': ['C', 'C']}
[0]
[]
"[[(151648, 198, 32313, 11, 773, 358, 3003, 2525, 3941, 419, 29803, 3491, 11, 323, 26044, 11, 432, 5(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
"<｜begin▁of▁sentence｜><｜User｜>Given the following question and four candidate answers (A(...TRUNCATED)
['C']
[]
"[[151646, 151646, 151644, 22043, 279, 2701, 3405, 323, 3040, 9144, 11253, 320, 32, 11, 425, 11, 356(...TRUNCATED)
"Given the following question and four candidate answers (A, B, C and D), choose the best answer.\n\(...TRUNCATED)
{'extractive_match': 1.0}
0
0
[0]
[]
"[([\"<think>\\nOkay, so I've come across this chemistry problem, and honestly, it's a bit tricky, b(...TRUNCATED)
{'extracted_predictions': ['C', 'C'], 'extracted_golds': ['C', 'C']}
[0]
End of preview. Expand in Dataset Viewer.

Dataset Card for Evaluation run of deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Dataset automatically created during the evaluation run of model deepseek-ai/DeepSeek-R1-Distill-Qwen-7B.

The dataset is composed of 1 configuration, each one coresponding to one of the evaluated task.

The dataset has been created from 2 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("lewtun/details_deepseek-ai__DeepSeek-R1-Distill-Qwen-7B",
    "results",
    split="train")

Latest results

These are the latest results from run 2025-02-05T14:49:38.490278(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": 0.45454545454545453,
        "extractive_match_stderr": 0.03547601494006936
    },
    "lighteval|gpqa:diamond|0": {
        "extractive_match": 0.45454545454545453,
        "extractive_match_stderr": 0.03547601494006936
    }
}

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
4
Size of downloaded dataset files:
89.6 MB
Size of the auto-converted Parquet files:
89.6 MB
Number of rows:
597