Dataset Preview
Duplicate
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed because of a cast error
Error code:   DatasetGenerationCastError
Exception:    DatasetGenerationCastError
Message:      An error occurred while generating the dataset

All the data files must have the same columns, but at some point there are 3 new columns ({'overlong_reward', 'overlong', 'used_r_module'})

This happened while the json dataset builder was generating data using

hf://datasets/zhen-yang/rollout_output_drm_qwen3_8b_base/verl/DAPO-DAPO-DRM-Qwen3-8B-Base/1.jsonl (at revision 8c1f2e307b3e834204b765b0ae93b8a61ecb0aea)

Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1831, in _prepare_split_single
                  writer.write_table(table)
                File "/usr/local/lib/python3.12/site-packages/datasets/arrow_writer.py", line 714, in write_table
                  pa_table = table_cast(pa_table, self._schema)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2272, in table_cast
                  return cast_table_to_schema(table, schema)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2218, in cast_table_to_schema
                  raise CastError(
              datasets.table.CastError: Couldn't cast
              input: string
              output: string
              gts: string
              score: double
              step: int64
              acc: bool
              pred: string
              overlong_reward: double
              overlong: bool
              advantages: double
              rollout_is_weights_0: double
              not_mask_seq: bool
              sequence_entropy: double
              use_rm: int64
              id: string
              used_r_module: int64
              uid: string
              to
              {'input': Value('string'), 'output': Value('string'), 'gts': Value('string'), 'score': Value('float64'), 'step': Value('int64'), 'acc': Value('bool'), 'pred': Value('string'), 'advantages': Value('float64'), 'rollout_is_weights_0': Value('float64'), 'not_mask_seq': Value('bool'), 'sequence_entropy': Value('float64'), 'use_rm': Value('int64'), 'id': Value('string'), 'uid': Value('string')}
              because column names don't match
              
              During handling of the above exception, another exception occurred:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1334, in compute_config_parquet_and_info_response
                  parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
                                                                        ^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 911, in stream_convert_to_parquet
                  builder._prepare_split(
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1702, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1833, in _prepare_split_single
                  raise DatasetGenerationCastError.from_cast_error(
              datasets.exceptions.DatasetGenerationCastError: An error occurred while generating the dataset
              
              All the data files must have the same columns, but at some point there are 3 new columns ({'overlong_reward', 'overlong', 'used_r_module'})
              
              This happened while the json dataset builder was generating data using
              
              hf://datasets/zhen-yang/rollout_output_drm_qwen3_8b_base/verl/DAPO-DAPO-DRM-Qwen3-8B-Base/1.jsonl (at revision 8c1f2e307b3e834204b765b0ae93b8a61ecb0aea)
              
              Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

input
string
output
string
gts
string
score
float64
step
int64
acc
bool
pred
string
advantages
float64
rollout_is_weights_0
float64
not_mask_seq
bool
sequence_entropy
float64
use_rm
int64
id
string
uid
string
<|im_start|>user Let $f(n)=\varphi(n^3)^{-1}$, where $\varphi(n)$ denotes the number of positive integers not greater than $n$ that are relatively prime to $n$. Suppose \[ \frac{f(1)+f(3)+f(5)+\dots}{f(2)+f(4)+f(6)+\dots} = \frac{m}{n} \] where $m$ and $n$ are relatively prime positive integers. Compute $100m+n$. Pleas...
Alright, I have this problem in front of me: Let \( f(n) = \varphi(n^3)^{-1} \), where \( \varphi(n) \) denotes the number of positive integers not greater than \( n \) that are relatively prime to \( n \). Suppose \[ \frac{f(1) + f(3) + f(5) + \dots}{f(2) + f(4) + f(6) + \dots} = \frac{m}{n} \] where \( m \) and \( n...
702
-1
1
false
10730
-0.365962
0.793068
true
0.297288
1
f4ba5bdbd4716ccc
006db5b0-2f2f-4516-8fc2-164767a282ff-1
<|im_start|>user Let $f(n)=\varphi(n^3)^{-1}$, where $\varphi(n)$ denotes the number of positive integers not greater than $n$ that are relatively prime to $n$. Suppose \[ \frac{f(1)+f(3)+f(5)+\dots}{f(2)+f(4)+f(6)+\dots} = \frac{m}{n} \] where $m$ and $n$ are relatively prime positive integers. Compute $100m+n$. Pleas...
Alright, I have this problem in front of me, and I need to solve it step by step. Let's break it down and see what's going on. ### Understanding the Problem First, let's understand what's being asked. We have a function defined as: \[ f(n) = \varphi(n^3)^{-1} \] where \( \varphi(n) \) is Euler's totient function, wh...
702
-1
1
false
3201
-0.365962
0.793068
true
0.373132
1
f4ba5bdbd4716ccc
006db5b0-2f2f-4516-8fc2-164767a282ff-1
<|im_start|>user Let $f(n)=\varphi(n^3)^{-1}$, where $\varphi(n)$ denotes the number of positive integers not greater than $n$ that are relatively prime to $n$. Suppose \[ \frac{f(1)+f(3)+f(5)+\dots}{f(2)+f(4)+f(6)+\dots} = \frac{m}{n} \] where $m$ and $n$ are relatively prime positive integers. Compute $100m+n$. Pleas...
Alright, I have this problem in front of me: Let \( f(n) = \varphi(n^3)^{-1} \), where \( \varphi(n) \) denotes the number of positive integers not greater than \( n \) that are relatively prime to \( n \). Suppose \[ \frac{f(1) + f(3) + f(5) + \dots}{f(2) + f(4) + f(6) + \dots} = \frac{m}{n} \] where \( m \) and \(...
702
-1
1
false
353
-0.365962
0.793068
true
0.388216
1
f4ba5bdbd4716ccc
006db5b0-2f2f-4516-8fc2-164767a282ff-1
<|im_start|>user Let $f(n)=\varphi(n^3)^{-1}$, where $\varphi(n)$ denotes the number of positive integers not greater than $n$ that are relatively prime to $n$. Suppose \[ \frac{f(1)+f(3)+f(5)+\dots}{f(2)+f(4)+f(6)+\dots} = \frac{m}{n} \] where $m$ and $n$ are relatively prime positive integers. Compute $100m+n$. Pleas...
Alright, I have this problem in front of me, and I need to solve it step by step. Let's break it down and see if I can understand what's going on. **Problem Statement:** We have a function defined as \( f(n) = \frac{1}{\varphi(n^3)} \), where \( \varphi(n) \) is Euler's totient function, which counts the number of po...
702
1
1
true
702
2.561734
0.930713
true
0.294037
1
f4ba5bdbd4716ccc
006db5b0-2f2f-4516-8fc2-164767a282ff-1
<|im_start|>user Let $f(n)=\varphi(n^3)^{-1}$, where $\varphi(n)$ denotes the number of positive integers not greater than $n$ that are relatively prime to $n$. Suppose \[ \frac{f(1)+f(3)+f(5)+\dots}{f(2)+f(4)+f(6)+\dots} = \frac{m}{n} \] where $m$ and $n$ are relatively prime positive integers. Compute $100m+n$. Pleas...
Alright, I have this problem in front of me, and I need to solve it step by step. Let's break it down. **Problem Statement:** Let \( f(n) = \varphi(n^3)^{-1} \), where \( \varphi(n) \) denotes the number of positive integers not greater than \( n \) that are relatively prime to \( n \). Suppose \[ \frac{f(1) + f(3) +...
702
-1
1
false
701
-0.365962
0.793068
true
0.440317
1
f4ba5bdbd4716ccc
006db5b0-2f2f-4516-8fc2-164767a282ff-1
"<|im_start|>user\nLet $f(n)=\\varphi(n^3)^{-1}$, where $\\varphi(n)$ denotes the number of positive(...TRUNCATED)
"Alright, I have this problem in front of me, and I need to solve it step by step. Let's break it do(...TRUNCATED)
702
-1
1
false
401
-0.365962
0.793068
true
0.390214
2
f4ba5bdbd4716ccc
006db5b0-2f2f-4516-8fc2-164767a282ff-2
"<|im_start|>user\nLet $f(n)=\\varphi(n^3)^{-1}$, where $\\varphi(n)$ denotes the number of positive(...TRUNCATED)
"Alright, I have this problem in front of me, and I need to solve it step by step. The problem is:\n(...TRUNCATED)
702
-1
1
false
2507
-0.365962
0.924938
true
0.256623
2
f4ba5bdbd4716ccc
006db5b0-2f2f-4516-8fc2-164767a282ff-2
"<|im_start|>user\nLet $f(n)=\\varphi(n^3)^{-1}$, where $\\varphi(n)$ denotes the number of positive(...TRUNCATED)
"Alright, I have this problem in front of me, and it seems a bit intimidating at first glance. Let's(...TRUNCATED)
702
-1
1
false
101
-0.365962
0.812663
true
0.560335
2
f4ba5bdbd4716ccc
006db5b0-2f2f-4516-8fc2-164767a282ff-2
"<|im_start|>user\nLet $f(n)=\\varphi(n^3)^{-1}$, where $\\varphi(n)$ denotes the number of positive(...TRUNCATED)
"Alright, I have this problem in front of me, and I need to solve it step by step. Let's break it do(...TRUNCATED)
702
-1
1
false
1805
-0.365962
0.793068
true
0.2279
4
f4ba5bdbd4716ccc
006db5b0-2f2f-4516-8fc2-164767a282ff-4
"<|im_start|>user\nLet $f(n)=\\varphi(n^3)^{-1}$, where $\\varphi(n)$ denotes the number of positive(...TRUNCATED)
"Alright, I have this problem in front of me, and I need to solve it step by step. Let's break it do(...TRUNCATED)
702
-1
1
false
[INVALID]
-0.365962
0.793068
true
1.714549
4
f4ba5bdbd4716ccc
006db5b0-2f2f-4516-8fc2-164767a282ff-4
End of preview.

No dataset card yet

Downloads last month
72