Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code: DatasetGenerationError
Exception: CastError
Message: Couldn't cast
input_path: string
output_path: string
dataset_id: string
tokenizer: string
rows_written: int64
attempts_processed: int64
turn_rows_processed: int64
datasets: struct<amobench: int64, astralbench: int64, beyondaime: int64, aime2026: int64, hmmtfeb2026: int64>
child 0, amobench: int64
child 1, astralbench: int64
child 2, beyondaime: int64
child 3, aime2026: int64
child 4, hmmtfeb2026: int64
turn_number: int64
turn_count: int64
dataset: string
problem_id: string
text: string
turn_index: int64
rollout_date: timestamp[s]
id: string
source_dataset_id: string
attempt_id: int64
to
{'id': Value('string'), 'text': Value('string'), 'dataset': Value('string'), 'problem_id': Value('string'), 'attempt_id': Value('int64'), 'turn_index': Value('int64'), 'turn_number': Value('int64'), 'turn_count': Value('int64'), 'rollout_date': Value('timestamp[s]'), 'source_dataset_id': Value('string')}
because column names don't match
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1872, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 265, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 120, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_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_path: string
output_path: string
dataset_id: string
tokenizer: string
rows_written: int64
attempts_processed: int64
turn_rows_processed: int64
datasets: struct<amobench: int64, astralbench: int64, beyondaime: int64, aime2026: int64, hmmtfeb2026: int64>
child 0, amobench: int64
child 1, astralbench: int64
child 2, beyondaime: int64
child 3, aime2026: int64
child 4, hmmtfeb2026: int64
turn_number: int64
turn_count: int64
dataset: string
problem_id: string
text: string
turn_index: int64
rollout_date: timestamp[s]
id: string
source_dataset_id: string
attempt_id: int64
to
{'id': Value('string'), 'text': Value('string'), 'dataset': Value('string'), 'problem_id': Value('string'), 'attempt_id': Value('int64'), 'turn_index': Value('int64'), 'turn_number': Value('int64'), 'turn_count': Value('int64'), 'rollout_date': Value('timestamp[s]'), 'source_dataset_id': Value('string')}
because column names don't match
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1347, in compute_config_parquet_and_info_response
parquet_operations = convert_to_parquet(builder)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 980, in convert_to_parquet
builder.download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 884, in download_and_prepare
self._download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 947, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1739, 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 1922, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
id string | text string | dataset string | problem_id string | attempt_id int64 | turn_index int64 | turn_number int64 | turn_count int64 | rollout_date timestamp[s] | source_dataset_id string |
|---|---|---|---|---|---|---|---|---|---|
amobench::amo-bench-1::attempt0::turn0 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 0 | 1 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn1 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 1 | 2 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn2 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 2 | 3 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn3 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 3 | 4 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn4 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 4 | 5 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn5 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 5 | 6 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn6 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 6 | 7 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn7 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 7 | 8 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn8 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 8 | 9 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn9 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 9 | 10 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn10 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 10 | 11 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn11 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 11 | 12 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn12 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 12 | 13 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn13 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 13 | 14 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn14 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 14 | 15 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn15 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 15 | 16 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn16 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 16 | 17 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt0::turn17 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 0 | 17 | 18 | 18 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn0 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 0 | 1 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn1 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 1 | 2 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn2 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 2 | 3 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn3 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 3 | 4 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn4 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 4 | 5 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn5 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 5 | 6 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn6 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 6 | 7 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn7 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 7 | 8 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn8 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 8 | 9 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn9 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 9 | 10 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn10 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 10 | 11 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn11 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 11 | 12 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn12 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 12 | 13 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn13 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 13 | 14 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
amobench::amo-bench-1::attempt1::turn14 | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2026-03-11
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a world-class ... | amobench | amo-bench-1 | 1 | 14 | 15 | 44 | 2026-03-11T00:00:00 | aimosprite/brian-rollouts-311-compact-turns |
End of preview.
brian-rollouts-311-specforge-preformatted-turns
Preformatted per-turn SpecForge training export derived from
aimosprite/brian-rollouts-311-compact-turns.
Contents
brian-rollouts-311-specforge-preformatted-turns.jsonlbrian-rollouts-311-specforge-preformatted-turns.jsonl.manifest.json
Each JSONL row is a single assistant turn rendered as a full GPT-OSS / Harmony
prompt-plus-completion string in a text field:
{
"id": "amobench::amo-bench-1::attempt0::turn0",
"text": "<|start|>system ... <|start|>assistant<|channel|>analysis ...",
"dataset": "amobench",
"problem_id": "amo-bench-1",
"attempt_id": 0,
"turn_index": 0,
"turn_number": 1,
"turn_count": 18,
"rollout_date": "2026-03-11",
"source_dataset_id": "aimosprite/brian-rollouts-311-compact-turns"
}
Intended usage
This export is meant for SpecForge preformatted-data training flows with the GPT-OSS chat template:
torchrun --standalone --nproc_per_node 8 scripts/train_eagle3.py \
--train-data-path ./brian-rollouts-311-specforge-preformatted-turns.jsonl \
--chat-template gpt-oss \
--is-preformatted
Source
- Source dataset:
aimosprite/brian-rollouts-311-compact-turns - Conversion: token-id decoding with
openai/gpt-oss-120b - Rows: 69,373
- Downloads last month
- 4