Datasets:

aimosprite
/

brian-rollouts-311-specforge-turn-conversations

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
total_messages: 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
attempt_id: int64
dataset: string
id: string
message_count: int64
rollout_date: timestamp[s]
source_dataset_id: string
turn_count: int64
problem_id: string
conversations: list<item: struct<role: string, content: string>>
  child 0, item: struct<role: string, content: string>
      child 0, role: string
      child 1, content: string
turn_number: int64
turn_index: int64
to
{'id': Value('string'), 'conversations': List({'role': Value('string'), 'content': 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'), 'message_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
              total_messages: 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
              attempt_id: int64
              dataset: string
              id: string
              message_count: int64
              rollout_date: timestamp[s]
              source_dataset_id: string
              turn_count: int64
              problem_id: string
              conversations: list<item: struct<role: string, content: string>>
                child 0, item: struct<role: string, content: string>
                    child 0, role: string
                    child 1, content: string
              turn_number: int64
              turn_index: int64
              to
              {'id': Value('string'), 'conversations': List({'role': Value('string'), 'content': 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'), 'message_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 dataset

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.

id string	conversations list	dataset string	problem_id string	attempt_id int64	turn_index int64	turn_number int64	turn_count int64	message_count int64	rollout_date timestamp[s]	source_dataset_id string
amobench::amo-bench-1::attempt0::turn0	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	0	1	18	3	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn1	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	1	2	18	4	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn2	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	2	3	18	5	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn3	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	3	4	18	6	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn4	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	4	5	18	7	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn5	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	5	6	18	8	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn6	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	6	7	18	9	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn7	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	7	8	18	10	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn8	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	8	9	18	11	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn9	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	9	10	18	12	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn10	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	10	11	18	14	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn11	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	11	12	18	15	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn12	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	12	13	18	16	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn13	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	13	14	18	17	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn14	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	14	15	18	18	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn15	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	15	16	18	19	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn16	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	16	17	18	21	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt0::turn17	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	0	17	18	18	22	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn0	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	0	1	44	3	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn1	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	1	2	44	4	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn2	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	2	3	44	5	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn3	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	3	4	44	6	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn4	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	4	5	44	7	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn5	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	5	6	44	8	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn6	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	6	7	44	9	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn7	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	7	8	44	10	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn8	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	8	9	44	11	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn9	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	9	10	44	12	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn10	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	10	11	44	13	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn11	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	11	12	44	14	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn12	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	12	13	44	15	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn13	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	13	14	44	16	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1::turn14	[ { "role": "system", "content": "You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2026-03-11\n\nReasoning: medium\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\n# Instructions\n\nYou are a world-class Intern...	amobench	amo-bench-1	1	14	15	44	17	2026-03-11T00:00:00	aimosprite/brian-rollouts-311-compact-turns

End of preview.

brian-rollouts-311-specforge-turn-conversations

Turn-level conversations SpecForge training export derived from aimosprite/brian-rollouts-311-compact-turns.

brian-rollouts-311-specforge-turn-conversations.jsonl
brian-rollouts-311-specforge-turn-conversations.jsonl.manifest.json

Each JSONL row is a single assistant call rendered as a full SpecForge conversations sample. The visible prefix context is intentionally repeated across rows so that every assistant turn is independently trainable:

{
  "id": "amobench::amo-bench-1::attempt0::turn0",
  "conversations": [
    {
      "role": "system",
      "content": "..."
    },
    {
      "role": "user",
      "content": "..."
    },
    {
      "role": "assistant_analysis",
      "content": "..."
    }
  ],
  "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 current SpecForge training flows that consume conversations JSONL with the GPT-OSS chat template:

torchrun --standalone --nproc_per_node 8 scripts/train_eagle3.py \
  --train-data-path ./brian-rollouts-311-specforge-turn-conversations.jsonl \
  --chat-template gpt-oss

This turn-level export is preferable to one-row-per-rollout data for compact GPT-OSS traces because later prompts do not retain earlier hidden analysis messages. Exploding to one row per assistant call preserves the current turn's reasoning/final output.

Source

Source dataset: aimosprite/brian-rollouts-311-compact-turns
Conversion: token-id decoding with openai/gpt-oss-120b
Rows: 69,373

Downloads last month: 2

Total file size:

1.06 GB

brian-rollouts-311-specforge-turn-conversations

Contents

Intended usage

Source