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
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
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
dataset: string
rollout_date: timestamp[s]
turn_count: int64
problem_id: string
message_count: int64
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
attempt_id: int64
source_dataset_id: string
to
{'id': Value('string'), 'conversations': List({'role': Value('string'), 'content': Value('string')}), 'dataset': Value('string'), 'problem_id': Value('string'), 'attempt_id': 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
              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
              dataset: string
              rollout_date: timestamp[s]
              turn_count: int64
              problem_id: string
              message_count: int64
              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
              attempt_id: int64
              source_dataset_id: string
              to
              {'id': Value('string'), 'conversations': List({'role': Value('string'), 'content': Value('string')}), 'dataset': Value('string'), 'problem_id': Value('string'), 'attempt_id': 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_count
int64
message_count
int64
rollout_date
timestamp[s]
source_dataset_id
string
amobench::amo-bench-1::attempt0
[ { "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
18
22
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt1
[ { "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
44
47
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt2
[ { "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
2
9
11
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt3
[ { "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
3
23
26
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt4
[ { "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
4
17
20
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt5
[ { "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
5
29
32
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt6
[ { "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
6
28
31
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-1::attempt7
[ { "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
7
17
20
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-4::attempt0
[ { "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-4
0
37
40
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-4::attempt1
[ { "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-4
1
5
7
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-4::attempt2
[ { "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-4
2
31
33
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-4::attempt3
[ { "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-4
3
5
7
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
amobench::amo-bench-4::attempt4
[ { "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-4
4
7
9
2026-03-11T00:00:00
aimosprite/brian-rollouts-311-compact-turns
End of preview.

brian-rollouts-311-specforge-conversations

Full-rollout conversations SpecForge training export derived from aimosprite/brian-rollouts-311-compact-turns.

Contents

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

Each JSONL row is one reconstructed rollout attempt in SpecForge conversations format. Harmony messages are reconstructed from the compact turn snapshots and merged so that repeated assistant text is not duplicated:

{
  "id": "amobench::amo-bench-1::attempt0",
  "conversations": [
    {
      "role": "system",
      "content": "..."
    },
    {
      "role": "user",
      "content": "..."
    },
    {
      "role": "assistant_analysis",
      "content": "..."
    },
    {
      "role": "assistant_final",
      "content": "..."
    }
  ],
  "dataset": "amobench",
  "problem_id": "amo-bench-1",
  "attempt_id": 0,
  "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-conversations.jsonl \
  --chat-template gpt-oss

This export follows SpecForge's actual Harmony loading path: safe_conversations_generator -> build_eagle3_dataset -> HarmonyParser. Consecutive assistant_analysis and assistant_final messages are preserved as distinct Harmony messages, and assistant loss is applied by SpecForge across assistant spans until the next user message.

Source

  • Source dataset: aimosprite/brian-rollouts-311-compact-turns
  • Conversion: token-id decoding with openai/gpt-oss-120b
  • Rows: 2,096
Downloads last month
-