Datasets:

bytkim
/

qodex-teacher-codex-r1-48k

Tasks:

Text Generation

Languages:

English

License:

Dataset card Data Studio Files Files and versions

xet

Community

Dataset Preview

Duplicate

Split (1)

train

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
prompt: list<item: struct<role: string, content: string, tool_calls: list<item: struct<type: string, functio (... 221 chars omitted)
  child 0, item: struct<role: string, content: string, tool_calls: list<item: struct<type: string, function: struct<n (... 209 chars omitted)
      child 0, role: string
      child 1, content: string
      child 2, tool_calls: list<item: struct<type: string, function: struct<name: string, arguments: struct<cmd: string, workdi (... 122 chars omitted)
          child 0, item: struct<type: string, function: struct<name: string, arguments: struct<cmd: string, workdir: string,  (... 110 chars omitted)
              child 0, type: string
              child 1, function: struct<name: string, arguments: struct<cmd: string, workdir: string, yield_time_ms: int64, max_outpu (... 66 chars omitted)
                  child 0, name: string
                  child 1, arguments: struct<cmd: string, workdir: string, yield_time_ms: int64, max_output_tokens: int64, input: string,  (... 33 chars omitted)
                      child 0, cmd: string
                      child 1, workdir: string
                      child 2, yield_time_ms: int64
                      child 3, max_output_tokens: int64
                      child 4, input: string
                      child 5, session_id: int64
                      child 6, chars: string
              child 2, id: string
      child 3, tool_call_id: string
      child 4, name: string
completion: list<item: struct<role
...
0, role: string
      child 1, content: string
      child 2, tool_calls: list<item: struct<type: string, function: struct<name: string, arguments: struct<cmd: string, workdi (... 122 chars omitted)
          child 0, item: struct<type: string, function: struct<name: string, arguments: struct<cmd: string, workdir: string,  (... 110 chars omitted)
              child 0, type: string
              child 1, function: struct<name: string, arguments: struct<cmd: string, workdir: string, yield_time_ms: int64, max_outpu (... 66 chars omitted)
                  child 0, name: string
                  child 1, arguments: struct<cmd: string, workdir: string, yield_time_ms: int64, max_output_tokens: int64, input: string,  (... 33 chars omitted)
                      child 0, cmd: string
                      child 1, workdir: string
                      child 2, yield_time_ms: int64
                      child 3, max_output_tokens: int64
                      child 4, input: string
                      child 5, session_id: int64
                      child 6, chars: string
              child 2, id: string
metadata: struct<source: string, trajectory_path: string, model: string, render_tokens_qwen36_no_thinking: int (... 73 chars omitted)
  child 0, source: string
  child 1, trajectory_path: string
  child 2, model: string
  child 3, render_tokens_qwen36_no_thinking: int64
  child 4, token_budget: string
  child 5, assistant_message_index: int64
  child 6, format: string
messages: null
to
{'messages': List(Json(decode=True)), 'metadata': {'source': Value('string'), 'trajectory_path': Value('string'), 'model': Value('string'), 'render_tokens_qwen36_no_thinking': Value('int64'), 'token_budget': 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 1779, in _prepare_split_single
                  for key, table in generator:
                                    ^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 299, 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 128, 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 2321, in table_cast
                  return cast_table_to_schema(table, schema)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2249, in cast_table_to_schema
                  raise CastError(
              datasets.table.CastError: Couldn't cast
              prompt: list<item: struct<role: string, content: string, tool_calls: list<item: struct<type: string, functio (... 221 chars omitted)
                child 0, item: struct<role: string, content: string, tool_calls: list<item: struct<type: string, function: struct<n (... 209 chars omitted)
                    child 0, role: string
                    child 1, content: string
                    child 2, tool_calls: list<item: struct<type: string, function: struct<name: string, arguments: struct<cmd: string, workdi (... 122 chars omitted)
                        child 0, item: struct<type: string, function: struct<name: string, arguments: struct<cmd: string, workdir: string,  (... 110 chars omitted)
                            child 0, type: string
                            child 1, function: struct<name: string, arguments: struct<cmd: string, workdir: string, yield_time_ms: int64, max_outpu (... 66 chars omitted)
                                child 0, name: string
                                child 1, arguments: struct<cmd: string, workdir: string, yield_time_ms: int64, max_output_tokens: int64, input: string,  (... 33 chars omitted)
                                    child 0, cmd: string
                                    child 1, workdir: string
                                    child 2, yield_time_ms: int64
                                    child 3, max_output_tokens: int64
                                    child 4, input: string
                                    child 5, session_id: int64
                                    child 6, chars: string
                            child 2, id: string
                    child 3, tool_call_id: string
                    child 4, name: string
              completion: list<item: struct<role
              ...
              0, role: string
                    child 1, content: string
                    child 2, tool_calls: list<item: struct<type: string, function: struct<name: string, arguments: struct<cmd: string, workdi (... 122 chars omitted)
                        child 0, item: struct<type: string, function: struct<name: string, arguments: struct<cmd: string, workdir: string,  (... 110 chars omitted)
                            child 0, type: string
                            child 1, function: struct<name: string, arguments: struct<cmd: string, workdir: string, yield_time_ms: int64, max_outpu (... 66 chars omitted)
                                child 0, name: string
                                child 1, arguments: struct<cmd: string, workdir: string, yield_time_ms: int64, max_output_tokens: int64, input: string,  (... 33 chars omitted)
                                    child 0, cmd: string
                                    child 1, workdir: string
                                    child 2, yield_time_ms: int64
                                    child 3, max_output_tokens: int64
                                    child 4, input: string
                                    child 5, session_id: int64
                                    child 6, chars: string
                            child 2, id: string
              metadata: struct<source: string, trajectory_path: string, model: string, render_tokens_qwen36_no_thinking: int (... 73 chars omitted)
                child 0, source: string
                child 1, trajectory_path: string
                child 2, model: string
                child 3, render_tokens_qwen36_no_thinking: int64
                child 4, token_budget: string
                child 5, assistant_message_index: int64
                child 6, format: string
              messages: null
              to
              {'messages': List(Json(decode=True)), 'metadata': {'source': Value('string'), 'trajectory_path': Value('string'), 'model': Value('string'), 'render_tokens_qwen36_no_thinking': Value('int64'), 'token_budget': 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 882, in download_and_prepare
                  self._download_and_prepare(
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 943, in _download_and_prepare
                  self._prepare_split(split_generator, **prepare_split_kwargs)
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1646, 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 1832, 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.

messages list	metadata dict
[ { "role": "system", "content": "<permissions instructions>\nFilesystem sandboxing defines which files can be read or written. `sandbox_mode` is `danger-full-access`: No filesystem sandboxing - all commands are permitted. Network access is enabled.\nApproval policy is currently never. Do not provide the `san...	{ "source": "harbor", "trajectory_path": "exports/20260501T073334Z-qodex-teacher-v0.1-final/sanitized_atif/Rscript_segfault_debugging_medium/Rscript_segfault_debugging_mediu__jz8dZ56/trajectory.json", "model": "gpt-5.5", "render_tokens_qwen36_no_thinking": 7192, "token_budget": "qwen36_48k_no_thinking" }
[ { "role": "system", "content": "<permissions instructions>\nFilesystem sandboxing defines which files can be read or written. `sandbox_mode` is `danger-full-access`: No filesystem sandboxing - all commands are permitted. Network access is enabled.\nApproval policy is currently never. Do not provide the `san...	{ "source": "harbor", "trajectory_path": "exports/20260501T073334Z-qodex-teacher-v0.1-final/sanitized_atif/aar_android_library_packaging_hard/aar_android_library_packaging_ha__SQW75hX/trajectory.json", "model": "gpt-5.5", "render_tokens_qwen36_no_thinking": 7583, "token_budget": "qwen36_48k_no_thinking" }
[ { "role": "system", "content": "<permissions instructions>\nFilesystem sandboxing defines which files can be read or written. `sandbox_mode` is `danger-full-access`: No filesystem sandboxing - all commands are permitted. Network access is enabled.\nApproval policy is currently never. Do not provide the `san...	{ "source": "harbor", "trajectory_path": "exports/20260501T073334Z-qodex-teacher-v0.1-final/sanitized_atif/active_directory_golden_ticket_hard/active_directory_golden_ticket_h__fcFajBL/trajectory.json", "model": "gpt-5.5", "render_tokens_qwen36_no_thinking": 7058, "token_budget": "qwen36_48k_no_thinking" }
[ { "role": "system", "content": "<permissions instructions>\nFilesystem sandboxing defines which files can be read or written. `sandbox_mode` is `danger-full-access`: No filesystem sandboxing - all commands are permitted. Network access is enabled.\nApproval policy is currently never. Do not provide the `san...	{ "source": "harbor", "trajectory_path": "exports/20260501T073334Z-qodex-teacher-v0.1-final/sanitized_atif/aes-known-plaintext-recovery/aes-known-plaintext-recovery__M9NSbnG/trajectory.json", "model": "gpt-5.5", "render_tokens_qwen36_no_thinking": 8936, "token_budget": "qwen36_48k_no_thinking" }
[ { "role": "system", "content": "<permissions instructions>\nFilesystem sandboxing defines which files can be read or written. `sandbox_mode` is `danger-full-access`: No filesystem sandboxing - all commands are permitted. Network access is enabled.\nApproval policy is currently never. Do not provide the `san...	{ "source": "harbor", "trajectory_path": "exports/20260501T073334Z-qodex-teacher-v0.1-final/sanitized_atif/alembic_migration_conflict_medium/alembic_migration_conflict_mediu__4Kxu9Hy/trajectory.json", "model": "gpt-5.5", "render_tokens_qwen36_no_thinking": 12762, "token_budget": "qwen36_48k_no_thinking" }
[ { "role": "system", "content": "<permissions instructions>\nFilesystem sandboxing defines which files can be read or written. `sandbox_mode` is `danger-full-access`: No filesystem sandboxing - all commands are permitted. Network access is enabled.\nApproval policy is currently never. Do not provide the `san...	{ "source": "harbor", "trajectory_path": "exports/20260501T073334Z-qodex-teacher-v0.1-final/sanitized_atif/amqp_rabbitmq_default_credentials_medium/amqp_rabbitmq_default_credential__xi32Tby/trajectory.json", "model": "gpt-5.5", "render_tokens_qwen36_no_thinking": 2563, "token_budget": "qwen36_48k_no_thinking"...
[ { "role": "system", "content": "<permissions instructions>\nFilesystem sandboxing defines which files can be read or written. `sandbox_mode` is `danger-full-access`: No filesystem sandboxing - all commands are permitted. Network access is enabled.\nApproval policy is currently never. Do not provide the `san...	{ "source": "harbor", "trajectory_path": "exports/20260501T073334Z-qodex-teacher-v0.1-final/sanitized_atif/analyze-stock-data-visualize/analyze-stock-data-visualize__5nVaUzW/trajectory.json", "model": "gpt-5.5", "render_tokens_qwen36_no_thinking": 7521, "token_budget": "qwen36_48k_no_thinking" }
[{"role":"system","content":"<permissions instructions>\nFilesystem sandboxing defines which files c(...TRUNCATED)	{"source":"harbor","trajectory_path":"exports/20260501T073334Z-qodex-teacher-v0.1-final/sanitized_at(...TRUNCATED)
[{"role":"system","content":"<permissions instructions>\nFilesystem sandboxing defines which files c(...TRUNCATED)	{"source":"harbor","trajectory_path":"exports/20260501T073334Z-qodex-teacher-v0.1-final/sanitized_at(...TRUNCATED)
[{"role":"system","content":"<permissions instructions>\nFilesystem sandboxing defines which files c(...TRUNCATED)	{"source":"harbor","trajectory_path":"exports/20260501T073334Z-qodex-teacher-v0.1-final/sanitized_at(...TRUNCATED)

End of preview.

Qodex Teacher Codex R1 48k

Codex CLI teacher trajectories rendered as Qwen ChatML with a 48k token budget.

Files

data/train.chatml.jsonl: 528 ChatML rows.
data/train.prompt_completion.jsonl: prompt/completion expansion for SFT tooling.
manifest.json: source export manifest.
reports/: token-budget and run-lineage reports.
CHECKSUMS.sha256: SHA-256 checksums for primary artifacts.

Source

Canonical archived source: archive/20260502-old-outputs/20260501T073334Z-qodex-teacher-v0.1-final/token_budget/2026-05-01_00-40-56_PDT-qwen36-48k-no-thinking/qwen_chatml_train_48k.jsonl

The ChatML file SHA-256 is: d29c8e7ffcbfb42d3079b0090d05bfbf64ecec514b4c1c7c5c8c8dfffe246ec8.

Downloads last month: 92

Total file size:

869 MB