Dataset Viewer
The dataset viewer is not available for this subset.
Cannot get the split names for the config 'default' of the dataset.
Exception: SplitsNotFoundError
Message: The split names could not be parsed from the dataset config.
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 236, in _generate_tables
pa_table = paj.read_json(
^^^^^^^^^^^^^^
File "pyarrow/_json.pyx", line 342, in pyarrow._json.read_json
File "pyarrow/error.pxi", line 155, in pyarrow.lib.pyarrow_internal_check_status
File "pyarrow/error.pxi", line 92, in pyarrow.lib.check_status
pyarrow.lib.ArrowInvalid: JSON parse error: Column(/steps/[]/model_input/[]/content) changed from string to array in row 0
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/lib/python3.12/site-packages/datasets/inspect.py", line 286, in get_dataset_config_info
for split_generator in builder._split_generators(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 93, in _split_generators
pa_table = next(iter(self._generate_tables(**splits[0].gen_kwargs, allow_full_read=False)))[1]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 250, in _generate_tables
batch = json_encode_fields_in_json_lines(original_batch, json_field_paths)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/utils/json.py", line 90, in json_encode_fields_in_json_lines
examples = [ujson_loads(line) for line in original_batch.splitlines()]
^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/utils/json.py", line 20, in ujson_loads
return pd.io.json.ujson_loads(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected object or value
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/split_names.py", line 65, in compute_split_names_from_streaming_response
for split in get_dataset_split_names(
^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/inspect.py", line 340, in get_dataset_split_names
info = get_dataset_config_info(
^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/inspect.py", line 291, in get_dataset_config_info
raise SplitsNotFoundError("The split names could not be parsed from the dataset config.") from err
datasets.inspect.SplitsNotFoundError: The split names could not be parsed from the dataset config.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.
GPT-OSS 120B SWE-Agent Execution Traces
Full execution traces of GPT-OSS 120B running SWE-Agent on SWE-Bench (Full).
Dataset Structure
Each JSON file in traces/ corresponds to one SWE-Bench problem instance. The filename is the instance ID (e.g., django__django-12345.json).
Trace Schema
{
"instance_id": "django__django-12345",
"model": "GPT-OSS-120B",
"agent": "SWE-agent",
"total_steps": 15,
"total_run_duration_seconds": 120.5,
"exit_status": "submitted",
"submission": "<git diff patch>",
"model_stats": { ... },
"steps": [
{
"step_index": 0,
"timestamp": 1711500000.0,
"model_input": [ ... ],
"model_output": {
"raw_response": "full text response from the model",
"thought": "extracted reasoning/thought",
"action": "bash command or tool call",
"thinking_blocks": [],
"tool_calls": [],
"tool_call_ids": []
},
"tool_execution": {
"command": "find /repo -name '*.py' | head -20",
"start_timestamp": 1711500001.0,
"duration_seconds": 0.25,
"output": "file1.py\nfile2.py\n...",
"execution_time_reported": 0.25
},
"exit_status": null,
"done": false,
"submission": null
}
]
}
Generation Details
- Model: GPT-OSS 120B served locally via sglang with EAGLE3 speculative decoding (TP=2)
- Agent: SWE-Agent v1.1.0 with thought_action parsing
- Benchmark: SWE-Bench Full
- Downloads last month
- 70