AlignX
Collection
A large-scale dataset of over 1.3 million personalized preference examples • 7 items • Updated • 1
Error code: DatasetGenerationError
Exception: TypeError
Message: Couldn't cast array of type
struct<from: string, history: list<item: struct<answer: string, chosen: string, rejected: string, responseA: string, responseB: string, task: string, value: string>>>
to
{'answer': Value('string'), 'chosen': Value('string'), 'chosen_log': Value('float64'), 'from': Value('string'), 'pre_prompt': Value('string'), 'rejected': Value('string'), 'rejected_log': Value('float64'), 'responseA': Value('string'), 'responseB': Value('string'), 'task': Value('string'), 'value': Value('string')}
Traceback: Traceback (most recent call last):
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1831, in _prepare_split_single
writer.write_table(table)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/arrow_writer.py", line 644, in write_table
pa_table = table_cast(pa_table, self._schema)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2272, in table_cast
return cast_table_to_schema(table, schema)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2223, in cast_table_to_schema
arrays = [
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2224, in <listcomp>
cast_array_to_feature(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 1795, in wrapper
return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 1795, in <listcomp>
return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/table.py", line 2092, in cast_array_to_feature
raise TypeError(f"Couldn't cast array of type\n{_short_str(array.type)}\nto\n{_short_str(feature)}")
TypeError: Couldn't cast array of type
struct<from: string, history: list<item: struct<answer: string, chosen: string, rejected: string, responseA: string, responseB: string, task: string, value: string>>>
to
{'answer': Value('string'), 'chosen': Value('string'), 'chosen_log': Value('float64'), 'from': Value('string'), 'pre_prompt': Value('string'), 'rejected': Value('string'), 'rejected_log': Value('float64'), 'responseA': Value('string'), 'responseB': Value('string'), 'task': Value('string'), 'value': Value('string')}
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 1456, 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 1055, in convert_to_parquet
builder.download_and_prepare(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 894, in download_and_prepare
self._download_and_prepare(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 970, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1702, in _prepare_split
for job_id, done, content in self._prepare_split_single(
File "/src/services/worker/.venv/lib/python3.9/site-packages/datasets/builder.py", line 1858, 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.
0 dict | 1 dict |
|---|---|
{
"answer": "Response A",
"chosen": "So your argument is, essentially, when people become too stupid to understand something, it is time to modify that thing in order to take into account the general dumbing down of the population. Brilliant!\n",
"chosen_log": 10.650071144104004,
"from": "human",
"pre_prompt"... | {
"from": "assistant",
"ground_truth": {
"value": "Response A"
}
} |
{
"answer": "Response A",
"chosen": "As a side topic I took a quantitative finance class from coursera and it relied heavily on the efficient market theory, where everything is suppose to be built into the price. I would like to find a similar course like you speak of using fundamental inputs instead of price histo... | {
"from": "assistant",
"ground_truth": {
"value": "Response A"
}
} |
{
"answer": "Response B",
"chosen": "Imagine Hillary without the lighthearted sense of humor.\n",
"chosen_log": 5.5038557052612305,
"from": "human",
"pre_prompt": "Generate the user's preference based on their historical behavior.\nThe following aspects can be referred to when analyzing user preferences.\nAge... | {
"from": "assistant",
"ground_truth": {
"value": "Response B"
}
} |
{
"answer": "Response A",
"chosen": "I'll be there!\n",
"chosen_log": 0.6309101581573481,
"from": "human",
"pre_prompt": "Generate the user's preference based on their historical behavior.\nThe following aspects can be referred to when analyzing user preferences.\nAge group; Gender; Degree of Neuroticism in t... | {
"from": "assistant",
"ground_truth": {
"value": "Response A"
}
} |
{
"answer": "Response B",
"chosen": "Voting itself is not an act of violence, no more so than writing any other name on a piece of paper. Both of which are speech and follow the standards for speech, which is that it can only be considered violence if it creates or intends to create violence. A decree or statement ... | {
"from": "assistant",
"ground_truth": {
"value": "Response B"
}
} |
{
"answer": "Response A",
"chosen": "This about sums up my entire childhood with my libertarian dad. He still says gay as a synonym for stupid :(\n",
"chosen_log": 4.057146072387695,
"from": "human",
"pre_prompt": "Generate the user's preference based on their historical behavior.\nThe following aspects can b... | {
"from": "assistant",
"ground_truth": {
"value": "Response A"
}
} |
{
"answer": "Response A",
"chosen": "1. All government programs are ultimately backed up by the initiation of the use of force. A voluntary interaction is win-win by definition. A forcible interaction (that is, interaction without the object's consent), is win-lose by definition. All government programs are forcibl... | {
"from": "assistant",
"ground_truth": {
"value": "Response A"
}
} |
{
"answer": "Response B",
"chosen": "This had been panned for months. People in Va tired of CW monuments being removed and were rallying to keep a statue of Robert E Lee from being removed. The rebel flag is not a symbol of racism. It's a battle flag from the confederate army and represents Souther Herritage. Slave... | {
"from": "assistant",
"ground_truth": {
"value": "Response B"
}
} |
{
"answer": "Response A",
"chosen": "Are you able to embrace suck?\n\nAre you able to embrace boring, sometimes demeaning suck, sometimes enhanced by assholes?\n\nAre you able to deal with a fight between your dream and reality and reality winning, hands-down?\n\nSure, then come. (No/s)\n",
"chosen_log": 14.67221... | {
"from": "assistant",
"ground_truth": {
"value": "Response A"
}
} |
{
"answer": "Response A",
"chosen": "First of all badass mom anything you want\nClothes bras \nShoes etc.\n",
"chosen_log": 3.752399444580078,
"from": "human",
"pre_prompt": "Generate the user's preference based on their historical behavior.\nThe following aspects can be referred to when analyzing user prefer... | {
"from": "assistant",
"ground_truth": {
"value": "Response A"
}
} |
{
"answer": "Response A",
"chosen": "Richest Man in Babylon recommends living on 70% of your take home, paying off debt with 20% and saving 10%.\n\nI would pay off the CC debt immediately with any non-registered investments.\n",
"chosen_log": 14.751352310180664,
"from": "human",
"pre_prompt": "Generate the us... | {
"from": "assistant",
"ground_truth": {
"value": "Response A"
}
} |
{
"answer": "Response A",
"chosen": "I've found the discomfort is perfectly manageable when it comes to arms and legs, but for more sensitive areas like the chest and stomach, a paracetamol tablet and a half a bottle of wine really helps. But it's absolutely worth it, given that hair takes a lot longer to grow back... | {
"from": "assistant",
"ground_truth": {
"value": "Response A"
}
} |