ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix: prefer tabular files over archives in Tier 1 dataset preview

Browse source 
Tier 1 check-format was picking images.zip over testmini.parquet,
causing wrong columns (image/label) and broken VLM mapping.
Also log first VLM conversion failure instead of swallowing silently.
This commit is contained in:
Roland Tannous 2026-03-09 22:00:20 +00:00
commit 1c87a4400c
1 changed files with 6 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

6
studio/backend/utils/datasets/format_conversion.py
View file

@ -505,6 +505,8 @@ def convert_to_vlm_format(
batch_results[idx] = future.result()
except Exception as e:
failed_count += 1
if failed_count == 1:
print(f"⚠️ First VLM conversion failure: {type(e).__name__}: {e}")
if failed_count == 1:
logger.info(f"⚠️ First VLM conversion failure: {type(e).__name__}: {e}")
@ -525,8 +527,12 @@ def convert_to_vlm_format(
for sample in pbar:
try:
converted_list.append(_convert_single_sample(sample))
except Exception as e:
except Exception as e:
failed_count += 1
if failed_count == 1:
# Log the first failure to aid debugging
print(f"⚠️ First VLM conversion failure: {type(e).__name__}: {e}")
if failed_count == 1:
# Log the first failure to aid debugging
logger.info(f"⚠️ First VLM conversion failure: {type(e).__name__}: {e}")