datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
hy3-math-forensics-datasetflashback-forensics
Flashback Forensics
Labelled telemetry from training runs that were deliberately broken at a known
step. Every row is a few hundred bytes of per-step summary statistics; the
label is the step at which the fault was actually injected.
The point of the dataset: to make "how early can you tell a run went wrong?"
a measurable question instead of an anecdote.
Contents
config
rows
one row is
steps
21,600
one training step of one run: 128 sketch metrics +… See the full description on the dataset page: https://huggingface.co/datasets/NagaYu/flashback-forensics.