These runs used the patched Coffee_D2 eval reset path that restores dataset model_file and initial states[0].
Camera override mode for this dataset is none.
The local eval summaries are included under metadata/<model>/.
Dataset action open-loop replay was checked separately. Stored final states are successful, but action replay under the current stack only reached official task success for 54/200 demos, indicating open-loop replay drift / stack sensitivity rather than a simple stored-state failure.

Layout

text

checkpoints/
  dpc/{latest.ckpt,best.ckpt}
  mail/{latest.ckpt,best.ckpt}
  maniflow/{latest.ckpt,best.ckpt}
  dispo/{latest.ckpt,best.ckpt}
metadata/
  <model>/{latest_eval.txt,eval_summary.csv,eval_summary.jsonl,hydra_config.yaml}
  replay_success_check/{replay_success.csv,replay_success.jsonl,replay_success_summary.*}

Junhyeong0411/mimicgen-coffee-ckpt

MimicGen Coffee_D2 Baseline Checkpoints

Latest Eval Snapshot

Notes

Layout

Junhyeong0411/
mimicgen-coffee-ckpt