Files
lerobot/examples
Pepijn ecbac17196 chore(training): align pi052_hirobot.slurm with the operator's actual command
Match the working SmolVLA2 launch pattern so the two SLURM scripts
are interchangeable:

  * literal NUM_PROCESSES / BATCH_SIZE / STEPS (no env-var defaults)
  * STEPS=10000 to match the next SmolVLA2 run
  * save_freq=$STEPS so only the final checkpoint is saved
  * dropouts 0.1/0.1/0.1 (mild — matches the operator's iteration)
  * flow_loss_weight / text_loss_weight come from the PI052Config
    defaults (10.0 / 1.0 per Pi 0.5 paper §IV.D), no need to pass
    them explicitly

Job name and policy_repo_id mirror the SmolVLA2 ``_tool-g2`` naming
so the two runs can be compared side-by-side in WandB.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 11:03:09 +02:00
..