mirror of
https://github.com/huggingface/lerobot.git
synced 2026-07-06 01:27:08 +00:00
johnnynunez
20c0f07858
Isaac-GR00T applies dual state regularization during fine-tuning: raw-state zeroing driven by the processor sidecar's state_dropout_prob (0.2 for the inspected N1.7 checkpoint) plus encoded-feature dropout. Baseline LeRobot kept the processor in deterministic mode, so the raw-state dropout never activated (RCA Tier-2 contributor to the LeRobot-trained SO-101 failures). - GrootN17PackInputsStep: runtime-only 'training' flag + state_dropout_prob; whole-sample state zeroing gated on torch.is_grad_enabled() so eval and no_grad validation paths are unaffected - sidecar loader reads state_dropout_prob from processor_config.json - state_dropout_prob serializes with the step; the training flag intentionally does not (reloaded pipelines default to eval, re-enabled only when processors are rebuilt with dataset_meta) - _set_groot_preprocessor_training toggles any dataclass step exposing a 'training' field on serialized-pipeline reloads Verification: tests/policies/groot/test_groot_state_dropout.py (4 passed) on RTX PRO 6000 / CUDA 13.3.