admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-08-08 09:29:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(g05): trim validation details

Browse Source
This commit is contained in:
Pepijn
2026-07-29 19:15:12 +02:00
parent e6524cbfa8
commit 47f845ac5d
1 changed files with 1 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/source/g05.mdx
+1 -35
View File
@@ -229,30 +229,7 @@ Do not override checkpoint contract fields unless deliberately converting or
validating another embodiment. Incompatible action heads, dimensions, horizons,
processor modes, and normalization contracts are rejected during loading.
## Evaluation and Validation
CPU unit tests cover factory loading, config incompatibilities, prompt pass-through,
LIBERO and `atomic_4` mappings, padding masks, inverse action projection, a finite
forward/backward/update, optimizer-group wiring, and save/reload parity:
```bash
uv run pytest tests/policies/g05 tests/runtime/test_g05_adapter.py -q
uv run ruff check src/lerobot/policies/g05 tests/policies/g05
```
The converted private `g05_base` checkpoint strict-loaded all 945 native model
tensors, and its ActionCodec sidecar strict-loaded all 208 tensors, with no
missing, unexpected, or shape-mismatched keys. Prompt token IDs and masks match
the released runtime exactly. ActionCodec code IDs match exactly; decoded values
differ only by normal floating-point noise. A batch-size-one System 1 flow smoke
produced a finite `[1, 32, 27]` action chunk on an RTX 5090.
The same native base checkpoint completed a real joint language/action forward
and backward on the RTX 5090. It produced finite `ce_loss=13.8141` and
`fm_loss=1.32647`, finite gradients for all 945 model tensors, all six optimizer
groups, and 19.32 GiB peak allocated CUDA memory. A System 2 smoke generated
`Subtask: grasp and lift the red cup with the right gripper` and a finite
same-pass `[1, 32, 27]` action in 1.07 seconds at 11.0 GiB peak.
## Evaluation
A 50-episode LIBERO/RoboTwin success-rate comparison additionally requires the
matching simulator, task assets, reset seeds, and author evaluator; no task-level
@@ -277,17 +254,6 @@ lerobot-eval \
--output_dir=outputs/g05-libero-lerobot-eval
```
The author-oracle command for the same 50-trial gate is:
```bash
LIBERO_CONFIG_PATH=$(pwd)/experiments/libero \
bash scripts/run/eval_libero.sh checkpoints/g05-libero/model.pt \
--suites "libero_goal" \
--num_trials 50 \
--num_parallel 1 \
--output_dir outputs/g05-libero-author-eval
```
## References
- [OpenGalaxea G0.5 model](https://huggingface.co/OpenGalaxea/G05)