GR00T N1.5 finetuned on an SO-101 sponge/marker manipulation dataset. Intermediate checkpoint at step 10,000 of a 30,000-step run.

This is the first checkpoint in this project trained on correctly-aligned video frames. All earlier sponge-marker checkpoints (the delta-* and frozenllm-* families) were trained with the torchcodec video backend, which misaligned roughly 35% of frames. This run uses decord (NVIDIA's recommended backend for the H.264 data). Do not compare metrics against the earlier families as if they differ only by recipe — the input data differed.

Stock GR00T N1.5 finetuning defaults — the same configuration NVIDIA's LIBERO checkpoints use. Backbone frozen, action head tuned.

sponge_marker_merged_video — LeRobot-format, merged from two SO-101 teleop datasets (grab sponge → place bowl; grab marker → place cup).

Gradients are stable. The only spikes are steps 10–40 during warmup; after step 2,000 the maximum grad_norm over 8,000 steps is 0.93. The heavy-tail gradient spiking seen previously on delta-action targets (with adam_beta2=0.999) does not appear here, so adam_beta2 was left at its default.

wandb: mkpongm-uci/gr00t-sponge-marker

No robot evaluation has been run on this checkpoint. Training loss alone cannot establish that this policy is useful.

On absolute actions, a policy can reach very low training loss by learning to echo the current joint state rather than predicting the next action — a shortcut that accounted for 94.9% of predicted variance in an earlier run on this dataset. The loss curve here (below 0.03 within 300 steps, then a slow grind) is consistent with both genuine learning and that shortcut; the metric cannot distinguish them. Treat the numbers above as evidence the run is healthy, not that it works.

Because of this, a later checkpoint is not automatically better than this one. A shortcut-fitted policy can degrade with additional steps, so 10k is worth evaluating alongside 30k rather than assuming the final checkpoint wins.

Serve with the plain absolute-action data config:

Requires Isaac-GR00T and the project's so101_configs.py. No normalization changes are needed — unlike the delta-* checkpoints, which require so101_delta_configs.py and a matching gripper normalization mode.

Model weights only (2 safetensors shards + index), config.json, and experiment_cfg/metadata.json (dataset statistics required for serving). Optimizer state is not included, so this checkpoint is servable but not resumable.