Downloads · 30 days
14
45% of all-time downloads
0915_isaacsim_auto_only_model_200k_steps
marin6670/0915_isaacsim_auto_only_model_200k_steps
0915_isaacsim_auto_only_model_200k_steps is a robotics model from marin6670. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for lerobot.
SmolVLA fine-tuned for 200,000 optimizer steps on the auto-only SO101 Isaac Sim dataset.
All-time downloads
31
Public
Parameters
450M
907 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors907 MB · 100%
Parameter types
How the weights are stored.
BF16447M · 99%
Base models
Model card
From the Hugging Face model README
0915_isaacsim_auto_only_model_200k_steps
SmolVLA fine-tuned for 200,000 optimizer steps on the auto-only SO101 Isaac Sim dataset.
| Setting | Value |
|---|---|
| Base model | lerobot/smolvla_base |
| Dataset | 0915_isaacsim_so101_auto_block_basketball_coca_cola_samsung_tv_remote_control_dataset |
| Training episodes | 200; 50 per target |
| Batch size | 8 |
| Seed | 1000 |
| Vision encoder | Frozen |
| Train expert only / state projection | True / True |
| Learning rate | 0.0001; 1,000 warmup steps; cosine decay to 0.0000025 |
| Chunk size / action steps | 50 / 50 |
| Camera mapping | front→camera1, top→camera2, wrist→camera3 |
The final 200,000-step inference checkpoint and preprocessing/postprocessing statistics are included.
Optimizer and RNG resume state remain with the original local training run.
The checkpoint weights are unchanged; repository/job references use the publication names.
The original training configuration is preserved under provenance/.
Evaluation results are pending. No success rate is claimed in this initial publication.
- Task
- Robotics
- Library
- lerobot
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026