---
license: other
tags:
- robotics
- gr00t
- isaac
- humanoid
base_model: nvidia/GR00T-N1.7-3B
---

# GR00T fine-tune

Fine-tuned from `nvidia/GR00T-N1.7-3B` on 2026-05-26T22:35:50+00:00.
Embodiment: `UNITREE_G1_SONIC`. Trained on 1 GPUs.

## Hyperparameters

```
timestamp           = 2026-05-26T21:02:27+00:00
log_file            = /home/ubuntu/groot-files/logs/train-2026-05-26-210227.log
base_model          = nvidia/GR00T-N1.7-3B
embodiment_tag      = UNITREE_G1_SONIC
dataset_dir         = /home/ubuntu/groot-files/dataset
hf_dataset          = LucaFrat/dataset_100
checkpoint_dir      = /home/ubuntu/groot-files/checkpoints/g1_finetune
num_gpus            = 1
visible_gpu         = 1
global_batch_size   = 64
max_steps           = 15000
save_steps          = 3000
save_total_limit    = 10
learning_rate       = 1e-4
warmup_ratio        = 0.05
weight_decay        = 1e-5
dataloader_workers  = 6
resume              = <none>
use_wandb           = 1
wandb_project       = groot-finetune
wandb_run_name      = <auto>
```

## Checkpoints

Intermediate checkpoints (`checkpoint-N/`) are pushed incrementally during
training; the top-level files in this repo are the final model state.