Views
No views yet
| atomic | composite (chained) | |
|---|---|---|
| term_head_from_n15base (this SFT) | 45.4% (18 tasks) | 0.6% (16 tasks) |
Termination head fires correctly under N1.5; chained-composite is horizon/threshold-sensitive (controller: EMA + threshold + debounce + buffer + min_steps).
sft_term_head_from_n15base_120k/ — the SFT checkpoint-120000 (full: model safetensors
optimizer.pt + scheduler/rng → resumable). embodiment robocasa_panda_omron, action_horizon 16, bf16/fp32.rl_atomic/{closeblenderlid,closefridge,closetoasterovendoor}/ — atomic RL ckpts at
global_step_80 (FSDP dcp_checkpoint + consolidated model_state_dict/full_weights.pt,
action-head LoRA r64/α128 unmerged). Convert to a loadable HF dir with convert_rl_ckpt.py
(merges LoRA, drops PPO value head) — see the code repo.tianyu →
n15base_subtask_termhead_rl/ (see README.md + *.patch).nvidia/GR00T-N1.5-3B; --dataset_soup subtask_full --use_termination_head --termination_coeff 0.1 --progress_coeff 0.05, 120k steps, 2×H100.