pi05_telearms_v5_exp_random_50

Final checkpoint: step 30,000.

π₀.₅ (lerobot/pi05_base) full fine-tune on mliu48/telearms-yam-cube-v5-exp-random-50 (revision ad16b769): 500 simulated bimanual YAM demonstrations of 10 tasks, 495,157 frames at 30 Hz, three 224×224 cameras, no domain randomization.

Selection. 50 demonstrations per task drawn at random from all successful demonstrations of the task in the full dataset that have a demo score and a rated player ELO. The Random sets are nested: Random-50 is contained in Random-100, and so on up to Random-1500.

One of eight v5 experiment runs (Random-50/100/500/1000/1500, Elo-1500, Score-1500, DemInf-1500) trained with the same recipe and the same 15.36M-sample budget so they can be compared.

• Code: helen9975/RoboEval-telearms branch PI05_training @ 9dc9e9f plus local changes (NaN guards, PyAV logging fix for data-loading speed, configurable minimum episodes per task), LeRobot 0.6.1 @ e40b58a8 with the repo's patch (tools/install_lerobot_patch.py).
• Full fine-tune (LLM + vision + action expert), bf16, gradient checkpointing; per-task prompt variants (meta/task_prompt_variants.json); no episodes held out, so there is no validation loss.
• 8 × H100 (1 node), batch 64/GPU (global 512), 30,000 steps = 15.36M samples; this checkpoint has seen 15.36M of them.
• AdamW (β = 0.9, 0.95, weight decay 0.01), peak LR 1e-4 (2.5e-5 × sqrt(512/32)), 1,000 warmup steps, cosine decay to 1e-5 over 30,000 steps; 50-step action chunks; relative actions with absolute grippers.
• Recent training loss: 0.006.
• These files are the checkpoint's pretrained_model/.
• Evaluation: not yet evaluated in simulation.