Aether258/pi05_bi_task1_all_step8000

pi05_bi — task1_all — step 8000

openpi pi05_bi checkpoint, snapshot at training step 8000. Task: "Use the left hand to pick up the black tube, and then transfer it to the right hand and place it into the rack."

Data

Merged from three LeRobot v2.1 datasets (30 fps, images embedded in parquet, total_videos=0):

source	episodes	frames
KaiyueChen/task1_01	550	375,061
KaiyueChen/task1_02	200	130,902
KaiyueChen/task1_03	200	114,987
merged	950	620,950

task1_01 shipped with the placeholder task string perform manipulation task while 02/03 carried the full description. Since prompt_from_task=True feeds this string to the model, all episodes were unified to the 02/03 wording at merge time — otherwise 58% of the data would train against an uninformative prompt.

Split (per-source 10% held out, seed 42): train 855 / val_seen 95 / val_unseen 95. Normalization statistics were computed over the train split only.

Model & training

• 6 camera streams: camera0, camera1, tactile_{left,right}_{0,1}
• state_dim=20, action_dim=20, action_horizon=50
• LoRA on the PaliGemma LLM (rank 16) and the action expert (rank 32)
• The SigLIP vision tower is fully fine-tuned, not LoRA — openpi's get_freeze_filter() matches .*llm.* only, so PaliGemma/img/* stays trainable. That is 413M of the 463M trainable parameters (89.8%).
• batch size 128, FSDP over 2×A100-80GB, ema_decay=None
• CosineDecaySchedule defaults: peak_lr 2.5e-5, warmup 1000, decay_steps 30000
• init from gs://openpi-assets/checkpoints/pi05_base/params

One epoch is 4356 steps, so step 8000 ≈ 1.8 epochs.

Validation at this checkpoint

Loss is the flow-matching training objective evaluated with train=False (image augmentation disabled), averaged over a fixed set of batches with a fixed rng so successive points differ only by the model.

step	val_seen	val_unseen
2000	0.0575	0.0534
4000	0.0530	0.0501
6000	0.0497	0.0482
8000	0.0483	0.0470

val_unseen was still decreasing monotonically at this checkpoint — no overfitting turn had occurred yet. (A previous run on a different dataset bottomed out at step 8000 and then degraded, which is why this step was snapshotted.)

Caveat on the numbers: validation used val_batches=20 at batch size 128 = 2560 frames, and episodes here average 653 frames, so each evaluation covers only the first 4 episodes of each split (5.4%). The absolute trend of val_unseen is meaningful (identical episodes and rng every time), but the seen-vs-unseen difference rests on 4 episodes per side and should not be read as a generalization gap.

Contents

Orbax checkpoint: params/, train_state/, assets/, _CHECKPOINT_METADATA.