OAT Dense LIBERO-10 — Checkpoint Epoch 950
Hugging Face model repository for a dense cross-attention OAT policy trained on
LIBERO-10 (N500) . Snapshot at epoch 950 during run oat_dense_with_uid_long_0530_220204.
This checkpoint is the best point on the training ladder after resume from ep-0700
(in-loop peak 52.67% ). Phase B confirm: 50.60% ± 0.76% on LIBERO-10.
Quick download
1 huggingface-cli download hackhackhack66666/oat-dense-blt-950 ep-0950.ckpt \
2 --local-dir ./checkpoints
Files
File Description ep-0950.ckptPyTorch workspace checkpoint (~729 MB) training_logs.jsonlFull training JSONL (train/val curves) training_metrics_dashboard.pngTraining loss / val / reconst MSE dashboard training_snapshot_ep0950.jsonOffline metrics at epoch 950 sim_eval/Phase A screen eval (30 ep/task) sim_eval_phase_b/Phase B confirm eval (50 ep/task, 3 seeds) experiment_log_dense_visual_memory.mdExperiment journal
Metrics @ epoch 950
Train loss Val loss Reconst MSE Phase A SR Phase B SR (confirm) 2.0182993412017822 5.783568859100342 0.07388626039028168 52.7% 50.60% ± 0.76%
In-loop eval at ep 950 (same run, 30 ep/task): 52.67% — noisier than Phase B; use Phase B as the calibrated reference.
Visualizations
Training (offline)
Training metrics dashboard Sim eval — Phase A screen (30 ep/task)
Mean success rate: 52.7% — 30 episodes/task, 300 total rollouts, seed 1000 (single experiment).
Phase A sim eval dashboard Task SR KITCHEN_SCENE6_put_the_yellow_and_white_mug_in_the_microwave…86.7% KITCHEN_SCENE4_put_the_black_bowl_in_the_bottom_drawer_of_th…86.7% KITCHEN_SCENE3_turn_on_the_stove_and_put_the_moka_pot_on_it83.3% LIVING_ROOM_SCENE2_put_both_the_cream_cheese_box_and_the_but…73.3% STUDY_SCENE1_pick_up_the_book_and_place_it_in_the_back_compa…66.7% LIVING_ROOM_SCENE5_put_the_white_mug_on_the_left_plate_and_p…53.3% KITCHEN_SCENE8_put_both_moka_pots_on_the_stove53.3% LIVING_ROOM_SCENE6_put_the_white_mug_on_the_plate_and_put_th…20.0% LIVING_ROOM_SCENE2_put_both_the_alphabet_soup_and_the_tomato…3.3% LIVING_ROOM_SCENE1_put_both_the_alphabet_soup_and_the_cream_…0.0%
Sim eval — Phase B confirm (50 ep/task, 3 seeds)
Mean success rate: 50.60% ± 0.76% — official-style protocol for comparison with OAT paper (~56.3%).
Seeds 1000 / 1500 / 2000 (seed_stride=500), 500 rollouts total. Per-seed mean SR: 52.0% · 49.4% · 50.4% .
Compared to ep-0700 Phase B confirm (47.60% ± 1.75% ): +3.0 pp on the calibrated protocol.
Phase B confirm dashboard Task SR KITCHEN_SCENE4_put_the_black_bowl_in_the_bottom_drawer_of_th…94.7% KITCHEN_SCENE3_turn_on_the_stove_and_put_the_moka_pot_on_it88.7% KITCHEN_SCENE6_put_the_yellow_and_white_mug_in_the_microwave…74.0% STUDY_SCENE1_pick_up_the_book_and_place_it_in_the_back_compa…66.0% LIVING_ROOM_SCENE2_put_both_the_cream_cheese_box_and_the_but…56.7% LIVING_ROOM_SCENE5_put_the_white_mug_on_the_left_plate_and_p…48.0% KITCHEN_SCENE8_put_both_moka_pots_on_the_stove43.3% LIVING_ROOM_SCENE6_put_the_white_mug_on_the_plate_and_put_th…34.0% LIVING_ROOM_SCENE2_put_both_the_alphabet_soup_and_the_tomato…0.7% LIVING_ROOM_SCENE1_put_both_the_alphabet_soup_and_the_cream_…0.0%
Ladder context
Paper OAT8 on LIBERO-10: ~56.3% mean success rate (external reference).
Model configuration
Policy: OAT with use_dense_visual_memory=true (spatial visual tokens + cross-attn)State memory: enabled (use_state_memory_tokens=true)Task UID: enabled in state tokensDataset: libero10_N500.zarrEmbed dim: 256Tokenizer: tokenizer_ep-0950_mse-0.002.ckpt (Mirageinv/oat)
Citation
If you use this checkpoint, please cite OAT: Ordered Action Tokenization and specify
epoch 950 of the dense LIBERO-10 ladder.
Source:
GadzhiAskhabaliev/OAT-BLT-Dense (
BLT-OAT-dense branch).
