Modelpublic

rookierufus/kinematic-oracles-ego10k

sourceHugging Facemitupdated 3mo agoView on Hugging Face

0likes

Model Card

Kinematic Oracles — Ego10k

Model: Pθ (forward/causal) + Qθ (backward/anti-causal) kinematic predictors on V-JEPA ViT-Base latents. Architecture: Depthwise-Separable Conv3D + RetractionMap (~613K params each, 1.2M total). Loss: Adaptive volatility-gated Huber (δema), AdamW, cosine annealing, FP32 mandate. **Dataset**: Egocentric-10K (ego-centric video), 151 videos → 5,026 tubelets (τkinetic=0.001, ε=0.678).

Run History

Run 001 — `δ_val=1.0` (hardcoded baseline)

Field	Value
Date	2026-06-23
Seed	42
δ_val	1.000000 (hardcoded — `compute_delta_val_streaming()` was too slow, bypassed)
δ_ema (final)	1.149586
Epochs	50
Best val loss	250.61
Identity baseline	475.50 (predict no change)
Improvement	47.3% over identity
Gate U (final)	Pθ=0.87, Qθ=0.88
Saturation warning	Epoch 30: P_θ U→0.90 (retraction map near-disabled)
Bug	`self.seed` not stored in trainer (AttributeError, patched)
Checkpoints	`checkpoints/oracle_epoch_*.pt` (35 of 50 pushed)
Deploy	`oracle_weights.pt`

Why another run? δ_val=1.0 was a guess — the data-driven compute_delta_val_streaming() was hanging due to an element-by-element Python loop (6.7B .item() calls). Fixing this should give a proper data-driven initial Huber threshold, potentially improving convergence.

Run 002 — `δ_val` data-driven (vectorized Welford)

Field	Value
Date	2026-06-23
Seed	42
δ_val	computed from validation set via vectorized Welford streaming
Fix	Replaced O(N_element) Python loop with per-tubelet `z.mean()/.var()` + batch-Welford merge (hours→seconds)
Epochs	50
Status	🏃 Training in progress...

Reproducibility

bash

# Data: builddotai/Egocentric-10K on HuggingFace
# V-JEPA: vjepa2_1_vitb_dist_vitG_384.pt (ViT-Base, 86.8M params)

cd "/root/the Compression problem"
python3 -m oracle.run \
  --data-dir /root/ego10k_data \
  --factories factory_001 factory_002 \
  --max-videos 500 \
  --epochs 50 \
  --cache-size 1000 \
  --batch-size 16 \
  --output-dir /root/oracle_output \
  --seed 42

Files

Path	Description
`checkpoints/oracle_epoch_*.pt`	Epoch checkpoints (Pθ + Qθ + optimizer state)
`oracle_weights.pt`	Frozen deploy weights (best val loss)
`training_log.json`	Per-epoch metrics (loss, lr, δ_ema, gate U)
`split.json`	Train/val video split (seed=42)
`latent_index.json`	Video→latent mapping, calibration params
`latents/*.pt`	Precomputed V-JEPA tubelets (FP16, auto-upcast to FP32)