Downloads · 30 days
0
dit_block_tower_baseline
pravsels/dit_block_tower_baseline
dit_block_tower_baseline is a machine learning model from pravsels. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Diffusion Transformer policy for the build block tower task, trained on 6 datasets (1 base + 5 DAgger rounds, ~341k human-control frames).
Access
Public
Updated Apr 10, 2026
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Access
- Public
- Created
- Apr 10, 2026
- Updated
- Apr 10, 2026
- SHA
- 31395080
Model card
From the Hugging Face model README
DiT Block Tower Baseline v1
Diffusion Transformer policy for the build block tower task, trained on 6 datasets (1 base + 5 DAgger rounds, ~341k human-control frames).
Status: Partial run — 35,000 / 50,000 steps completed (hit 24h walltime). Loss was still decreasing at cutoff.
Model
| Architecture | Diffusion Transformer (DiT) |
| Vision encoder | CLIP ViT-B/16 (per-camera, lr_mult=0.1) |
| Text encoder | CLIP ViT-B/16 |
| Transformer | 512 hidden, 6 layers, 8 heads |
| Diffusion | DDPM, 100 steps, squaredcos_cap_v2 |
| State dim | 16 (7 joint pos + 9 eef rot6d) |
| Action dim | 17 (7 joint cmd + 9 eef rot6d + 1 gripper) |
| Cameras | front (480x640), wrist (480x640) |
Training
| Parameter | Value |
|---|---|
| Batch size | 64 per GPU (256 global, 4x GH200) |
| Train steps | 50,000 (35,000 completed) |
| Learning rate | 2e-5, cosine schedule |
| Warmup | 500 steps |
| Horizon | 100 |
| Action steps | 50 |
| Obs steps | 2 |
| AMP | enabled |
Datasets
| Dataset | Role |
|---|---|
villekuosmanen/build_block_tower | Base demonstrations |
villekuosmanen/dAgger_build_block_tower_1.0.0 | DAgger round 1 |
villekuosmanen/dAgger_build_block_tower_1.1.0 | DAgger round 2 |
villekuosmanen/dAgger_build_block_tower_1.2.0 | DAgger round 3 |
villekuosmanen/dAgger_build_block_tower_1.3.0 | DAgger round 4 |
villekuosmanen/dAgger_build_block_tower_1.4.0 | DAgger round 5 |
DAgger policy frames filtered out via ControlModePlugin (only human-control frames used).
Files
README.md
TRAINING_LOG.md
assets/
ramen_stats.pt # Normalization statistics
valid_indices.json # Per-dataset valid frame indices after DAgger filtering
checkpoints/
35000/
model.safetensors # Model weights (inference + fine-tuning)
config.json # Resolved model config
Checkpoint Integrity
sha256 (checkpoint files):
6192188a config.json
8f00265f model.safetensors
df43463f ramen_stats.pt
Full hashes:
6192188a6a705cb6ab1632234a1b4724935d42b311c1d01fff16b0eee5c00e4a config.json
8f00265f043db4bf520441bf8eec07b6ccdcbff41f6db7a4852dea25218d2ac0 model.safetensors
df43463ff96e90b952fb3e7bc971cd7c584308acfab82ba29d0560318e2b9d2d ramen_stats.pt
Reproduce with:
cd checkpoints/35000 && sha256sum config.json model.safetensors
cd assets && sha256sum ramen_stats.pt
W&B
Training curves: https://wandb.ai/pravsels/dit_block_tower/runs/pv8q64et
Usage
This checkpoint is from the multitask_dit_policy repo, branch stage1-multimodal-abstraction.
- Created
- Apr 10, 2026
- Updated
- Apr 10, 2026