Release LUMINA-2M v0.1.4 (2.4M params)
Browse files- README.md +9 -5
- model.pt +2 -2
- model.safetensors +1 -1
- pareto_front.png +0 -0
README.md
CHANGED
|
@@ -21,16 +21,16 @@ Trained on ACOPF datasets spanning **multiple network topologies**, LUMINA-2M ge
|
|
| 21 |
|
| 22 |
## Model Details
|
| 23 |
|
| 24 |
-
- **Version**: v0.1.
|
| 25 |
- **Model Architecture**: HGT
|
| 26 |
- **Total Parameters**: 2,375,548 (2.4M)
|
| 27 |
- **Trainable Parameters**: 2,375,548 (2.4M)
|
| 28 |
- **Training Case**: case14_ieee, case30_ieee, case57_ieee, case118_ieee, case500_goc, case2000_goc, case4661_sdet, case6470_rte, case10000_goc, case13659_pegase
|
| 29 |
- **Training Data Size**: 240,000 samples per case
|
| 30 |
-
- **Training Date**: 2026-08-
|
| 31 |
-
- **Training Epochs**:
|
| 32 |
- **Loss Type**: Augmented Lagrangian
|
| 33 |
-
- **Final Validation Loss**: 0.
|
| 34 |
|
| 35 |
> **Note**: The validation loss is only comparable across releases that share the same **Loss Type**. For example, an Augmented Lagrangian loss includes constraint-violation penalties and Lagrangian terms, so its magnitude is not directly comparable to a plain MSE loss.
|
| 36 |
|
|
@@ -47,6 +47,7 @@ This repository contains the model in multiple formats:
|
|
| 47 |
- `model.pt` - Complete PyTorch checkpoint with metadata and config
|
| 48 |
- `model.safetensors` - Model weights in SafeTensors format (recommended)
|
| 49 |
- `requirements.txt` - Required Python libraries
|
|
|
|
| 50 |
|
| 51 |
## Installation
|
| 52 |
|
|
@@ -158,8 +159,11 @@ https://doi.org/10.48550/arXiv.2406.07234.
|
|
| 158 |
|
| 159 |
## Release History
|
| 160 |
|
|
|
|
|
|
|
| 161 |
| Version | Date | Epochs | Val Loss | Training Case |
|
| 162 |
|---------|------|--------|----------|---------------|
|
|
|
|
| 163 |
| [v0.1.3](https://huggingface.co/argonne/LUMINA-2M/tree/v0.1.3) | 2026-08-12 | 69 | 0.190340 | full-topology + N-1 + FT |
|
| 164 |
| [v0.1.2](https://huggingface.co/argonne/LUMINA-2M/tree/v0.1.2) | 2026-07-31 | 63 | 0.120890 | full-topology + N-1 |
|
| 165 |
| [v0.1.1](https://huggingface.co/argonne/LUMINA-2M/tree/v0.1.1) | 2026-07-16 | 34 | 0.052400 | case14_ieee, case30_ieee, case57_ieee, case118_ieee, case500_goc, case2000_goc, case4661_sdet, case6470_rte, case10000_goc, case13659_pegase |
|
|
@@ -193,6 +197,6 @@ This research used resources of the National Energy Research Scientific Computin
|
|
| 193 |
|
| 194 |
## License
|
| 195 |
|
| 196 |
-
Released under the Apache License, Version 2.0. See the bundled [`LICENSE`](https://huggingface.co/argonne/LUMINA-2M/blob/v0.1.
|
| 197 |
|
| 198 |
Copyright 2026 UChicago Argonne, LLC.
|
|
|
|
| 21 |
|
| 22 |
## Model Details
|
| 23 |
|
| 24 |
+
- **Version**: v0.1.4
|
| 25 |
- **Model Architecture**: HGT
|
| 26 |
- **Total Parameters**: 2,375,548 (2.4M)
|
| 27 |
- **Trainable Parameters**: 2,375,548 (2.4M)
|
| 28 |
- **Training Case**: case14_ieee, case30_ieee, case57_ieee, case118_ieee, case500_goc, case2000_goc, case4661_sdet, case6470_rte, case10000_goc, case13659_pegase
|
| 29 |
- **Training Data Size**: 240,000 samples per case
|
| 30 |
+
- **Training Date**: 2026-08-27
|
| 31 |
+
- **Training Epochs**: 71
|
| 32 |
- **Loss Type**: Augmented Lagrangian
|
| 33 |
+
- **Final Validation Loss**: 0.531175
|
| 34 |
|
| 35 |
> **Note**: The validation loss is only comparable across releases that share the same **Loss Type**. For example, an Augmented Lagrangian loss includes constraint-violation penalties and Lagrangian terms, so its magnitude is not directly comparable to a plain MSE loss.
|
| 36 |
|
|
|
|
| 47 |
- `model.pt` - Complete PyTorch checkpoint with metadata and config
|
| 48 |
- `model.safetensors` - Model weights in SafeTensors format (recommended)
|
| 49 |
- `requirements.txt` - Required Python libraries
|
| 50 |
+
- `pareto_front.png` - Accuracy vs. constraint-violation plot across all released checkpoints (see Release History)
|
| 51 |
|
| 52 |
## Installation
|
| 53 |
|
|
|
|
| 159 |
|
| 160 |
## Release History
|
| 161 |
|
| 162 |
+

|
| 163 |
+
|
| 164 |
| Version | Date | Epochs | Val Loss | Training Case |
|
| 165 |
|---------|------|--------|----------|---------------|
|
| 166 |
+
| [v0.1.4](https://huggingface.co/argonne/LUMINA-2M/tree/v0.1.4) | 2026-08-27 | 71 | 0.531175 | full-topology + N-1 + FT |
|
| 167 |
| [v0.1.3](https://huggingface.co/argonne/LUMINA-2M/tree/v0.1.3) | 2026-08-12 | 69 | 0.190340 | full-topology + N-1 + FT |
|
| 168 |
| [v0.1.2](https://huggingface.co/argonne/LUMINA-2M/tree/v0.1.2) | 2026-07-31 | 63 | 0.120890 | full-topology + N-1 |
|
| 169 |
| [v0.1.1](https://huggingface.co/argonne/LUMINA-2M/tree/v0.1.1) | 2026-07-16 | 34 | 0.052400 | case14_ieee, case30_ieee, case57_ieee, case118_ieee, case500_goc, case2000_goc, case4661_sdet, case6470_rte, case10000_goc, case13659_pegase |
|
|
|
|
| 197 |
|
| 198 |
## License
|
| 199 |
|
| 200 |
+
Released under the Apache License, Version 2.0. See the bundled [`LICENSE`](https://huggingface.co/argonne/LUMINA-2M/blob/v0.1.4/LICENSE) and [`NOTICE`](https://huggingface.co/argonne/LUMINA-2M/blob/v0.1.4/NOTICE) files for the full terms and attribution.
|
| 201 |
|
| 202 |
Copyright 2026 UChicago Argonne, LLC.
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a01fc984821090cefe1de24218790caa0dbcc70d6ff71b670eae19716906669
|
| 3 |
+
size 28499319
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9520848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:002e3faea331731d2fcd5bae16db8508bf91ba2125532af0dee41f0dbcace03d
|
| 3 |
size 9520848
|
pareto_front.png
ADDED
|