STRATA v1.0 release

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+latlon_ne1024pg2.nc filter=lfs diff=lfs merge=lfs -text

ATTRIBUTION.md

@@ -0,0 +1,32 @@
+SCREAM-derived static forcing files — CC BY 4.0
+===============================================
+
+The following files in this repository are derived from the SCREAM (Simple
+Cloud-Resolving E3SM Atmosphere Model) simulation output that NVIDIA published
+as the STRATA-SCREAM datasets under the Creative Commons Attribution 4.0
+International license (https://creativecommons.org/licenses/by/4.0/; full text
+in third_party/CC-BY-4.0.txt):
+
+  phis.npy      surface geopotential (static forcing field)
+  sgh30.npy     standard deviation of sub-grid orography (static forcing field)
+  landfrac.npy  land fraction (static forcing field)
+
+All other files (model weights, normalization statistics, configuration and model
+card) are original NVIDIA works licensed under the OpenMDW License Agreement,
+version 1.1 (see LICENSE).
+
+Sources
+-------
+- STRATA-SCREAM datasets (CC BY 4.0), published by NVIDIA; dataset owner: E3SM Project,
+  U.S. Department of Energy. Simulations F20TR-SCREAMv1 (sdecadal) and F2010-SCREAMv1
+  (sdy1, sdy2) on the ne1024pg2 cubed-sphere grid.
+  https://huggingface.co/datasets/nvidia/STRATA-SCREAM-sdecadal
+  https://huggingface.co/datasets/nvidia/STRATA-SCREAM-sdy1
+  https://huggingface.co/datasets/nvidia/STRATA-SCREAM-sdy2
+  Original raw SCREAM output: https://portal.nersc.gov/archive/home/n/ndk/www/STRATA2026
+- SCREAM / E3SM: Caldwell, P. M., et al. (2021), Convection-Permitting Simulations With the
+  E3SM Global Atmosphere Model, J. Adv. Model. Earth Syst., https://doi.org/10.1029/2021MS002544
+
+Changes made by NVIDIA: the static fields were extracted from the simulation output,
+cast to 32-bit floats and stored as NumPy arrays in the model's ne1024pg2 column
+order; no values were modified.

CONTRIBUTING.md

@@ -0,0 +1 @@
+This project is currently not accepting contributions.

LICENSE

@@ -0,0 +1,49 @@
+OpenMDW License Agreement, version 1.1 (OpenMDW-1.1)
+
+By exercising rights granted to you under this agreement, you accept and agree
+to its terms.
+
+As used in this agreement, "Model Materials" means the materials provided to
+you under this agreement, consisting of: (1) one or more machine learning
+models (including architecture and parameters); and (2) all related artifacts
+(including associated data, documentation and software) that are provided to
+you hereunder.
+
+Subject to your compliance with this agreement, permission is hereby granted,
+free of charge, to deal in the Model Materials without restriction, including
+under all copyright, patent, database, and trade secret rights included or
+embodied therein.
+
+If you distribute any portion of the Model Materials, you shall retain in your
+distribution (1) a copy of this agreement, and (2) all copyright notices and
+other notices of origin included in the Model Materials that are applicable to
+your distribution.
+
+If you file, maintain, or voluntarily participate in a lawsuit against any
+person or entity asserting that the Model Materials directly or indirectly
+infringe any patent or copyright, then all rights and grants made to you
+hereunder are terminated, unless that lawsuit was in response to a
+corresponding lawsuit first brought against you.
+
+This agreement does not impose any restrictions or obligations with respect to
+any use, modification, or sharing of any outputs generated by using the Model
+Materials.
+
+THE MODEL MATERIALS ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE, NONINFRINGEMENT, ACCURACY, OR THE
+ABSENCE OF LATENT OR OTHER DEFECTS OR ERRORS, WHETHER OR NOT DISCOVERABLE, ALL
+TO THE GREATEST EXTENT PERMISSIBLE UNDER APPLICABLE LAW.
+
+YOU ARE SOLELY RESPONSIBLE FOR (1) CLEARING RIGHTS OF OTHER PERSONS THAT MAY
+APPLY TO THE MODEL MATERIALS OR ANY USE THEREOF, INCLUDING WITHOUT LIMITATION
+ANY PERSON'S COPYRIGHTS OR OTHER RIGHTS INCLUDED OR EMBODIED IN THE MODEL
+MATERIALS; (2) OBTAINING ANY NECESSARY CONSENTS, PERMISSIONS OR OTHER RIGHTS
+REQUIRED FOR ANY USE OF THE MODEL MATERIALS; OR (3) PERFORMING ANY DUE
+DILIGENCE OR UNDERTAKING ANY OTHER INVESTIGATIONS INTO THE MODEL MATERIALS OR
+ANYTHING INCORPORATED OR EMBODIED THEREIN.
+
+IN NO EVENT SHALL THE PROVIDERS OF THE MODEL MATERIALS BE LIABLE FOR ANY CLAIM,
+DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE MODEL MATERIALS, THE
+USE THEREOF OR OTHER DEALINGS THEREIN.

MANIFEST.md

@@ -0,0 +1,26 @@
+# strata_v1 release package
+
+manifest updated 2026-10-23T18:25:31Z (README.md checksum); source `best.pth` of pixeldit_sem1024d24l_pix128d4l_bilineardwgeluproject_unfreeze_3src_const1em5_t128_4stepft
+
+| file | size | sha256 |
+|---|---|---|
+| ATTRIBUTION.md | 0.0 MiB | e1b27ced4d5c7c96d321d6dfedc66b0cd5cc5005a48f397e5bd996db3e25cfe8 |
+| CONTRIBUTING.md | 0.0 MiB | eb2d2bb57508d7d0d467c7a73bf1f1d8e6b20413a5f91fde67a8fc606e2e5873 |
+| LICENSE | 0.0 MiB | 2ab44b68365473c112f5092211a38f231cb23e50de68b75a13369adbd76a74df |
+| README.md | 0.0 MiB | 6f1417267e4e904ff17991f130e7b7ae16ea914231bd8978a475bb833628af73 |
+| channels.json | 0.0 MiB | 92908962377d5b17d19ecba0dbc23b4c9d7c6e026fa19c5f3822adc8ea85caee |
+| checkpoints/strata_v1.pth | 1265.3 MiB | a66bc75c1f04ddb43375d4280d71951c3d0874b043ad854b5791bc4d6f316a45 |
+| config.json | 0.0 MiB | 9f3ee7771666a639033c0755098e34130dbefd8fe39fe3848818deb2911dbcf5 |
+| input_norm_mean.npy | 0.0 MiB | ca25e622b933e0fdb3beca5b7279789d913658af313a15b9867f09049379f67a |
+| input_norm_var.npy | 0.0 MiB | 55f98f3e73ac0ae963fce4e6c0cc396b2fca3ff5380f1370902737de682884bd |
+| landfrac.npy | 96.0 MiB | 32e8afe0cce988e7303fe54287adf9bc0929e0649233966dc0c766a8e0b69159 |
+| model_cards/bias.md | 0.0 MiB | 01209bc233ab53a3736d13f43b887a49c3db9446b20f568762b213f5f1cd5d92 |
+| model_cards/explainability.md | 0.0 MiB | 782a0a30a479d4af1d2f0ed9b4667bd2c19c6666e7664a7e2fdd88568069ecd8 |
+| model_cards/privacy.md | 0.0 MiB | bada9a09353e8e8605676cc1002755ade1f31e111583897fde3775a7e00492f9 |
+| model_cards/safety.md | 0.0 MiB | c9db8998622f44ce0f8c7695151f9242dee767770fd6dcb43c49badbf0d800c9 |
+| phis.npy | 96.0 MiB | 8e38cc10273db85cbb737c4c6b7ceac1fd211455be9fe2adfb251ecc1d4edea5 |
+| sgh30.npy | 96.0 MiB | 50a0e306d2ccc7b33cce552a047fc8b838ddf719918df1a970ad25dc4f29e105 |
+| target_norm_mean.npy | 0.0 MiB | 55abaad5b7e740193b38f34613bd8dd201348d078e8b7854f00cc27223014420 |
+| target_norm_var.npy | 0.0 MiB | 2386d61e88210c9f2ee2a31eaa8a06b3fe9f997ba2117e30bb1638c05ae54be7 |
+| third_party/CC-BY-4.0.txt | 0.0 MiB | 9ba9550ad48438d0836ddab3da480b3b69ffa0aac7b7878b5a0039e7ab429411 |
+| train_config.json | 0.0 MiB | 794ec1963d7c55a9ceebe13e1e4a56e1d6c5d5d33f30a6e36713162eedf95cd8 |

README.md

@@ -0,0 +1,178 @@
+---
+license: openmdw-1.1
+---
+# Earth-2 Checkpoints: STRATA
+
+## Description:
+
+STRATA (Storm-resolving Tile-based autoRegressive Atmosphere Transformer Architecture) is a global, kilometer-scale AI atmosphere model that emulates the SCREAM (Simple Cloud-Resolving E3SM Atmosphere Model) global storm-resolving simulation. It autoregressively predicts the three-dimensional atmospheric state on SCREAM's native ne1024pg2 cubed-sphere grid (6 faces × 2048 × 2048 ≈ 25.2 million columns, ~4.9 km grid spacing) with a 10-minute time step. The prognostic state consists of potential temperature, zonal and meridional wind, geopotential height, vertical pressure velocity and specific humidity on 24 model levels, plus 2-m air temperature; surface pressure and liquid/ice surface precipitation fluxes are diagnosed at every step.
+
+Inference is tile based: the global state is processed as overlapping cubed-sphere tiles (128–256 pixels with halos), so a single GPU can advance any part of the globe and a multi-GPU domain decomposition advances the full globe. Training recipes and the inference wrapper are in the public [NVlabs/STRATA](https://github.com/NVlabs/STRATA) repository (Apache-2.0); the network architecture itself lives in [NVIDIA PhysicsNeMo](https://github.com/NVIDIA/physicsnemo) as `physicsnemo.experimental.models.strata`.
+
+This model is ready for commercial or non-commercial use.
+
+### License/Terms of Use:
+
+**Governing Terms**: Use of this model is governed by the [Linux Foundation OpenMDW License Agreement, version 1.1](https://github.com/OpenMDW/OpenMDW/blob/main/1.1/LICENSE.OpenMDW-1.1).
+See the `LICENSE` file for the governing terms. The files `phis.npy`, `sgh30.npy` and `landfrac.npy` are derived from the CC BY 4.0 licensed STRATA-SCREAM datasets, with attribution obligations listed in `ATTRIBUTION.md`.
+
+### Deployment Geography:
+
+Global
+
+### Use Case:
+
+Kilometer-scale global atmosphere emulation for weather and climate research: short-range (hours to days) forecasting of the SCREAM state, emulation of storm-resolving simulations, and research on coupling AI emulators of different resolutions (e.g. large-scale nudging / downscaling experiments).
+
+### Release Date:
+
+Hugging Face: 11/02/2026 (planned) via [https://huggingface.co/nvidia/strata](https://huggingface.co/nvidia/strata)
+
+## Reference(s):
+
+- [Hu, Z., et al. (2026), Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet, arXiv:2606.31248](https://arxiv.org/abs/2606.31248)
+- SCREAM: Caldwell et al. (2021), [Convection-Permitting Simulations With the E3SM Global Atmosphere Model](https://doi.org/10.1029/2021MS002544)
+
+## Model Architecture:
+
+**Architecture Type:** Two-stage transformer ("PixelDiT"): a semantic transformer backbone operating on 4×4-pixel patches (24 blocks, width 1024, 16 heads, 3-D neighborhood attention with kernel 9 and dilation 3, gated attention, alternating depth-wise attention, stereographic 2-D rotary position embeddings, latitude/longitude index conditioning, wind-vector rotation across cube faces) followed by a pixel-resolution refinement transformer (4 blocks, width 128, kernel 9, bilinear depth-wise GELU projection with adaptive layer norm). The model is a deterministic single-step predictor trained with a regression (smooth-L1) loss on a mixed state/tendency target; no diffusion sampling is involved. 331.7 M parameters. <br>
+**Network Architecture:** Transformer with Neighborhood Attention (NATTEN) <br>
+
+This model provides the following checkpoint:
+
+- `checkpoints/strata_v1.pth` -- ne1024pg2 grid, 10-minute time step, 331.7 M parameters (pretraining followed by a 4-step autoregressive fine-tune)
+
+## Input:
+
+**Input Type(s):**
+
+- Tensor (149 channels: 145 prognostic atmospheric state channels and 4 forcing channels) <br>
+
+**Input Format(s):** PyTorch tensors <br>
+
+**Input Parameters:**
+
+- Four Dimensional (4D): (batch, channel, tile height, tile width) per cubed-sphere tile; the tiled inference wrapper accepts the global state as (batch, channel, 6 faces, 2048, 2048) <br>
+
+**Other Properties Related to Input:**
+
+- Grid: SCREAM ne1024pg2 cubed-sphere physics grid (6 × 2048 × 2048 columns).
+- Prognostic 3-D variables on 24 SCREAM hybrid model levels (archived level indices 8–31; nominal pressures ≈100, 117, 136, 158, 184, 214, 250, 290, 338, 394, 459, 534, 614, 690, 758, 814, 854, 880, 904, 927, 948, 967, 983 and 998 hPa for a 1000 hPa surface): `PotentialTemperature`, `U`, `V`, `z_mid`, `omega`, `qv`.
+- Prognostic 2-D variable: `T_2m`.
+- Forcing channels: `coszr` (cosine of the solar zenith angle, computed from the valid time of the atmospheric state before the tensor is assembled), `phis` (surface geopotential), `sgh30` (sub-grid orography standard deviation), `landfrac` (land fraction). The three static fields are distributed with the model as `phis.npy`, `sgh30.npy` and `landfrac.npy`.
+- Inputs are normalized per channel with statistics stored in the checkpoint (also exported as `input_norm_mean.npy` / `input_norm_var.npy`; channel order in `channels.json`).
+
+## Output:
+
+**Output Type(s):** Tensor (148 channels: the 145 prognostic state channels at t + 10 min and 3 diagnostic channels) <br>
+**Output Format:** PyTorch Tensors <br>
+**Output Parameters:** Four Dimensional (4D) (batch, channel, tile height, tile width) <br>
+**Other Properties Related to Output:**
+
+- Diagnostic channels: `ps` (surface pressure), `precip_liq_surf_mass_flux`, `precip_ice_surf_mass_flux` (surface precipitation mass fluxes, m/s)
+- Output lead time is one 10-minute step; longer forecasts are produced autoregressively by the wrapper.
+
+Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
+
+## Software Integration:
+
+**Runtime Engine(s):** PyTorch, NVIDIA PhysicsNeMo (with NATTEN neighborhood attention) <br>
+**Supported Hardware Microarchitecture Compatibility:** <br>
+* NVIDIA Ampere <br>
+* NVIDIA Hopper <br>
+* NVIDIA Blackwell <br>
+
+**Supported Operating System(s):**
+* Linux <br>
+
+The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.
+
+## Model Version(s):
+
+**Model Version:** v1 (`strata_v1`) <br>
+
+# Training, Testing, and Evaluation Datasets:
+
+## Training Dataset:
+
+**Link:** [STRATA-SCREAM-sdecadal](https://huggingface.co/datasets/nvidia/STRATA-SCREAM-sdecadal), [STRATA-SCREAM-sdy1](https://huggingface.co/datasets/nvidia/STRATA-SCREAM-sdy1), [STRATA-SCREAM-sdy2](https://huggingface.co/datasets/nvidia/STRATA-SCREAM-sdy2) <br>
+
+*Data Collection Method by dataset:* <br>
+* Automated (numerical simulation output) <br>
+
+*Labeling Method by dataset:* <br>
+* Not Applicable (self-supervised next-step prediction; no human labels) <br>
+
+*Data Modality:*
+* Gridded geophysical time series
+
+*Data Size:*
+* ~76 TB total (sdecadal 36.8 TB, sdy1 19.6 TB, sdy2 19.7 TB); the training periods below are subsets of each store
+
+**Properties:**
+Output of three SCREAM v1 global storm-resolving simulations on the ne1024pg2 grid (~4.9 km physics grid), archived every 10 minutes on 32 model levels and published as cubed-sphere zarr stores: a 14-day segment of a transient historical (F20TR) simulation (sdecadal, 1994-10-01 to 1994-10-14) and two 7-day present-day (F2010) simulations for the DYAMOND periods (sdy1: 2016-08-01 to 2016-08-07; sdy2: 2020-01-20 to 2020-01-26). Training uses 17 simulated days: 1994-10-02 to 1994-10-10 of sdecadal, 2016-08-02 to 2016-08-05 of sdy1 and 2020-01-21 to 2020-01-24 of sdy2 (the first simulated day of every store is excluded; the remaining days of sdecadal are held out for testing and evaluation). The published sdecadal zarr store and the model code label the sdecadal dates as October 2020. The datasets are released under CC-BY-4.0. <br>
+
+## Testing Dataset:
+
+**Link:** same simulations as above (held-out later time periods of each simulation) <br>
+
+*Data Collection Method by dataset:* <br>
+* Automated (numerical simulation output) <br>
+
+*Labeling Method by dataset:* <br>
+* Not Applicable <br>
+
+**Properties:**
+Held-out portion of the sdecadal simulation after the training period (simulated days 11–14; validation samples every 6 hours on day 14), never seen during training (dates labelled October 2020 in the store). <br>
+
+## Evaluation Dataset:
+
+**Link:** same simulations as above <br>
+
+*Data Collection Method by dataset:* <br>
+* Automated (numerical simulation output) <br>
+
+*Labeling Method by dataset:* <br>
+* Not Applicable <br>
+
+**Properties:**
+Multi-day autoregressive rollouts initialized from six held-out sdecadal states at 12-hourly intervals (2020-10-11 12:00 to 2020-10-14 00:00 UTC in the store's date labelling) are scored against the SCREAM trajectory: area-weighted RMSE and bias per variable and level, radially averaged power spectra, and precipitation statistics; see the paper for results. <br>
+
+## Inference:
+
+**Engine:** PyTorch, PhysicsNeMo <br>
+**Test Hardware:**
+* H100 <br>
+* A100 <br>
+
+### Files in this repository
+
+| file | content |
+|---|---|
+| `checkpoints/strata_v1.pth` | network weights (fp32), input/target normalization statistics, model/training configuration |
+| `channels.json` | variable and level lists, grid and tile size |
+| `input_norm_mean.npy`, `input_norm_var.npy`, `target_norm_mean.npy`, `target_norm_var.npy` | per-channel normalization statistics (also inside the checkpoint) |
+| `phis.npy`, `sgh30.npy`, `landfrac.npy` | static forcing fields (float32, in the model's ne1024pg2 column order) |
+| `third_party/CC-BY-4.0.txt` | license text of the CC BY 4.0 licensed SCREAM-derived files (see `ATTRIBUTION.md`) |
+| `MANIFEST.md` | file sizes and SHA-256 checksums |
+
+### Contributions
+
+This repository distributes model weights and auxiliary files only and does not accept contributions (see `CONTRIBUTING.md`). Please report issues and propose changes to the code in the [NVlabs/STRATA](https://github.com/NVlabs/STRATA) repository.
+
+### Minimal usage
+
+```python
+import os
+os.environ["AUX_DATA_ROOT"] = "/path/to/this/repo"   # auxiliary files are resolved here
+from screamcast.earth2studio_wrappers import ScreamcastModel   # pip install from https://github.com/NVlabs/STRATA
+model = ScreamcastModel.from_checkpoint("/path/to/this/repo/checkpoints/strata_v1.pth")
+```
+
+## Ethical Considerations:
+
+NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
+
+For more detailed information on ethical considerations for this model, please see the Model Card++ [Bias](model_cards/bias.md), [Explainability](model_cards/explainability.md), [Safety & Security](model_cards/safety.md), and [Privacy](model_cards/privacy.md) subcards.
+
+Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns on the [NVIDIA security vulnerability submission page](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

channels.json

@@ -0,0 +1,52 @@
+{
+ "variables_prognostic": [
+  "PotentialTemperature",
+  "U",
+  "V",
+  "z_mid",
+  "omega",
+  "qv",
+  "T_2m"
+ ],
+ "variables_forcing": [
+  "coszr",
+  "phis",
+  "sgh30",
+  "landfrac"
+ ],
+ "variables_diagnostic": [
+  "precip_ice_surf_mass_flux",
+  "precip_liq_surf_mass_flux",
+  "ps"
+ ],
+ "levels": [
+  8,
+  9,
+  10,
+  11,
+  12,
+  13,
+  14,
+  15,
+  16,
+  17,
+  18,
+  19,
+  20,
+  21,
+  22,
+  23,
+  24,
+  25,
+  26,
+  27,
+  28,
+  29,
+  30,
+  31
+ ],
+ "grid": "cubesphere ne1024pg2",
+ "nside": 2048,
+ "tile_size": 128,
+ "time_step_minutes": 10
+}

checkpoints/strata_v1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66bc75c1f04ddb43375d4280d71951c3d0874b043ad854b5791bc4d6f316a45
+size 1326762379

config.json

@@ -0,0 +1,8 @@
+{
+ "name": "strata",
+ "model_type": "pixeldit",
+ "parameters": 331664906,
+ "grid": "cubesphere ne1024pg2",
+ "tile_size": 128,
+ "time_step_minutes": 10
+}

input_norm_mean.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca25e622b933e0fdb3beca5b7279789d913658af313a15b9867f09049379f67a
+size 724

input_norm_var.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f98f3e73ac0ae963fce4e6c0cc396b2fca3ff5380f1370902737de682884bd
+size 724

landfrac.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e8afe0cce988e7303fe54287adf9bc0929e0649233966dc0c766a8e0b69159
+size 100663424

model_cards/bias.md

@@ -0,0 +1,5 @@
+Field                                                                                               |  Response
+:---------------------------------------------------------------------------------------------------|:---------------
+Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing:  |  Not Applicable
+Measures taken to mitigate against unwanted bias:                                                   |  Not Applicable
+Bias Metric (If Measured): | Not Applicable

model_cards/explainability.md

@@ -0,0 +1,13 @@
+Field                                                                                                  |  Response
+:------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------
+Intended Task/Domain:                                                                                  |  Kilometer-scale global atmosphere emulation (weather and climate research)
+Model Type:                                                                                            |  Transformer with neighborhood attention (two-stage "PixelDiT": semantic backbone + pixel refinement)
+Intended Users:                                                                                        |  Weather and climate ML researchers / developers building or evaluating km-scale global atmosphere emulators
+Output:                                                                                                |  148 channels on the SCREAM ne1024pg2 cubed-sphere grid (6 × 2048 × 2048 columns, ~4.9 km): potential temperature, zonal/meridional wind, geopotential height, vertical pressure velocity and specific humidity on 24 model levels, 2-m temperature, surface pressure and liquid/ice surface precipitation fluxes
+Describe how the model works:                                                                          |  STRATA autoregressively predicts the SCREAM atmospheric state 10 minutes ahead. The current state (145 channels) plus four forcing channels (solar zenith angle, surface geopotential, sub-grid orography, land fraction) are normalized and processed tile by tile on the cubed-sphere; a semantic transformer on 4×4-pixel patches captures mesoscale structure and a pixel-resolution transformer refines the output at native resolution. The network predicts a mixed state/tendency target which is de-normalized and added to the input state; longer forecasts are produced by feeding predictions back as inputs.
+Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:  |  Not Applicable
+Technical Limitations & Mitigation:                                                                    |  The model emulates one specific simulation (SCREAM v1) rather than observations, so it inherits SCREAM's biases and is not calibrated against real-world data. The model was trained on only 17 simulated days from three SCREAM runs, so it has seen a limited range of seasons and climate states. Forecast skill degrades with lead time (multi-day) and small-scale features such as individual convective cells decorrelate within hours; tile-based inference can introduce faint tile-boundary artifacts that are mitigated with overlapping halos and sub-patch jitter. Users should validate on their own use case.
+Verified to have met prescribed NVIDIA quality standards:                                              |  Yes
+Performance Metrics:                                                                                   |  Area-weighted Root Mean Square Error (RMSE) and bias per variable and level against SCREAM, radially averaged power spectra, precipitation statistics
+Potential Known Risks:                                                                                 |  The model may mispredict the location, intensity or timing of severe weather (e.g. convective systems, tropical cyclones, heavy precipitation). It is a research model and should not be used as the sole basis for safety-critical decisions.
+Licensing:                                                                                             |  [Linux Foundation OpenMDW License Agreement, version 1.1](https://github.com/OpenMDW/OpenMDW/blob/main/1.1/LICENSE.OpenMDW-1.1)

model_cards/privacy.md

@@ -0,0 +1,3 @@
+NVIDIA and its affiliates ("NVIDIA") are committed to respecting user privacy. No personal data was used to create this model. Data from user interactions with the model was not used to train it, and the model does not generate personal data. Provenance is available for all datasets used in training. The dataset was reviewed during dataset creation, model training, evaluation, and before release.
+
+[NVIDIA Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/)

model_cards/safety.md

@@ -0,0 +1,6 @@
+Field                                               |  Response
+:---------------------------------------------------|:----------------------------------
+Model Application Field(s):                         |  Climate
+Describe the life critical impact (if present).     |  Not Applicable
+Use Case Restrictions:                              |  Abide by [Linux Foundation OpenMDW License Agreement, version 1.1](https://github.com/OpenMDW/OpenMDW/blob/main/1.1/LICENSE.OpenMDW-1.1)
+Model and dataset restrictions:                     |  The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development.  Restrictions enforce dataset access during training, and dataset license constraints adhered to.

phis.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e38cc10273db85cbb737c4c6b7ceac1fd211455be9fe2adfb251ecc1d4edea5
+size 100663424

sgh30.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a0e306d2ccc7b33cce552a047fc8b838ddf719918df1a970ad25dc4f29e105
+size 100663424

target_norm_mean.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55abaad5b7e740193b38f34613bd8dd201348d078e8b7854f00cc27223014420
+size 720

target_norm_var.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2386d61e88210c9f2ee2a31eaa8a06b3fe9f997ba2117e30bb1638c05ae54be7
+size 720

third_party/CC-BY-4.0.txt

@@ -0,0 +1,396 @@
+Attribution 4.0 International
+
+=======================================================================
+
+Creative Commons Corporation ("Creative Commons") is not a law firm and
+does not provide legal services or legal advice. Distribution of
+Creative Commons public licenses does not create a lawyer-client or
+other relationship. Creative Commons makes its licenses and related
+information available on an "as-is" basis. Creative Commons gives no
+warranties regarding its licenses, any material licensed under their
+terms and conditions, or any related information. Creative Commons
+disclaims all liability for damages resulting from their use to the
+fullest extent possible.
+
+Using Creative Commons Public Licenses
+
+Creative Commons public licenses provide a standard set of terms and
+conditions that creators and other rights holders may use to share
+original works of authorship and other material subject to copyright
+and certain other rights specified in the public license below. The
+following considerations are for informational purposes only, are not
+exhaustive, and do not form part of our licenses.
+
+     Considerations for licensors: Our public licenses are
+     intended for use by those authorized to give the public
+     permission to use material in ways otherwise restricted by
+     copyright and certain other rights. Our licenses are
+     irrevocable. Licensors should read and understand the terms
+     and conditions of the license they choose before applying it.
+     Licensors should also secure all rights necessary before
+     applying our licenses so that the public can reuse the
+     material as expected. Licensors should clearly mark any
+     material not subject to the license. This includes other CC-
+     licensed material, or material used under an exception or
+     limitation to copyright. More considerations for licensors:
+    wiki.creativecommons.org/Considerations_for_licensors
+
+     Considerations for the public: By using one of our public
+     licenses, a licensor grants the public permission to use the
+     licensed material under specified terms and conditions. If
+     the licensor's permission is not necessary for any reason--for
+     example, because of any applicable exception or limitation to
+     copyright--then that use is not regulated by the license. Our
+     licenses grant only permissions under copyright and certain
+     other rights that a licensor has authority to grant. Use of
+     the licensed material may still be restricted for other
+     reasons, including because others have copyright or other
+     rights in the material. A licensor may make special requests,
+     such as asking that all changes be marked or described.
+     Although not required by our licenses, you are encouraged to
+     respect those requests where reasonable. More considerations
+     for the public:
+    wiki.creativecommons.org/Considerations_for_licensees
+
+=======================================================================
+
+Creative Commons Attribution 4.0 International Public License
+
+By exercising the Licensed Rights (defined below), You accept and agree
+to be bound by the terms and conditions of this Creative Commons
+Attribution 4.0 International Public License ("Public License"). To the
+extent this Public License may be interpreted as a contract, You are
+granted the Licensed Rights in consideration of Your acceptance of
+these terms and conditions, and the Licensor grants You such rights in
+consideration of benefits the Licensor receives from making the
+Licensed Material available under these terms and conditions.
+
+
+Section 1 -- Definitions.
+
+  a. Adapted Material means material subject to Copyright and Similar
+     Rights that is derived from or based upon the Licensed Material
+     and in which the Licensed Material is translated, altered,
+     arranged, transformed, or otherwise modified in a manner requiring
+     permission under the Copyright and Similar Rights held by the
+     Licensor. For purposes of this Public License, where the Licensed
+     Material is a musical work, performance, or sound recording,
+     Adapted Material is always produced where the Licensed Material is
+     synched in timed relation with a moving image.
+
+  b. Adapter's License means the license You apply to Your Copyright
+     and Similar Rights in Your contributions to Adapted Material in
+     accordance with the terms and conditions of this Public License.
+
+  c. Copyright and Similar Rights means copyright and/or similar rights
+     closely related to copyright including, without limitation,
+     performance, broadcast, sound recording, and Sui Generis Database
+     Rights, without regard to how the rights are labeled or
+     categorized. For purposes of this Public License, the rights
+     specified in Section 2(b)(1)-(2) are not Copyright and Similar
+     Rights.
+
+  d. Effective Technological Measures means those measures that, in the
+     absence of proper authority, may not be circumvented under laws
+     fulfilling obligations under Article 11 of the WIPO Copyright
+     Treaty adopted on December 20, 1996, and/or similar international
+     agreements.
+
+  e. Exceptions and Limitations means fair use, fair dealing, and/or
+     any other exception or limitation to Copyright and Similar Rights
+     that applies to Your use of the Licensed Material.
+
+  f. Licensed Material means the artistic or literary work, database,
+     or other material to which the Licensor applied this Public
+     License.
+
+  g. Licensed Rights means the rights granted to You subject to the
+     terms and conditions of this Public License, which are limited to
+     all Copyright and Similar Rights that apply to Your use of the
+     Licensed Material and that the Licensor has authority to license.
+
+  h. Licensor means the individual(s) or entity(ies) granting rights
+     under this Public License.
+
+  i. Share means to provide material to the public by any means or
+     process that requires permission under the Licensed Rights, such
+     as reproduction, public display, public performance, distribution,
+     dissemination, communication, or importation, and to make material
+     available to the public including in ways that members of the
+     public may access the material from a place and at a time
+     individually chosen by them.
+
+  j. Sui Generis Database Rights means rights other than copyright
+     resulting from Directive 96/9/EC of the European Parliament and of
+     the Council of 11 March 1996 on the legal protection of databases,
+     as amended and/or succeeded, as well as other essentially
+     equivalent rights anywhere in the world.
+
+  k. You means the individual or entity exercising the Licensed Rights
+     under this Public License. Your has a corresponding meaning.
+
+
+Section 2 -- Scope.
+
+  a. License grant.
+
+       1. Subject to the terms and conditions of this Public License,
+          the Licensor hereby grants You a worldwide, royalty-free,
+          non-sublicensable, non-exclusive, irrevocable license to
+          exercise the Licensed Rights in the Licensed Material to:
+
+            a. reproduce and Share the Licensed Material, in whole or
+               in part; and
+
+            b. produce, reproduce, and Share Adapted Material.
+
+       2. Exceptions and Limitations. For the avoidance of doubt, where
+          Exceptions and Limitations apply to Your use, this Public
+          License does not apply, and You do not need to comply with
+          its terms and conditions.
+
+       3. Term. The term of this Public License is specified in Section
+          6(a).
+
+       4. Media and formats; technical modifications allowed. The
+          Licensor authorizes You to exercise the Licensed Rights in
+          all media and formats whether now known or hereafter created,
+          and to make technical modifications necessary to do so. The
+          Licensor waives and/or agrees not to assert any right or
+          authority to forbid You from making technical modifications
+          necessary to exercise the Licensed Rights, including
+          technical modifications necessary to circumvent Effective
+          Technological Measures. For purposes of this Public License,
+          simply making modifications authorized by this Section 2(a)
+          (4) never produces Adapted Material.
+
+       5. Downstream recipients.
+
+            a. Offer from the Licensor -- Licensed Material. Every
+               recipient of the Licensed Material automatically
+               receives an offer from the Licensor to exercise the
+               Licensed Rights under the terms and conditions of this
+               Public License.
+
+            b. No downstream restrictions. You may not offer or impose
+               any additional or different terms or conditions on, or
+               apply any Effective Technological Measures to, the
+               Licensed Material if doing so restricts exercise of the
+               Licensed Rights by any recipient of the Licensed
+               Material.
+
+       6. No endorsement. Nothing in this Public License constitutes or
+          may be construed as permission to assert or imply that You
+          are, or that Your use of the Licensed Material is, connected
+          with, or sponsored, endorsed, or granted official status by,
+          the Licensor or others designated to receive attribution as
+          provided in Section 3(a)(1)(A)(i).
+
+  b. Other rights.
+
+       1. Moral rights, such as the right of integrity, are not
+          licensed under this Public License, nor are publicity,
+          privacy, and/or other similar personality rights; however, to
+          the extent possible, the Licensor waives and/or agrees not to
+          assert any such rights held by the Licensor to the limited
+          extent necessary to allow You to exercise the Licensed
+          Rights, but not otherwise.
+
+       2. Patent and trademark rights are not licensed under this
+          Public License.
+
+       3. To the extent possible, the Licensor waives any right to
+          collect royalties from You for the exercise of the Licensed
+          Rights, whether directly or through a collecting society
+          under any voluntary or waivable statutory or compulsory
+          licensing scheme. In all other cases the Licensor expressly
+          reserves any right to collect such royalties.
+
+
+Section 3 -- License Conditions.
+
+Your exercise of the Licensed Rights is expressly made subject to the
+following conditions.
+
+  a. Attribution.
+
+       1. If You Share the Licensed Material (including in modified
+          form), You must:
+
+            a. retain the following if it is supplied by the Licensor
+               with the Licensed Material:
+
+                 i. identification of the creator(s) of the Licensed
+                    Material and any others designated to receive
+                    attribution, in any reasonable manner requested by
+                    the Licensor (including by pseudonym if
+                    designated);
+
+                ii. a copyright notice;
+
+               iii. a notice that refers to this Public License;
+
+                iv. a notice that refers to the disclaimer of
+                    warranties;
+
+                 v. a URI or hyperlink to the Licensed Material to the
+                    extent reasonably practicable;
+
+            b. indicate if You modified the Licensed Material and
+               retain an indication of any previous modifications; and
+
+            c. indicate the Licensed Material is licensed under this
+               Public License, and include the text of, or the URI or
+               hyperlink to, this Public License.
+
+       2. You may satisfy the conditions in Section 3(a)(1) in any
+          reasonable manner based on the medium, means, and context in
+          which You Share the Licensed Material. For example, it may be
+          reasonable to satisfy the conditions by providing a URI or
+          hyperlink to a resource that includes the required
+          information.
+
+       3. If requested by the Licensor, You must remove any of the
+          information required by Section 3(a)(1)(A) to the extent
+          reasonably practicable.
+
+       4. If You Share Adapted Material You produce, the Adapter's
+          License You apply must not prevent recipients of the Adapted
+          Material from complying with this Public License.
+
+
+Section 4 -- Sui Generis Database Rights.
+
+Where the Licensed Rights include Sui Generis Database Rights that
+apply to Your use of the Licensed Material:
+
+  a. for the avoidance of doubt, Section 2(a)(1) grants You the right
+     to extract, reuse, reproduce, and Share all or a substantial
+     portion of the contents of the database;
+
+  b. if You include all or a substantial portion of the database
+     contents in a database in which You have Sui Generis Database
+     Rights, then the database in which You have Sui Generis Database
+     Rights (but not its individual contents) is Adapted Material; and
+
+  c. You must comply with the conditions in Section 3(a) if You Share
+     all or a substantial portion of the contents of the database.
+
+For the avoidance of doubt, this Section 4 supplements and does not
+replace Your obligations under this Public License where the Licensed
+Rights include other Copyright and Similar Rights.
+
+
+Section 5 -- Disclaimer of Warranties and Limitation of Liability.
+
+  a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
+     EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
+     AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
+     ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
+     IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
+     WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
+     PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
+     ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
+     KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
+     ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
+
+  b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
+     TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
+     NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
+     INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
+     COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
+     USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
+     ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
+     DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
+     IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
+
+  c. The disclaimer of warranties and limitation of liability provided
+     above shall be interpreted in a manner that, to the extent
+     possible, most closely approximates an absolute disclaimer and
+     waiver of all liability.
+
+
+Section 6 -- Term and Termination.
+
+  a. This Public License applies for the term of the Copyright and
+     Similar Rights licensed here. However, if You fail to comply with
+     this Public License, then Your rights under this Public License
+     terminate automatically.
+
+  b. Where Your right to use the Licensed Material has terminated under
+     Section 6(a), it reinstates:
+
+       1. automatically as of the date the violation is cured, provided
+          it is cured within 30 days of Your discovery of the
+          violation; or
+
+       2. upon express reinstatement by the Licensor.
+
+     For the avoidance of doubt, this Section 6(b) does not affect any
+     right the Licensor may have to seek remedies for Your violations
+     of this Public License.
+
+  c. For the avoidance of doubt, the Licensor may also offer the
+     Licensed Material under separate terms or conditions or stop
+     distributing the Licensed Material at any time; however, doing so
+     will not terminate this Public License.
+
+  d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
+     License.
+
+
+Section 7 -- Other Terms and Conditions.
+
+  a. The Licensor shall not be bound by any additional or different
+     terms or conditions communicated by You unless expressly agreed.
+
+  b. Any arrangements, understandings, or agreements regarding the
+     Licensed Material not stated herein are separate from and
+     independent of the terms and conditions of this Public License.
+
+
+Section 8 -- Interpretation.
+
+  a. For the avoidance of doubt, this Public License does not, and
+     shall not be interpreted to, reduce, limit, restrict, or impose
+     conditions on any use of the Licensed Material that could lawfully
+     be made without permission under this Public License.
+
+  b. To the extent possible, if any provision of this Public License is
+     deemed unenforceable, it shall be automatically reformed to the
+     minimum extent necessary to make it enforceable. If the provision
+     cannot be reformed, it shall be severed from this Public License
+     without affecting the enforceability of the remaining terms and
+     conditions.
+
+  c. No term or condition of this Public License will be waived and no
+     failure to comply consented to unless expressly agreed to by the
+     Licensor.
+
+  d. Nothing in this Public License constitutes or may be interpreted
+     as a limitation upon, or waiver of, any privileges and immunities
+     that apply to the Licensor or You, including from the legal
+     processes of any jurisdiction or authority.
+
+
+=======================================================================
+
+Creative Commons is not a party to its public
+licenses. Notwithstanding, Creative Commons may elect to apply one of
+its public licenses to material it publishes and in those instances
+will be considered the “Licensor.” The text of the Creative Commons
+public licenses is dedicated to the public domain under the CC0 Public
+Domain Dedication. Except for the limited purpose of indicating that
+material is shared under a Creative Commons public license or as
+otherwise permitted by the Creative Commons policies published at
+creativecommons.org/policies, Creative Commons does not authorize the
+use of the trademark "Creative Commons" or any other trademark or logo
+of Creative Commons without its prior written consent including,
+without limitation, in connection with any unauthorized modifications
+to any of its public licenses or any other arrangements,
+understandings, or agreements concerning use of licensed material. For
+the avoidance of doubt, this paragraph does not form part of the
+public licenses.
+
+Creative Commons may be contacted at creativecommons.org.
+

train_config.json

@@ -0,0 +1,198 @@
+{
+ "experiment": {
+  "name": "pixeldit_sem1024d24l_pix128d4l_bilineardwgeluproject_unfreeze_3src_const1em5_t128_4stepft",
+  "rundir": "",
+  "model_type": "pixeldit",
+  "resume_from": "",
+  "reset_best_valid_loss": true,
+  "reset_scheduler_state": true,
+  "skip_optimizer_reloading": true
+ },
+ "dit": {
+  "patch_size": 1,
+  "patch_size_vert": 1,
+  "patch_size_horiz": 4,
+  "embed_dim": 1024,
+  "n_layers": 24,
+  "num_heads": 16,
+  "qk_norm": true,
+  "qk_norm_elementwise_affine": false,
+  "attn_kernel": 9,
+  "do_interleaved_dilation": false,
+  "na_dilations": 3,
+  "na3d_backend": "",
+  "gated_attention": true,
+  "do_alt_depthwise_attn": true,
+  "use_conv_instead_of_na3d": false,
+  "conv_kernel_size": 3,
+  "do_rope_2d": false,
+  "do_rope_2d_stereographic": true,
+  "do_rotate_wind": true,
+  "do_absolute_pos_embedding": false,
+  "index_is_latlon": true,
+  "do_arcsinh_input": false,
+  "do_te_mlp_last_layer": false,
+  "use_cross_layer_concat_skip_connection": false,
+  "do_activation_checkpointing": 1.0
+ },
+ "pixel_dit": {
+  "embed_dim": 128,
+  "n_layers": 4,
+  "num_heads": null,
+  "mlp_ratio": 4.0,
+  "attn_kernel": 9,
+  "gated_attention": false,
+  "qk_norm": true,
+  "qk_norm_elementwise_affine": false,
+  "freeze_semantic": false,
+  "freeze_pixel_blocks": false,
+  "use_bilinear_dw_gelu_project_adaln": true,
+  "do_activation_checkpointing": 0.0
+ },
+ "pipeline": {
+  "target_type": "mixed_state_diff",
+  "do_qv_softplus": true,
+  "do_precip_relu": true,
+  "variables_input_zeroed": []
+ },
+ "compute": {
+  "do_bf16_mixed": true,
+  "do_torch_compile": true
+ },
+ "training": {
+  "lr": 1e-05,
+  "loss_lr": 0.1,
+  "epochs": 50,
+  "batch_size": 1,
+  "num_workers": 2,
+  "num_workers_inference": 2,
+  "optimizer": "adamw",
+  "beta1": 0.9,
+  "beta2": 0.999,
+  "weight_decay": 1e-05,
+  "seed": 42,
+  "scheduler_type": "constant",
+  "warmup_steps": 2000,
+  "cosine_t_max": 100,
+  "cosine_n_cycles": 5,
+  "cosine_decay": 0.3162,
+  "num_steps": 4,
+  "multistep_training_mode": "final_only",
+  "do_tf32": true,
+  "grad_clip_max_norm": 0.5,
+  "backup_every_steps": 100,
+  "loss_type": "smooth_l1",
+  "resume_from": null,
+  "reset_best_valid_loss": false,
+  "reset_scheduler_state": false,
+  "skip_optimizer_reloading": false,
+  "fit_batches_for_norm": 1280,
+  "normalization_ref_path_input": "",
+  "normalization_ref_path_target": "",
+  "do_dual_normalization": false,
+  "pooled_loss": null,
+  "pooled_loss_channel_weights_csv": null,
+  "max_steps_per_epoch": null,
+  "validate_steps": 400,
+  "validate_min_samples": 1024,
+  "validate_total_images": null,
+  "validate_num_shards": null,
+  "exit_after_first_validation": false,
+  "max_validations": 5,
+  "no_save": false,
+  "save_ckpt_every_epoch": true,
+  "use_time_variation_seed": true,
+  "do_backtest_inference": false,
+  "do_track_gns": false,
+  "gns_decay": 0.99,
+  "gns_freq": 1
+ },
+ "data": {
+  "grid_type": "cubesphere",
+  "cubesphere_ne": 1024,
+  "cubesphere_npg": 2,
+  "tile_size": 128,
+  "nside": 2048,
+  "level_start": 8,
+  "level_end": 32,
+  "plevel": 1,
+  "cross_face_tiles": false,
+  "use_duo_padding": false,
+  "duo_padding_scrip_src_path": null,
+  "duo_padding_scrip_tgt_path": null,
+  "skip_corner_tiles": false,
+  "balance_cross_face": false,
+  "variables_prognostic": [
+   "PotentialTemperature",
+   "U",
+   "V",
+   "z_mid",
+   "omega",
+   "qv",
+   "T_2m"
+  ],
+  "variables_prognostic_state": [
+   "omega"
+  ],
+  "variables_forcing": [
+   "coszr",
+   "phis",
+   "sgh30",
+   "landfrac"
+  ],
+  "variables_diagnostic": [
+   "precip_ice_surf_mass_flux",
+   "precip_liq_surf_mass_flux",
+   "ps"
+  ],
+  "train_main_zarr_paths": [
+   "sdecadal.ne1024pg2_ne1024pg2.F20TR-SCREAMv1.c10-sep11.out10min.cubesphere.zarr",
+   "sdy2.ne1024pg2_ne1024pg2.F2010-SCREAMv1.c10-sep11-f602da2b98.out10min-4lev.cubesphere.zarr",
+   "sdy1.ne1024pg2_ne1024pg2.F2010-SCREAMv1.c10-sep11-f602da2b98.out10min-4lev.cubesphere.zarr"
+  ],
+  "train_aux_zarr_paths": [
+   "sdecadal.ne1024pg2_ne1024pg2.F20TR-SCREAMv1.c10-sep11.out10min.cubesphere.zarr",
+   "sdy2.ne1024pg2_ne1024pg2.F2010-SCREAMv1.c10-sep11-f602da2b98.out10min-4lev.cubesphere.zarr",
+   "sdy1.ne1024pg2_ne1024pg2.F2010-SCREAMv1.c10-sep11-f602da2b98.out10min-4lev.cubesphere.zarr"
+  ],
+  "train_zarr_weights": [
+   0.5,
+   1.0,
+   1.0
+  ],
+  "train_start_indices": [
+   144,
+   144,
+   144
+  ],
+  "train_end_indices": [
+   1435,
+   720,
+   720
+  ],
+  "split_by_time": true,
+  "train_start_index": 144,
+  "train_end_index": 1435,
+  "test_start_index": 1872,
+  "test_end_index": 2015,
+  "test_stride": 36,
+  "inference_start_index": 1872,
+  "backtest_main_zarr_path": "",
+  "backtest_aux_zarr_path": "",
+  "backtest_start_index": 864,
+  "backtest_end_index": 1007,
+  "backtest_stride": 36,
+  "latlon_path": "latlon_ne1024pg2.nc",
+  "do_fixed_z": false,
+  "fixed_z_npy_path": "data/z_coordinate_24levels.npy",
+  "phis_npy_path": "data/phis.npy"
+ },
+ "debug": {
+  "print_steps": 5,
+  "mock": false,
+  "skip_india_ocean_eval": true,
+  "use_full_test_set": true,
+  "recreate_dataloader_each_validation": true,
+  "wandb_disabled": false
+ }
+}