diff --git a/mlproject/MLproject b/mlproject/MLproject index 2164c9c..8e1545c 100644 --- a/mlproject/MLproject +++ b/mlproject/MLproject @@ -8,7 +8,7 @@ entry_points: default: /p/scratch/deepacf/maelstrom/maelstrom_data/ap1/air_temperature datasize: type: string - default: 5GB + default: 5TB mode: type: string default: train @@ -26,7 +26,7 @@ entry_points: default: 3 command: > python3 -u benchmark.py - {datadir}/{datasize}/202???01T*.nc + {datadir}/{datasize}/20200301T*.nc -m {mode} -b {batch_size} -p {patch_size} diff --git a/mlproject/README.md b/mlproject/README.md index 59ac80c..4e475e9 100644 --- a/mlproject/README.md +++ b/mlproject/README.md @@ -25,10 +25,9 @@ pip install -r maelstrom-train/benchmark/requirements_wo_modules.txt 5. The results will be logged to an Experiment on the MLflow tracking server on Mantik. Set up a project in Mantik and create a new Experiment. Note its experiment Id, which will be needed in the submission command. For a step-by-step guide, refer to the Quickstart tutorial available [here](https://mantik-ai.gitlab.io/mantik/ui/quickstart.html). -6. Update the `unicore-config-venv.yaml` file by specifying the `PreRunCommand` with the path to your virtual environment. +6. Update the `unicore-config-venv.yaml` file by specifying the `PreRunCommandOnComputeNode` with the path to your virtual environment. -
PreRunCommand:
- Command: >
+ PreRunCommandOnComputeNode: >
module load Stages/2022 GCCcore/.11.2.0 NCCL/2.11.4-CUDA-11.5 Python/3.9.6;
source /path/to/<venv-name>/bin/activate;
diff --git a/mlproject/unicore-config-venv.yaml b/mlproject/unicore-config-venv.yaml
index ecd5fa6..ea7f638 100644
--- a/mlproject/unicore-config-venv.yaml
+++ b/mlproject/unicore-config-venv.yaml
@@ -1,18 +1,15 @@
UnicoreApiUrl: https://zam2125.zam.kfa-juelich.de:9112/JUWELS/rest/core
+Exclude:
+ - '*.sif'
+ - figures
+ - saved_model
+ - README.md
+Resources:
+ Nodes: 1
+ Queue: develbooster
Environment:
- PreRunCommand:
- Command: >
- module load Stages/2022 GCCcore/.11.2.0 NCCL/2.11.4-CUDA-11.5 Python/3.9.6;
- source /p/project/deepacf/maelstrom/grau1/ap1/bin/activate;
- ExecuteOnLoginNode: False
Variables:
GIT_PYTHON_REFRESH: quiet
-Resources:
- Queue: devel
- Nodes: 1
-Exclude:
- - "*.sif"
- - "figures"
- - "saved_model"
- - README.md
-
+ PreRunCommandOnComputeNode: >
+ module load Stages/2022 GCCcore/.11.2.0 NCCL/2.11.4-CUDA-11.5 Python/3.9.6;
+ source /p/scratch/deepacf/maelstrom/grau1/ap1_env/bin/activate