From 4806578f50bb470c50319e02b7302264004df7fd Mon Sep 17 00:00:00 2001 From: saragrau4 <138492377+saragrau4@users.noreply.github.com> Date: Mon, 4 Mar 2024 10:25:35 +0100 Subject: [PATCH 01/12] Update unicore-config-venv.yaml --- mlproject/unicore-config-venv.yaml | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/mlproject/unicore-config-venv.yaml b/mlproject/unicore-config-venv.yaml index ecd5fa6..638e864 100644 --- a/mlproject/unicore-config-venv.yaml +++ b/mlproject/unicore-config-venv.yaml @@ -1,10 +1,8 @@ UnicoreApiUrl: https://zam2125.zam.kfa-juelich.de:9112/JUWELS/rest/core Environment: - PreRunCommand: - Command: > + PreRunCommandOnComputeNode: > 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: From c1f2f761a36312dd33192af97c1096f9c7bf8cd7 Mon Sep 17 00:00:00 2001 From: saragrau4 <138492377+saragrau4@users.noreply.github.com> Date: Mon, 4 Mar 2024 10:28:15 +0100 Subject: [PATCH 02/12] Update unicore-config-venv.yaml --- mlproject/unicore-config-venv.yaml | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/mlproject/unicore-config-venv.yaml b/mlproject/unicore-config-venv.yaml index 638e864..4d7e117 100644 --- a/mlproject/unicore-config-venv.yaml +++ b/mlproject/unicore-config-venv.yaml @@ -1,8 +1,12 @@ UnicoreApiUrl: https://zam2125.zam.kfa-juelich.de:9112/JUWELS/rest/core +Modules: + - Stages/2022 + - GCCcore/.11.2.0 + - NCCL/2.11.4-CUDA-11.5 + - Python/3.9.6; Environment: - PreRunCommandOnComputeNode: > - 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; + Python: + Path: source /p/project/deepacf/maelstrom/grau1/ap1/bin/activate; Variables: GIT_PYTHON_REFRESH: quiet Resources: From 3d174a53e2b1f6900d77e1d5c44e7bd4592b6e3e Mon Sep 17 00:00:00 2001 From: saragrau4 <138492377+saragrau4@users.noreply.github.com> Date: Mon, 4 Mar 2024 10:33:40 +0100 Subject: [PATCH 03/12] Update path to venv in unicore-config-venv.yaml --- mlproject/unicore-config-venv.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mlproject/unicore-config-venv.yaml b/mlproject/unicore-config-venv.yaml index 4d7e117..4692496 100644 --- a/mlproject/unicore-config-venv.yaml +++ b/mlproject/unicore-config-venv.yaml @@ -6,7 +6,7 @@ Modules: - Python/3.9.6; Environment: Python: - Path: source /p/project/deepacf/maelstrom/grau1/ap1/bin/activate; + Path: /p/project/deepacf/maelstrom/grau1/ap1/bin/activate; Variables: GIT_PYTHON_REFRESH: quiet Resources: From 5a13935da7c104e3b66456a9cd3a6a49a0e0b861 Mon Sep 17 00:00:00 2001 From: saragrau4 <138492377+saragrau4@users.noreply.github.com> Date: Mon, 4 Mar 2024 10:46:34 +0100 Subject: [PATCH 04/12] Update path to venv in unicore-config-venv.yaml --- mlproject/unicore-config-venv.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mlproject/unicore-config-venv.yaml b/mlproject/unicore-config-venv.yaml index 4692496..41ff66d 100644 --- a/mlproject/unicore-config-venv.yaml +++ b/mlproject/unicore-config-venv.yaml @@ -6,7 +6,7 @@ Modules: - Python/3.9.6; Environment: Python: - Path: /p/project/deepacf/maelstrom/grau1/ap1/bin/activate; + Path: /p/project/deepacf/maelstrom/grau1/ap1 Variables: GIT_PYTHON_REFRESH: quiet Resources: From 59bbb8c504bb53b58e8377b13ef5e445c8490b6e Mon Sep 17 00:00:00 2001 From: saragrau4 <138492377+saragrau4@users.noreply.github.com> Date: Mon, 4 Mar 2024 10:54:06 +0100 Subject: [PATCH 05/12] Modules as part of environment in unicore-config-venv.yaml --- mlproject/unicore-config-venv.yaml | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/mlproject/unicore-config-venv.yaml b/mlproject/unicore-config-venv.yaml index 41ff66d..0dc51e3 100644 --- a/mlproject/unicore-config-venv.yaml +++ b/mlproject/unicore-config-venv.yaml @@ -1,12 +1,12 @@ UnicoreApiUrl: https://zam2125.zam.kfa-juelich.de:9112/JUWELS/rest/core -Modules: - - Stages/2022 - - GCCcore/.11.2.0 - - NCCL/2.11.4-CUDA-11.5 - - Python/3.9.6; Environment: Python: Path: /p/project/deepacf/maelstrom/grau1/ap1 + Modules: + - Stages/2022 + - GCCcore/.11.2.0 + - NCCL/2.11.4-CUDA-11.5 + - Python/3.9.6 Variables: GIT_PYTHON_REFRESH: quiet Resources: From 304a03814d26598012976ce346f3f34b6ae974f3 Mon Sep 17 00:00:00 2001 From: saragrau4 <138492377+saragrau4@users.noreply.github.com> Date: Mon, 4 Mar 2024 14:54:46 +0100 Subject: [PATCH 06/12] Update MLproject --- mlproject/MLproject | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/mlproject/MLproject b/mlproject/MLproject index 2164c9c..cf0d94e 100644 --- a/mlproject/MLproject +++ b/mlproject/MLproject @@ -3,12 +3,9 @@ name: ap1 entry_points: main: parameters: - datadir: + datadirpattern: type: string - default: /p/scratch/deepacf/maelstrom/maelstrom_data/ap1/air_temperature - datasize: - type: string - default: 5GB + default: /p/scratch/deepacf/maelstrom/maelstrom_data/ap1/air_temperature/5TB/20200301T*.nc mode: type: string default: train @@ -26,7 +23,7 @@ entry_points: default: 3 command: > python3 -u benchmark.py - {datadir}/{datasize}/202???01T*.nc + {datadirpattern} -m {mode} -b {batch_size} -p {patch_size} From 7de7b317d9b6c3bce40d64537d74dd3b1e1a0d6b Mon Sep 17 00:00:00 2001 From: saragrau4 <138492377+saragrau4@users.noreply.github.com> Date: Mon, 4 Mar 2024 15:03:15 +0100 Subject: [PATCH 07/12] Update MLproject --- mlproject/MLproject | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mlproject/MLproject b/mlproject/MLproject index cf0d94e..3bb5556 100644 --- a/mlproject/MLproject +++ b/mlproject/MLproject @@ -3,9 +3,9 @@ name: ap1 entry_points: main: parameters: - datadirpattern: + datadirsize: type: string - default: /p/scratch/deepacf/maelstrom/maelstrom_data/ap1/air_temperature/5TB/20200301T*.nc + default: /p/scratch/deepacf/maelstrom/maelstrom_data/ap1/air_temperature/5TB mode: type: string default: train @@ -23,11 +23,11 @@ entry_points: default: 3 command: > python3 -u benchmark.py - {datadirpattern} + {datadirsize}/20200301T*.nc -m {mode} -b {batch_size} -p {patch_size} -j {num_parallel_calls} -e {nepochs} - -val {datadir}/{datasize}/20200615T*.nc + -val {datadirsize}/20200615T*.nc --norm {datadir}/normalization.yml From 3c8f9325959fa1ede8b42392fdaa8ccec6ea1a06 Mon Sep 17 00:00:00 2001 From: saragrau4 <138492377+saragrau4@users.noreply.github.com> Date: Mon, 4 Mar 2024 15:04:53 +0100 Subject: [PATCH 08/12] Update MLproject --- mlproject/MLproject | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/mlproject/MLproject b/mlproject/MLproject index 3bb5556..8e1545c 100644 --- a/mlproject/MLproject +++ b/mlproject/MLproject @@ -3,9 +3,12 @@ name: ap1 entry_points: main: parameters: - datadirsize: + datadir: type: string - default: /p/scratch/deepacf/maelstrom/maelstrom_data/ap1/air_temperature/5TB + default: /p/scratch/deepacf/maelstrom/maelstrom_data/ap1/air_temperature + datasize: + type: string + default: 5TB mode: type: string default: train @@ -23,11 +26,11 @@ entry_points: default: 3 command: > python3 -u benchmark.py - {datadirsize}/20200301T*.nc + {datadir}/{datasize}/20200301T*.nc -m {mode} -b {batch_size} -p {patch_size} -j {num_parallel_calls} -e {nepochs} - -val {datadirsize}/20200615T*.nc + -val {datadir}/{datasize}/20200615T*.nc --norm {datadir}/normalization.yml From 3fc30d0b98018550ad5b2f02280049bbe5f9a051 Mon Sep 17 00:00:00 2001 From: saragrau4 <138492377+saragrau4@users.noreply.github.com> Date: Wed, 6 Mar 2024 10:15:22 +0100 Subject: [PATCH 09/12] Update PreRunCommandOnComputeNode README.md --- mlproject/README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/mlproject/README.md b/mlproject/README.md index 59ac80c..bfcb766 100644 --- a/mlproject/README.md +++ b/mlproject/README.md @@ -27,8 +27,7 @@ pip install -r maelstrom-train/benchmark/requirements_wo_modules.txt 6. Update the `unicore-config-venv.yaml` file by specifying the `PreRunCommand` 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;
From 73e89cd8f9da74a0a06c5dc7bab46387b85f4823 Mon Sep 17 00:00:00 2001
From: saragrau4 <138492377+saragrau4@users.noreply.github.com>
Date: Wed, 6 Mar 2024 10:16:09 +0100
Subject: [PATCH 10/12] Update README.md
---
mlproject/README.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mlproject/README.md b/mlproject/README.md
index bfcb766..4e475e9 100644
--- a/mlproject/README.md
+++ b/mlproject/README.md
@@ -25,7 +25,7 @@ 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.
PreRunCommandOnComputeNode: >
module load Stages/2022 GCCcore/.11.2.0 NCCL/2.11.4-CUDA-11.5 Python/3.9.6;
From 4974d6ed5eb047e9c318918e3d7e3e62bd2925ac Mon Sep 17 00:00:00 2001
From: saragrau4 <138492377+saragrau4@users.noreply.github.com>
Date: Fri, 8 Mar 2024 15:07:05 +0100
Subject: [PATCH 11/12] Update unicore-config-venv.yaml
---
mlproject/unicore-config-venv.yaml | 27 +++++++++++----------------
1 file changed, 11 insertions(+), 16 deletions(-)
diff --git a/mlproject/unicore-config-venv.yaml b/mlproject/unicore-config-venv.yaml
index 0dc51e3..5227d53 100644
--- a/mlproject/unicore-config-venv.yaml
+++ b/mlproject/unicore-config-venv.yaml
@@ -1,20 +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:
- Python:
- Path: /p/project/deepacf/maelstrom/grau1/ap1
- Modules:
- - Stages/2022
- - GCCcore/.11.2.0
- - NCCL/2.11.4-CUDA-11.5
- - Python/3.9.6
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/project/deepacf/maelstrom/grau1/ap1_env/bin/activate
From 7067b787208aaf5bd8b774a0ff8c93556bfe18a4 Mon Sep 17 00:00:00 2001
From: saragrau4 <138492377+saragrau4@users.noreply.github.com>
Date: Fri, 22 Mar 2024 11:20:08 +0100
Subject: [PATCH 12/12] Update unicore-config-venv.yaml
---
mlproject/unicore-config-venv.yaml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mlproject/unicore-config-venv.yaml b/mlproject/unicore-config-venv.yaml
index 5227d53..ea7f638 100644
--- a/mlproject/unicore-config-venv.yaml
+++ b/mlproject/unicore-config-venv.yaml
@@ -12,4 +12,4 @@ Environment:
GIT_PYTHON_REFRESH: quiet
PreRunCommandOnComputeNode: >
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_env/bin/activate
+ source /p/scratch/deepacf/maelstrom/grau1/ap1_env/bin/activate