From d43a9e2b3c53685c9346e66a83f986af70a6604f Mon Sep 17 00:00:00 2001
From: "ys1087@partner.kit.edu" <ys1087@hkn1990.localdomain>
Date: Wed, 27 Aug 2025 12:23:43 +0200
Subject: [PATCH] Fix WandB configuration for proper logging

- Configure DPPO_WANDB_ENTITY environment variable in dev script
- Update README with clear WandB setup instructions
- Remove wandb=null to enable logging when credentials are set
---
 README.md             | 14 +++++++++++---
 slurm/run_dppo_dev.sh | 13 +++++++------
 2 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/README.md b/README.md
index 0225c1b..b81bac0 100644
--- a/README.md
+++ b/README.md
@@ -119,14 +119,22 @@ tail -f logs/dppo_<job_id>.out
 
 ### Configuration
 
-Before running experiments, set your WandB credentials:
+**Required for WandB logging**: Set your credentials as environment variables before submitting jobs:
 
 ```bash
+# Set these in your shell before running experiments
 export WANDB_API_KEY=<your_api_key>
-export WANDB_ENTITY=<your_username_or_team>
+export DPPO_WANDB_ENTITY=<your_username_or_team>
+
+# Then submit jobs normally
+./submit_job.sh dev
 ```
 
-Or disable WandB by adding `wandb=null` to your python command.
+**Alternative**: Modify the SLURM scripts directly to set your credentials:
+- Edit `slurm/run_dppo_dev.sh` and replace `"your_wandb_username"` with your actual WandB username
+- Uncomment and set `WANDB_API_KEY` in the scripts
+
+**Disable WandB**: Add `wandb=null` to python commands if you don't want logging.
 
 ### Repository Changes
 
diff --git a/slurm/run_dppo_dev.sh b/slurm/run_dppo_dev.sh
index 1487154..685c37f 100755
--- a/slurm/run_dppo_dev.sh
+++ b/slurm/run_dppo_dev.sh
@@ -14,11 +14,12 @@
 # Load required modules
 module load devel/cuda/12.4
 
-# Set environment variables
+# Set environment variables for WandB
 export WANDB_MODE=online
 export WANDB_PROJECT=dppo_dev_test
-# export WANDB_API_KEY=<your_api_key>  # TODO: Set your API key
-# export WANDB_ENTITY=<your_entity>    # TODO: Set your entity (username or team)
+export DPPO_WANDB_ENTITY=${DPPO_WANDB_ENTITY:-"your_wandb_username"}  # TODO: Set your WandB username
+# TODO: Set your WandB API key as environment variable:
+# export WANDB_API_KEY=<your_api_key>
 
 # Default paths (can be overridden by environment)
 export DPPO_DATA_DIR=${DPPO_DATA_DIR:-$SLURM_SUBMIT_DIR/data}
@@ -41,11 +42,11 @@ echo "PyTorch version: $(python -c 'import torch; print(torch.__version__)')"
 echo "CUDA available: $(python -c 'import torch; print(torch.cuda.is_available())')"
 echo ""
 
-# Run a quick pre-training test with reduced epochs (disable WandB for dev test)
+# Run a quick pre-training test with reduced epochs
+# Note: Will only log to WandB if WANDB_API_KEY and DPPO_WANDB_ENTITY are properly set
 python script/run.py --config-name=pre_diffusion_mlp \
     --config-dir=cfg/gym/pretrain/hopper-medium-v2 \
     train.n_epochs=2 \
-    train.save_model_freq=1 \
-    wandb=null
+    train.save_model_freq=1
 
 echo "Dev test completed!"
\ No newline at end of file