dodox/dppo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
47 Commits 1 Branch 0 Tags 800 KiB
a67f474fc0
Commit Graph

5 Commits

Author SHA1 Message Date
ys1087@partner.kit.edu
5a458aac67 Configure personal WandB entity and clean up docs 
Set DPPO_WANDB_ENTITY to dominik_roth for personal logging
Remove irrelevant implementation details from experiment plan
 2025-08-27 12:24:39 +02:00
ys1087@partner.kit.edu
d43a9e2b3c 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
 2025-08-27 12:23:43 +02:00
ys1087@partner.kit.edu
e8e7233d98 Fix WandB config issue and achieve working DPPO setup 
- Disable WandB in dev script to avoid config object vs string error
- Successfully completed development test (Job 3445106)
- Confirmed: pre-training works, loss reduces, checkpoints save
- Update experiment tracking with successful results
 2025-08-27 12:19:38 +02:00
ys1087@partner.kit.edu
4adf67694a Fix Hydra config error in dev script 
- Change train.n_iters to train.n_epochs (correct DPPO parameter)
- Update experiment tracking with failed job details
- Ready for corrected dev test
 2025-08-27 12:07:38 +02:00
ys1087@partner.kit.edu
05dddfa10c Add HoReKa cluster setup and SLURM scripts 
- Add installation script for HoReKa with Python 3.10 venv
- Add SLURM job submission scripts for dev and production runs
- Add convenient submit_job.sh wrapper for easy job submission
- Update .gitignore to allow shell scripts (removed *.sh exclusion)
- Configure git remotes: upstream (original) and origin (fork)
 2025-08-27 11:57:32 +02:00