Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions docker-compose.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -41,8 +41,8 @@ services:
"
environment:
# W&B settings for this job
- WANDB_ENTITY=mcclain
- WANDB_PROJECT=plasmidrl-trl-grpo
- WANDB_ENTITY=ucl-cssb
- WANDB_PROJECT=PlasmidRL
- WANDB_TAGS=["plasmid","rl","trl","grpo"]
- WANDB_NOTES=TRL GRPO training on plasmid design
- WANDB_DIR=/tmp/wandb
Expand Down Expand Up @@ -76,8 +76,8 @@ services:
uv run wandb agent ${SWEEP_ID}
"
environment:
- WANDB_ENTITY=mcclain
- WANDB_PROJECT=plasmidrl-grpo-sweeps
- WANDB_ENTITY=ucl-cssb
- WANDB_PROJECT=PlasmidRL
- WANDB_DIR=/tmp/wandb
- SWEEP_ID=${SWEEP_ID}
- PYTHONPATH=/mcclain
Expand Down
10 changes: 10 additions & 0 deletions src/config.py
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,16 @@ class Config(BaseSettings):
region_name: str = "us-east-1"
runs_path: str = "runs/"
infered_path: str = "infered/"
checkpoints_path: str = "checkpoints/" # S3 prefix for checkpoint storage

# Production GRPO hyperparameters (from sweep optimization)
grpo_learning_rate: float = 0.00001906419115928539
grpo_per_device_train_batch_size: int = 16
grpo_num_generations: int = 4
grpo_temperature: float = 1.2292317925218237
grpo_top_p: float = 0.9086524230707756
grpo_beta: float = 0.00088482365318492
grpo_epsilon: float = 0.2649093053949679

model_config = {
"env_file": ".env",
Expand Down
Loading
Loading