metadata/training_launch.env

# 16k MolmoBot-DROID finetune on the directional left/right SimpleDesk pick/place
# dataset (200 demos, tested40 target set). Sharded intermediate eval and one
# matching final eval on FrankaPickAndPlaceRelativeNextToSimpleDeskDiverseTargetsTested40Bench.
# No prompt randomization. FT_LLM=True. Eval uses 10 parent-managed MolmoSpaces shards.

RUN_NAME=lr_custom_16k
DATASET_ID=ccwatson/directional_pick_place_simpledesk_diverse_targets_tested40_200demos_20260716_molmobot
DATASET_LOCAL_NAME=directional_pick_place_simpledesk_diverse_targets_tested40_200demos_20260716_molmobot
BASE_MODEL_ID=allenai/MolmoBot-DROID

SAVE_ROOT=/ceph/projects/dineshj/lab/ccwatson/MolmoBot_runs
WANDB_DIR=${SAVE_ROOT}/${RUN_NAME}/wandb
WANDB_CACHE_DIR=${SAVE_ROOT}/${RUN_NAME}/.cache/wandb
WANDB_ARTIFACT_DIR=${SAVE_ROOT}/${RUN_NAME}/wandb/artifacts
WANDB_CONFIG_DIR=${SAVE_ROOT}/${RUN_NAME}/wandb/config
STATS_PATH=/vast/projects/dineshj/lab/ccwatson/Documents/molmo-robotics-stack/components/MolmoBot/MolmoBot/scratch/datasets/directional_pick_place_simpledesk_diverse_targets_tested40_200demos_20260716_molmobot/directional_pick_place_simpledesk_diverse_targets_tested40_200demos_20260716_norm_stats.yaml
RANDOMIZE_PROMPTS=0

RUN_STEPS=16000
DEVICE_BATCH_SIZE=16
GLOBAL_BATCH_SIZE=32
SAVE_INTERVAL=2000
SAVE_NUM_CHECKPOINTS_TO_KEEP=1
CHECKPOINT_RETENTION_FREQUENCY=null
SAVE_FINAL_UNSHARDED_CHECKPOINT=True
SAVE_FINAL_OPTIM=False
RESET_TRAINER_STATE=True
RESET_OPTIMIZER_STATE=True
HF_UPLOAD=0

ACTION_PRESET=franka_joint
CAMERA_PRESET=franka_droid
SEQ_LEN=928
N_OBS_STEPS=2
OBS_STEP_DELTA=8
MAX_IMAGES=4
MAX_FRAMES=1
SINGLE_FRAME=False
WEIGHTED_SAMPLING=1
FT_EMBEDDING=ae
NUM_FLOW_TIMESTAMPS=8
FT_LLM=True
IMG_AUG=1
CONNECTOR_LR=5e-6
VIT_LR=5e-6
LLM_LR=1e-5
ACTION_EXPERT_LR=1e-4
NO_VAL=0
VAL_INTERVAL=200
VAL_MAX_EXAMPLES=200
NUM_WORKERS=4
PREFETCH_FACTOR=4
WANDB_PROJECT=molmobot_finetune
WANDB_ENTITY=ccwatson
WANDB_MODE=online

# Intermediate eval on the left/right SimpleDesk relative-next-to benchmark.
EXTERNAL_EVAL_ENABLED=1
EXTERNAL_EVAL_INTERVAL=2000
EXTERNAL_EVAL_NUM_CHECKPOINTS_TO_KEEP=2
EXTERNAL_EVAL_RESULT_POLL_INTERVAL_STEPS=50
EXTERNAL_EVAL_FINAL_RESULT_WAIT_SECONDS=7200
EXTERNAL_EVAL_METRIC_FOR_BEST=success_rate
EXTERNAL_EVAL_METRIC_MODE=max

EXTERNAL_EVAL_BENCHMARK_DIR=/vast/projects/dineshj/lab/ccwatson/Documents/molmo-robotics-stack/components/molmospaces/benchmarks/custom/molmospaces-bench-v2/procthor-objaverse/FrankaPickAndPlaceRelativeNextToSimpleDeskDiverseTargetsTested40Bench/FrankaPickAndPlaceRelativeNextToSimpleDeskDiverseTargetsTested40Bench_20260716_json_benchmark
EXTERNAL_EVAL_EXTRA_ARGS="--task_horizon_steps 500"
EXTERNAL_EVAL_NUM_WORKERS=1
EXTERNAL_EVAL_PARALLEL_SHARDS=10
EXTERNAL_EVAL_RENDERER=filament
EXTERNAL_EVAL_CAMERA_NAMES="droid_shoulder_light_randomization wrist_camera_zed_mini"

EXTERNAL_EVAL_WANDB_ENABLED=1
EXTERNAL_EVAL_WANDB_PROJECT=mlspaces-json-eval
EXTERNAL_EVAL_WANDB_GROUP=lr-custom-ie-16k-b16-32
EXTERNAL_EVAL_WANDB_TAGS=betty,vla-harness,molmospaces,intermediate-eval,molmobot-droid,left-right-pick-place,simple-desk,relative-next-to,sharded-intermediate-eval,filament,10x

# Final eval on the same left/right SimpleDesk benchmark.
EXTERNAL_EVAL_FINAL_ENABLED=1
EXTERNAL_EVAL_FINAL_REQUIRED=1
EXTERNAL_EVAL_FINAL_WAIT_SECONDS=7200
EXTERNAL_EVAL_FINAL_UPLOAD_LOGS=1
EXTERNAL_EVAL_FINAL_NUM_WORKERS=1
EXTERNAL_EVAL_FINAL_PARALLEL_SHARDS=10
EXTERNAL_EVAL_FINAL_RENDERER=filament
EXTERNAL_EVAL_FINAL_CAMERA_NAMES="droid_shoulder_light_randomization wrist_camera_zed_mini"
EXTERNAL_EVAL_FINAL_EVAL_WANDB_ENABLED=1
EXTERNAL_EVAL_FINAL_EVAL_WANDB_PROJECT=mlspaces-json-eval
EXTERNAL_EVAL_FINAL_EVAL_WANDB_GROUP=lr-custom-fe-16k-b16-32
EXTERNAL_EVAL_FINAL_EVAL_WANDB_TAGS=betty,vla-harness,molmospaces,final-eval,molmobot-droid,left-right-pick-place,simple-desk,relative-next-to,sharded-final-eval,filament,10x

EXTERNAL_EVAL_FINAL_BENCHMARK_1_NAME=FrankaPickAndPlaceRelativeNextToSimpleDeskDiverseTargetsTested40Bench
EXTERNAL_EVAL_FINAL_BENCHMARK_1_DIR=/vast/projects/dineshj/lab/ccwatson/Documents/molmo-robotics-stack/components/molmospaces/benchmarks/custom/molmospaces-bench-v2/procthor-objaverse/FrankaPickAndPlaceRelativeNextToSimpleDeskDiverseTargetsTested40Bench/FrankaPickAndPlaceRelativeNextToSimpleDeskDiverseTargetsTested40Bench_20260716_json_benchmark
EXTERNAL_EVAL_FINAL_BENCHMARK_1_EXTRA_ARGS="--task_horizon_steps 500"

SLURM_JOB_NAME=lr-custom-ie-fe-16k-b16-32
SLURM_PARTITION=dgx-b200
SLURM_QOS=normal
SLURM_GRES=gpu:1
SLURM_CPUS=28
SLURM_MEM=224G
SLURM_TIME=20:00:00