mirror of
https://github.com/huggingface/lerobot.git
synced 2026-05-16 17:20:05 +00:00
danaaubakirova
d148279921
- 2-GPU SLURM job (distributed training) - 1-GPU local accelerate and direct training scripts - Accelerate configs for 1-GPU and 2-GPU setups
68 lines
2.0 KiB
Bash
68 lines
2.0 KiB
Bash
#!/bin/bash
|
|
#SBATCH --job-name=test_accelerate
|
|
#SBATCH --nodes=1
|
|
#SBATCH --ntasks-per-node=1
|
|
#SBATCH --cpus-per-task=16
|
|
#SBATCH --gres=gpu:2
|
|
#SBATCH --time=1:00:00
|
|
#SBATCH --partition=hopper-prod
|
|
#SBATCH --output=/fsx/dana_aubakirova/vla/logs/test_accelerate_%j.out
|
|
#SBATCH --error=/fsx/dana_aubakirova/vla/logs/test_accelerate_%j.err
|
|
|
|
# Create logs directory if it doesn't exist
|
|
mkdir -p /fsx/dana_aubakirova/vla/pr/lerobot/logs
|
|
|
|
# Activate conda environment
|
|
source /fsx/dana_aubakirova/miniconda3/etc/profile.d/conda.sh
|
|
conda activate multi
|
|
|
|
# 2-GPU Test CUDA environment
|
|
export CUDA_VISIBLE_DEVICES=0,1
|
|
export PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:128,expandable_segments:True
|
|
export TORCH_DISTRIBUTED_DEBUG=OFF
|
|
export NCCL_DEBUG=INFO
|
|
export CUDA_LAUNCH_BLOCKING=0
|
|
export ACCELERATE_USE_FSDP=false
|
|
export ACCELERATE_USE_DEEPSPEED=false
|
|
export HF_ACCELERATE_DEVICE_MAP=false
|
|
export TRANSFORMERS_NO_ADVISORY_WARNINGS=1
|
|
export SAFETENSORS_FAST_GPU=1
|
|
export HF_HUB_ENABLE_HF_TRANSFER=1
|
|
export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
|
|
export ACCELERATE_TORCH_DEVICE_MAP_AUTO=false
|
|
|
|
# Change to working directory
|
|
cd /fsx/dana_aubakirova/vla/pr/lerobot
|
|
|
|
echo "=== Testing Accelerate Multi-GPU Training with SmolVLA ==="
|
|
echo "Dataset: lerobot/svla_so100_sorting"
|
|
echo "GPUs: 2"
|
|
echo "Steps: 100 (for quick test)"
|
|
echo "Job ID: $SLURM_JOB_ID"
|
|
echo ""
|
|
|
|
# Set output directory with job ID
|
|
export OUTPUT_DIR="outputs/test_accelerate_2gpu_job_${SLURM_JOB_ID}"
|
|
|
|
echo "Output directory: $OUTPUT_DIR"
|
|
echo ""
|
|
|
|
# Test accelerate training
|
|
accelerate launch --config_file accelerate_configs/2gpu_config_safe.yaml -m lerobot.scripts.train \
|
|
--policy.type=smolvla \
|
|
--policy.push_to_hub=false \
|
|
--dataset.repo_id=lerobot/svla_so100_sorting \
|
|
--dataset.video_backend=pyav \
|
|
--steps=100 \
|
|
--save_freq=50 \
|
|
--log_freq=5 \
|
|
--batch_size=2 \
|
|
--num_workers=0 \
|
|
--output_dir=$OUTPUT_DIR \
|
|
--wandb.enable=false
|
|
|
|
echo ""
|
|
echo "=== Training completed! ==="
|
|
echo "Check logs and outputs in: $OUTPUT_DIR"
|
|
echo "Job ID: $SLURM_JOB_ID"
|