-

Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

Prasyarat

    • JSON

  2. #set up a virtual environment
python3 -m venv ${PWD}/venv
source venv/bin/activate


  3. git clone https://github.com/aws/sagemaker-hyperpod-training-adapter-for-nemo.git
git clone --recursive https://github.com/aws/sagemaker-hyperpod-recipes.git
cd sagemaker-hyperpod-recipes
pip3 install -r requirements.txt


  4. REGION="<region>"
IMAGE="658645717510.dkr.ecr.${REGION}.amazonaws.com/smdistributed-modelparallel:2.4.1-gpu-py311-cu121"
aws ecr get-login-password --region ${REGION} | docker login --username AWS --password-stdin 658645717510.dkr.ecr.${REGION}.amazonaws.com
enroot import -o $PWD/smdistributed-modelparallel.sqsh dockerd://${IMAGE}
mv $PWD/smdistributed-modelparallel.sqsh "/fsx/<any-path-in-the-shared-filesystem>"


  5. container: /fsx/path/to/your/smdistributed-modelparallel.sqsh


  • recipes.model.hf_access_token=<your_hf_token>
#!/bin/bash
IMAGE="${YOUR_IMAGE}"
SAGEMAKER_TRAINING_LAUNCHER_DIR="${SAGEMAKER_TRAINING_LAUNCHER_DIR:-${PWD}}"

TRAIN_DIR="${YOUR_TRAIN_DIR}" # Location of training dataset
VAL_DIR="${YOUR_VAL_DIR}" # Location of validation dataset

# experiment ouput directory
EXP_DIR="${YOUR_EXP_DIR}"

HYDRA_FULL_ERROR=1 python3 "${SAGEMAKER_TRAINING_LAUNCHER_DIR}/main.py" \
  recipes=training/llama/hf_llama3_8b_seq16k_gpu_p5x16_pretrain \
  base_results_dir="${SAGEMAKER_TRAINING_LAUNCHER_DIR}/results" \
  recipes.run.name="hf_llama3_8b" \
  recipes.exp_manager.exp_dir="$EXP_DIR" \
  recipes.model.data.train_dir="$TRAIN_DIR" \
  recipes.model.data.val_dir="$VAL_DIR" \
  container="${IMAGE}" \
  +cluster.container_mounts.0="/fsx:/fsx" 


bash launcher_scripts/llama/run_hf_llama3_8b_seq16k_gpu_p5x16_pretrain.sh