Add mitch-ish 256 for LUMI (#351)

scripts/lumi/mitch-ish-7b.sh

@@ -0,0 +1,60 @@
+#!/bin/bash
+#SBATCH --job-name=v1.5-mix-medium-mitch-ish
+#SBATCH --account=project_462000229
+#SBATCH --output=/pfs/lustref1/flash/project_462000229/logs/%j.log
+#SBATCH --nodes=256             # Total number of nodes 
+#SBATCH --ntasks-per-node=8
+#SBATCH --gpus-per-node=8       # Allocate one gpu per MPI rank
+#SBATCH --cpus-per-task=6
+#SBATCH --time=48:00:00
+#SBATCH --time-min=24:00:00
+#SBATCH --mem=0			# All memory on the node
+#SBATCH --partition=standard-g
+
+module load LUMI/22.08 partition/G
+
+# export OLMO_CONTAINER=llm-lumi_latest.sif
+export OLMO_CONTAINER=llm-lumi-torch21_latest.sif
+
+export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK
+export MPICH_GPU_SUPPORT_ENABLED=1
+export NCCL_SOCKET_IFNAME=hsn
+export NCCL_NET_GDR_LEVEL=3
+export MIOPEN_USER_DB_PATH=/tmp/${USER}-miopen-cache-${SLURM_JOB_ID}
+export MIOPEN_CUSTOM_CACHE_DIR=${MIOPEN_USER_DB_PATH}
+export CXI_FORK_SAFE=1
+export CXI_FORK_SAFE_HP=1
+export FI_CXI_DISABLE_CQ_HUGETLB=1
+
+# We need to set this to avoid "Cassini Event Queue overflow detected." errors.
+export FI_CXI_DEFAULT_CQ_SIZE=131072
+
+#export NCCL_DEBUG=INFO
+export PYTHONPATH=.:${PYTHONPATH}
+export ROCM_PATH=/opt/rocm
+export SINGULARITYENV_LD_LIBRARY_PATH=/usr/local/lib:/opt/cray/libfabric/1.15.2.0/lib64
+
+# Try playing with max_split_size_mb if you run into OOM errors.
+#export PYTORCH_HIP_ALLOC_CONF=max_split_size_mb:128
+
+export DATA_PATH=$FLASH_DIR/preprocessed/olmo-mix
+export CHECKPOINTS_PATH=$FLASH_DIR/checkpoints
+export EVAL_DATA_PATH=$SCRATCH_DIR/eval-data
+
+srun \
+  --cpus-per-task=$SLURM_CPUS_PER_TASK \
+  --distribution=block:block \
+  --kill-on-bad-exit \
+  scripts/run_with_environment.sh \
+    singularity exec \
+    -B"$PROJECT_DIR:$PROJECT_DIR" \
+    -B"$FLASH_DIR:$FLASH_DIR" \
+    -B"$SCRATCH_DIR:$SCRATCH_DIR" \
+    -B /opt/cray:/opt/cray \
+    -B /usr/lib64/libcxi.so.1:/usr/lib64/libcxi.so.1 \
+    -B /usr/lib64/libjson-c.so.3:/usr/lib64/libjson-c.so.3 \
+    $PROJECT_DIR/containers/$OLMO_CONTAINER \
+    python scripts/train.py configs/v1_5-mix-medium-mitch-ish.yaml ${@} \
+      --run_name=${SLURM_JOB_ID} \
+      --global_train_batch_size=4096 \
+      --max_duration=238418