Ensure delayed evaluation of SLURM_PROCID

kp-forks · Nov 12, 2024 · 4580b8f · 4580b8f
1 parent e59fd97
commit 4580b8f
Show file tree

Hide file tree

Showing 5 changed files with 5 additions and 5 deletions.
diff --git a/scripts/training/train_embonly.sh b/scripts/training/train_embonly.sh
@@ -39,7 +39,7 @@ LAUNCHER="accelerate launch \
     --main_process_ip "$MASTER_ADDR" \
     --main_process_port $MASTER_PORT \
     --num_processes $WORLD_SIZE \
-    --machine_rank $SLURM_PROCID \
+    --machine_rank \$SLURM_PROCID \
     --role $SLURMD_NODENAME: \
     --rdzv_conf rdzv_backend=c10d \
     --max_restarts 0 \

diff --git a/scripts/training/train_genonly.sh b/scripts/training/train_genonly.sh
@@ -39,7 +39,7 @@ LAUNCHER="accelerate launch \
     --main_process_ip "$MASTER_ADDR" \
     --main_process_port $MASTER_PORT \
     --num_processes $WORLD_SIZE \
-    --machine_rank $SLURM_PROCID \
+    --machine_rank \$SLURM_PROCID \
     --role $SLURMD_NODENAME: \
     --rdzv_conf rdzv_backend=c10d \
     --max_restarts 0 \

diff --git a/scripts/training/train_gritlm_7b.sh b/scripts/training/train_gritlm_7b.sh
@@ -41,7 +41,7 @@ LAUNCHER="accelerate launch \
     --main_process_ip "$MASTER_ADDR" \
     --main_process_port $MASTER_PORT \
     --num_processes $WORLD_SIZE \
-    --machine_rank $SLURM_PROCID \
+    --machine_rank \$SLURM_PROCID \
     --role $SLURMD_NODENAME: \
     --rdzv_conf rdzv_backend=c10d \
     --max_restarts 0 \

diff --git a/scripts/training/train_gritlm_8x7b.sh b/scripts/training/train_gritlm_8x7b.sh
@@ -41,7 +41,7 @@ LAUNCHER="accelerate launch \
     --main_process_ip "$MASTER_ADDR" \
     --main_process_port $MASTER_PORT \
     --num_processes $WORLD_SIZE \
-    --machine_rank $SLURM_PROCID \
+    --machine_rank \$SLURM_PROCID \
     --role $SLURMD_NODENAME: \
     --rdzv_conf rdzv_backend=c10d \
     --max_restarts 0 \

diff --git a/scripts/training/train_test.sh b/scripts/training/train_test.sh
@@ -41,7 +41,7 @@ LAUNCHER="accelerate launch \
     --main_process_ip "$MASTER_ADDR" \
     --main_process_port $MASTER_PORT \
     --num_processes $WORLD_SIZE \
-    --machine_rank $SLURM_PROCID \
+    --machine_rank \$SLURM_PROCID \
     --role $SLURMD_NODENAME: \
     --rdzv_conf rdzv_backend=c10d \
     --max_restarts 0 \