summaryrefslogtreecommitdiff
path: root/scripts/slurm_train.sh
diff options
context:
space:
mode:
Diffstat (limited to 'scripts/slurm_train.sh')
-rw-r--r--scripts/slurm_train.sh4
1 files changed, 3 insertions, 1 deletions
diff --git a/scripts/slurm_train.sh b/scripts/slurm_train.sh
index e1df687..361ba94 100644
--- a/scripts/slurm_train.sh
+++ b/scripts/slurm_train.sh
@@ -1,4 +1,5 @@
#!/bin/bash
+#SBATCH --signal=SIGUSR1@120
export HF_HOME=/projects/bfqt/users/yurenh2/hf_cache
export TRANSFORMERS_CACHE=/projects/bfqt/users/yurenh2/hf_cache/transformers
export HF_HUB_CACHE=/projects/bfqt/users/yurenh2/hf_cache/hub
@@ -18,4 +19,5 @@ echo "GPU: $(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader)"
echo ""
echo "=== Starting training ==="
-python3 -u scripts/train.py --config configs/sanity_check.yaml
+echo " Auto-resume enabled: will pick up from latest checkpoint"
+python3 -u scripts/train.py --config ${CONFIG:-configs/sanity_check.yaml}