diff --git a/recipes/launch.slurm b/recipes/launch.slurm index 15ef4b6..17f1afc 100644 --- a/recipes/launch.slurm +++ b/recipes/launch.slurm @@ -24,7 +24,7 @@ GPUS_PER_NODE=8 WORLD_SIZE=$(($NUM_NODES*$GPUS_PER_NODE)) # Due to conflicts between Accelerate's DeepSpeed configs and Transformers' TrainingArguments, we need to parse the gradient accumulation steps from the config file to ensure they match CONFIG_FILE=recipes/$MODEL/$TASK/config_$PRECISION.yaml -GRAD_ACC_STEPS=$(yq -r .gradient_accumulation_steps $CONFIG_FILE) +GRAD_ACC_STEPS=$(grep 'gradient_accumulation_steps' $CONFIG_FILE | awk '{print $2}') # Split the string into individual arguments IFS=' ' read -ra ARGS <<< "$OPTIONAL_ARGS"