diff --git a/finetune/finetune_lora_ds.sh b/finetune/finetune_lora_ds.sh
index 12efc6e..d877030 100644
--- a/finetune/finetune_lora_ds.sh
+++ b/finetune/finetune_lora_ds.sh
@@ -44,4 +44,5 @@ torchrun $DISTRIBUTED_ARGS finetune.py \
     --model_max_length 2048 \
     --lazy_preprocess True \
     --use_lora \
+    --gradient_checkpointing \
     --deepspeed finetune/ds_config_zero2.json
\ No newline at end of file
diff --git a/finetune/finetune_lora_single_gpu.sh b/finetune/finetune_lora_single_gpu.sh
index 47b7237..9333b7d 100644
--- a/finetune/finetune_lora_single_gpu.sh
+++ b/finetune/finetune_lora_single_gpu.sh
@@ -32,4 +32,5 @@ python finetune.py \
   --report_to "none" \
   --model_max_length 2048 \
   --lazy_preprocess True \
+  --gradient_checkpointing \
   --use_lora
\ No newline at end of file
diff --git a/finetune/finetune_qlora_ds.sh b/finetune/finetune_qlora_ds.sh
index debea4f..58c05e9 100644
--- a/finetune/finetune_qlora_ds.sh
+++ b/finetune/finetune_qlora_ds.sh
@@ -46,4 +46,5 @@ torchrun $DISTRIBUTED_ARGS finetune.py \
     --lazy_preprocess True \
     --use_lora \
     --q_lora \
+    --gradient_checkpointing \
     --deepspeed finetune/ds_config_zero2.json
\ No newline at end of file
diff --git a/finetune/finetune_qlora_single_gpu.sh b/finetune/finetune_qlora_single_gpu.sh
index 3b89ee4..bf65b9f 100644
--- a/finetune/finetune_qlora_single_gpu.sh
+++ b/finetune/finetune_qlora_single_gpu.sh
@@ -32,5 +32,6 @@ python finetune.py \
   --report_to "none" \
   --model_max_length 2048 \
   --lazy_preprocess True \
+  --gradient_checkpointing \
   --use_lora \
   --q_lora
\ No newline at end of file