diff --git a/examples/cerebras/qlora.yml b/examples/cerebras/qlora.yml
index 9340299b9..2f3700249 100644
--- a/examples/cerebras/qlora.yml
+++ b/examples/cerebras/qlora.yml
@@ -35,7 +35,7 @@ torchdistx_path:
 lr_scheduler: cosine
 learning_rate: 0.0002
 train_on_inputs: false
-group_by_length: true
+group_by_length: false
 bf16: true
 fp16: false
 tf32: true
diff --git a/examples/gptj/qlora.yml b/examples/gptj/qlora.yml
index 858c14862..f2427f4d4 100644
--- a/examples/gptj/qlora.yml
+++ b/examples/gptj/qlora.yml
@@ -32,7 +32,7 @@ torchdistx_path:
 lr_scheduler: cosine
 learning_rate: 0.0001
 train_on_inputs: false
-group_by_length: true
+group_by_length: false
 bf16: true
 fp16: false
 tf32: true
diff --git a/examples/llama-2/lora.yml b/examples/llama-2/lora.yml
index 74934320c..494538fff 100644
--- a/examples/llama-2/lora.yml
+++ b/examples/llama-2/lora.yml
@@ -38,7 +38,7 @@ lr_scheduler: cosine
 learning_rate: 0.0002
 
 train_on_inputs: false
-group_by_length: true
+group_by_length: false
 bf16: true
 fp16: false
 tf32: false
diff --git a/examples/llama-2/qlora.yml b/examples/llama-2/qlora.yml
index 1a45e7268..64728ac3d 100644
--- a/examples/llama-2/qlora.yml
+++ b/examples/llama-2/qlora.yml
@@ -39,7 +39,7 @@ lr_scheduler: cosine
 learning_rate: 0.0002
 
 train_on_inputs: false
-group_by_length: true
+group_by_length: false
 bf16: true
 fp16: false
 tf32: false
diff --git a/examples/openllama-3b/qlora.yml b/examples/openllama-3b/qlora.yml
index 83ae31f91..dcad9bbcd 100644
--- a/examples/openllama-3b/qlora.yml
+++ b/examples/openllama-3b/qlora.yml
@@ -34,7 +34,7 @@ torchdistx_path:
 lr_scheduler: cosine
 learning_rate: 0.0002
 train_on_inputs: false
-group_by_length: true
+group_by_length: false
 bf16: true
 fp16: false
 tf32: true