reduce batch size for lora_llama2

stanford-crfm · Feb 13, 2024 · 8c18358 · 8c18358
1 parent c70eedc
commit 8c18358
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/config/lora_llama2.yaml b/config/lora_llama2.yaml
@@ -9,7 +9,7 @@ trainer:
     project: "levanter-lora"
     tags: ["lora", "llama2"]
   num_train_steps: 5000  # tune to suit your needs
-  train_batch_size: 128
+  train_batch_size: 64
 
   # if using model parallelism, this is useful:
   tensor_parallel_axes: ["mlp", "heads"]