diff --git a/README.md b/README.md
index 50bd58b..14f8c7d 100644
--- a/README.md
+++ b/README.md
@@ -147,10 +147,10 @@ run python run_eval.py --checkpoint_path train_outputs/runs/.../pytorch_model.bi
 uv run python run_eval.py --checkpoint_path train_outputs/runs/May08_13-56-31_slurm0-a3nodeset-5_59383_906acb28/checkpoint-105000/pytorch_model.bin --datasets negative_nq triviaqa_retrieved squad longbench_e --split test
 
 # base model
-uv run python run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets longbench_e --split test
+uv run python run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets negative_nq triviaqa_retrieved squad longbench_e --split test
 
 # base model w/o context
-run uv run python run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets longbench_e --split test --remove_context
+run uv run python run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets negative_nq triviaqa_retrieved squad longbench_e --split test --remove_context
 
 # # benchmark
 # cd LongBench/LongBench