yolov3: reduce batch size due to OOM (#111959)

yolov3 w/ cudagraphs (known to use more memory) is failing perf test due to OOM (https://hud.pytorch.org/benchmark/torchbench/inductor_with_cudagraphs?startTime=Mon,%2016%20Oct%202023%2020:19:47%20GMT&stopTime=Mon,%2023%20Oct%202023%2020:19:47%20GMT&granularity=hour&mode=training&dtype=amp&lBranch=main&lCommit=0b424ee0b7bfe09e0a438a63e8336e95eea85901&rBranch=main&rCommit=29048be41ca3aa8974795d93b9ea9fd6dee415fc)

I'm reducing the batch size from 16 to 8 to keep the same batch size for all yolov3 HUD benchmarks

Pull Request resolved: #111959
Approved by: https://github.com/xuzhao9

benchmarks/dynamo/torchbench.py

@@ -56,6 +56,7 @@ def setup_torchbench_cwd():
     "hf_T5_base": 4,
     "timm_efficientdet": 1,
     "llama_v2_7b_16h": 1,
+    "yolov3": 8,  # reduced from 16 due to cudagraphs OOM in TorchInductor dashboard
 }
 
 DETECTRON2_MODELS = {