temporary: the only valid use of a module is looking up an attribute but found = prim::SetAttr[name="num_batches_tracked"](%self, %11)

## 🐞Describe the bug
I got this error while:
nn.BatchNorm2d -> torch.jit.script -> coreml

## Trace
```python3
Traceback (most recent call last):
File "mini_code.py", line 13, in
model = ct.convert(
File "/opt/conda/lib/python3.8/site-packages/coremltools/converters/_converters_entry.py", line 175, in convert
mlmodel = mil_convert(
File "/opt/conda/lib/python3.8/site-packages/coremltools/converters/mil/converter.py", line 128, in mil_convert
proto = mil_convert_to_proto(model, convert_from, convert_to,
File "/opt/conda/lib/python3.8/site-packages/coremltools/converters/mil/converter.py", line 171, in mil_convert_to_proto
prog = frontend_converter(model, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/coremltools/converters/mil/converter.py", line 85, in __call__
return load(*args, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/coremltools/converters/mil/frontend/torch/load.py", line 70, in load
converter = TorchConverter(torchscript, inputs, outputs, cut_at_symbols)
File "/opt/conda/lib/python3.8/site-packages/coremltools/converters/mil/frontend/torch/converter.py", line 145, in __init__
raw_graph, params_dict = self._expand_and_optimize_ir(self.torchscript)
File "/opt/conda/lib/python3.8/site-packages/coremltools/converters/mil/frontend/torch/converter.py", line 262, in _expand_and_optimize_ir
graph, params = _torch._C._jit_pass_lower_graph(
RuntimeError:
temporary: the only valid use of a module is looking up an attribute but found = prim::SetAttr[name="num_batches_tracked"](%self, %11)
:
```

## To Reproduce
```
import torch
import coremltools as ct

# init torch module
torch_model = torch.nn.BatchNorm2d(3)

# script
script_model = torch.jit.script(torch_model)

# Convert to Core ML using the Unified Conversion API
model = ct.convert(
script_model,
inputs=[ct.ImageType(name="input", shape=(1, 3, 224, 224))],
)
```

## System environment (please complete the following information):
- coremltools version (e.g., 3.0b5): 4.1
- OS (e.g., MacOS, Linux): Ubuntu20.04 LTS
- How you install python (anaconda, virtualenv, system): miniconda
- python version (e.g. 3.7): 3.8.5
- any other relevant information:
- pytorch version: 1.9.0
- gpu: GeForce GTX 1650
- driver: Driver Version: 460.80
- CUDA: CUDA Version: 11.2

Reproduce the BatchNorm2d conversion from the provided script, then start in coremltools/converters/mil/frontend/torch/load.py and converter.py around _expand_and_optimize_ir and the torch lower-graph call. Compare the generated TorchScript graph with the reported prim::SetAttr error. Done means this repro converts successfully without the runtime error, with regression coverage for the case.

Written by the indexing model from the issue text.