RuntimeError: Error(s) in loading state_dict for DetectionModel

[shreeramsigdel77]

Error occurred after the completion of training. In this case: after finding the best model error occurred.

Post training:
Graphs and confusion matrix should have been generated but failed. in general cannot run validation (val.py)[Tested: leads to same error]
Another error cannot convert to ONNX with official conversion script

Environment
Include all relevant environment information:

1. OS [ Ubuntu 22.04 LTS]:
2. Python version [ 3.10.12]:
3. SparseML version or commit hash [1.8.0]:
4. ML framework version(s) [ torch 2.1.2]:
5. Other Python package versions [ SparseZoo 1.8.1, ]:
6. Other relevant environment information [ CUDA version 12.2]:

To Reproduce
Trained with custom dataset (rest trained with default parameters)
sparseml.yolov5.train
--cfg yolov5s.yaml
--weights zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned75_quant-none?recipe_type=transfer_learn
--recipe zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned75_quant-none?recipe_type=transfer_learn
--data custom-data.yaml
--patience 20
--hyp hyps/hyp.finetune.yaml

Errors

Its too long so please download from here...
Sample:
yolov5sparse/mysparsevenv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2152, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for DetectionModel: Missing key(s) in state_dict:

Additional context
While converting the model to ONNX
While running val.py