I am curious on what is the MLM-accuracy of my eval-set run on the pre-trained model that google-research provided. Specifically, the bert-large-uncased model. However, when trying to execute the run_pretraining.py script to evaluate the model, I encounter the following error:
tensorflow.python.framework.errors_impl.NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Key global_step not found in checkpoint
[[node save/RestoreV2 (defined at /home/.virtualenvs/ai/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
It seems that the downloaded google-research model does not have a "global_step" Key and so I'm unable to load the model to predict the MLM-accuracy of it. Is there a way I can get the original model with checkpoints weights and all? Is anyone able to evaluate the MLM accuracy of the pre-trained models given by google-research? If so, please let me know how.
Hello all,
I am curious on what is the MLM-accuracy of my eval-set run on the pre-trained model that google-research provided. Specifically, the bert-large-uncased model. However, when trying to execute the
run_pretraining.pyscript to evaluate the model, I encounter the following error:It seems that the downloaded google-research model does not have a "global_step" Key and so I'm unable to load the model to predict the MLM-accuracy of it. Is there a way I can get the original model with checkpoints weights and all? Is anyone able to evaluate the MLM accuracy of the pre-trained models given by google-research? If so, please let me know how.