Transformers: Loading pre-trained ELECTRA checkpoint to HuggingFace

Created on 7 Apr 2020  ·  7Comments  ·  Source: huggingface/transformers

❓ Questions & Help

Hello everyone!

I have been struggling with HuggingFace interface for loading ELECTRA model via transformers.TFElectraModel class. Since TF version of ElectraModel didn't manage to help me restore the checkpoint from the official Google Research implementation (they save only .ckpl files) due to this error:

NotImplementedError: Weights may only be loaded based on topology into Models when loading TensorFlow-formatted weights (got by_name=True to load_weights).

However, the normal ElectraModel.from_pretrained() procedure managed to load my model, writing this to the stdout:

Skipping discriminator_predictions/dense/bias ['discriminator_predictions', 'dense', 'bias'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense/bias/adam_m ['discriminator_predictions', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense/bias/adam_v ['discriminator_predictions', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense/kernel ['discriminator_predictions', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense/kernel/adam_m ['discriminator_predictions', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense/kernel/adam_v ['discriminator_predictions', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense_1/bias ['discriminator_predictions', 'dense_prediction', 'bias'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense_1/bias/adam_m ['discriminator_predictions', 'dense_prediction', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense_1/bias/adam_v ['discriminator_predictions', 'dense_prediction', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense_1/kernel ['discriminator_predictions', 'dense_prediction', 'kernel'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense_1/kernel/adam_m ['discriminator_predictions', 'dense_prediction', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping discriminator_predictions/dense_1/kernel/adam_v ['discriminator_predictions', 'dense_prediction', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'discriminator_predictions'
Skipping electra/embeddings/LayerNorm/beta ['electra', 'embeddings', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/LayerNorm/beta/adam_m ['electra', 'embeddings', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/LayerNorm/beta/adam_v ['electra', 'embeddings', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/LayerNorm/gamma ['electra', 'embeddings', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/LayerNorm/gamma/adam_m ['electra', 'embeddings', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/LayerNorm/gamma/adam_v ['electra', 'embeddings', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/position_embeddings ['electra', 'embeddings', 'position_embeddings'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/position_embeddings/adam_m ['electra', 'embeddings', 'position_embeddings', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/position_embeddings/adam_v ['electra', 'embeddings', 'position_embeddings', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/token_type_embeddings ['electra', 'embeddings', 'token_type_embeddings'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/token_type_embeddings/adam_m ['electra', 'embeddings', 'token_type_embeddings', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/token_type_embeddings/adam_v ['electra', 'embeddings', 'token_type_embeddings', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/word_embeddings ['electra', 'embeddings', 'word_embeddings'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/word_embeddings/adam_m ['electra', 'embeddings', 'word_embeddings', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/embeddings/word_embeddings/adam_v ['electra', 'embeddings', 'word_embeddings', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/dense/bias ['electra', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/dense/kernel ['electra', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/key/bias ['electra', 'encoder', 'layer_0', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_0', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_0', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/key/kernel ['electra', 'encoder', 'layer_0', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_0', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_0', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/query/bias ['electra', 'encoder', 'layer_0', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_0', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_0', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/query/kernel ['electra', 'encoder', 'layer_0', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_0', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_0', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/value/bias ['electra', 'encoder', 'layer_0', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_0', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_0', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/value/kernel ['electra', 'encoder', 'layer_0', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_0', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_0', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/intermediate/dense/bias ['electra', 'encoder', 'layer_0', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_0', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_0', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/intermediate/dense/kernel ['electra', 'encoder', 'layer_0', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_0', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_0', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/LayerNorm/beta ['electra', 'encoder', 'layer_0', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_0', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_0', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/LayerNorm/gamma ['electra', 'encoder', 'layer_0', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_0', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_0', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/dense/bias ['electra', 'encoder', 'layer_0', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/dense/bias/adam_m ['electra', 'encoder', 'layer_0', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/dense/bias/adam_v ['electra', 'encoder', 'layer_0', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/dense/kernel ['electra', 'encoder', 'layer_0', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_0', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_0/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_0', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/dense/bias ['electra', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/dense/kernel ['electra', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/key/bias ['electra', 'encoder', 'layer_1', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_1', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_1', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/key/kernel ['electra', 'encoder', 'layer_1', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_1', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_1', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/query/bias ['electra', 'encoder', 'layer_1', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_1', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_1', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/query/kernel ['electra', 'encoder', 'layer_1', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_1', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_1', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/value/bias ['electra', 'encoder', 'layer_1', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_1', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_1', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/value/kernel ['electra', 'encoder', 'layer_1', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_1', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_1', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/intermediate/dense/bias ['electra', 'encoder', 'layer_1', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_1', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_1', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/intermediate/dense/kernel ['electra', 'encoder', 'layer_1', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_1', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_1', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/LayerNorm/beta ['electra', 'encoder', 'layer_1', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_1', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_1', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/LayerNorm/gamma ['electra', 'encoder', 'layer_1', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_1', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_1', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/dense/bias ['electra', 'encoder', 'layer_1', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/dense/bias/adam_m ['electra', 'encoder', 'layer_1', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/dense/bias/adam_v ['electra', 'encoder', 'layer_1', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/dense/kernel ['electra', 'encoder', 'layer_1', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_1', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_1/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_1', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/dense/bias ['electra', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/dense/kernel ['electra', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/key/bias ['electra', 'encoder', 'layer_10', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_10', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_10', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/key/kernel ['electra', 'encoder', 'layer_10', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_10', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_10', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/query/bias ['electra', 'encoder', 'layer_10', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_10', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_10', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/query/kernel ['electra', 'encoder', 'layer_10', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_10', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_10', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/value/bias ['electra', 'encoder', 'layer_10', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_10', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_10', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/value/kernel ['electra', 'encoder', 'layer_10', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_10', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_10', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/intermediate/dense/bias ['electra', 'encoder', 'layer_10', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_10', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_10', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/intermediate/dense/kernel ['electra', 'encoder', 'layer_10', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_10', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_10', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/LayerNorm/beta ['electra', 'encoder', 'layer_10', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_10', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_10', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/LayerNorm/gamma ['electra', 'encoder', 'layer_10', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_10', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_10', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/dense/bias ['electra', 'encoder', 'layer_10', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/dense/bias/adam_m ['electra', 'encoder', 'layer_10', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/dense/bias/adam_v ['electra', 'encoder', 'layer_10', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/dense/kernel ['electra', 'encoder', 'layer_10', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_10', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_10/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_10', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/dense/bias ['electra', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/dense/kernel ['electra', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/key/bias ['electra', 'encoder', 'layer_11', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_11', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_11', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/key/kernel ['electra', 'encoder', 'layer_11', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_11', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_11', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/query/bias ['electra', 'encoder', 'layer_11', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_11', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_11', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/query/kernel ['electra', 'encoder', 'layer_11', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_11', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_11', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/value/bias ['electra', 'encoder', 'layer_11', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_11', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_11', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/value/kernel ['electra', 'encoder', 'layer_11', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_11', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_11', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/intermediate/dense/bias ['electra', 'encoder', 'layer_11', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_11', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_11', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/intermediate/dense/kernel ['electra', 'encoder', 'layer_11', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_11', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_11', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/LayerNorm/beta ['electra', 'encoder', 'layer_11', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_11', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_11', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/LayerNorm/gamma ['electra', 'encoder', 'layer_11', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_11', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_11', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/dense/bias ['electra', 'encoder', 'layer_11', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/dense/bias/adam_m ['electra', 'encoder', 'layer_11', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/dense/bias/adam_v ['electra', 'encoder', 'layer_11', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/dense/kernel ['electra', 'encoder', 'layer_11', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_11', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_11/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_11', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/dense/bias ['electra', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/dense/kernel ['electra', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/key/bias ['electra', 'encoder', 'layer_2', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_2', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_2', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/key/kernel ['electra', 'encoder', 'layer_2', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_2', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_2', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/query/bias ['electra', 'encoder', 'layer_2', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_2', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_2', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/query/kernel ['electra', 'encoder', 'layer_2', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_2', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_2', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/value/bias ['electra', 'encoder', 'layer_2', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_2', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_2', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/value/kernel ['electra', 'encoder', 'layer_2', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_2', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_2', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/intermediate/dense/bias ['electra', 'encoder', 'layer_2', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_2', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_2', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/intermediate/dense/kernel ['electra', 'encoder', 'layer_2', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_2', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_2', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/LayerNorm/beta ['electra', 'encoder', 'layer_2', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_2', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_2', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/LayerNorm/gamma ['electra', 'encoder', 'layer_2', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_2', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_2', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/dense/bias ['electra', 'encoder', 'layer_2', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/dense/bias/adam_m ['electra', 'encoder', 'layer_2', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/dense/bias/adam_v ['electra', 'encoder', 'layer_2', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/dense/kernel ['electra', 'encoder', 'layer_2', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_2', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_2/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_2', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/dense/bias ['electra', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/dense/kernel ['electra', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/key/bias ['electra', 'encoder', 'layer_3', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_3', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_3', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/key/kernel ['electra', 'encoder', 'layer_3', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_3', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_3', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/query/bias ['electra', 'encoder', 'layer_3', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_3', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_3', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/query/kernel ['electra', 'encoder', 'layer_3', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_3', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_3', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/value/bias ['electra', 'encoder', 'layer_3', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_3', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_3', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/value/kernel ['electra', 'encoder', 'layer_3', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_3', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_3', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/intermediate/dense/bias ['electra', 'encoder', 'layer_3', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_3', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_3', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/intermediate/dense/kernel ['electra', 'encoder', 'layer_3', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_3', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_3', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/LayerNorm/beta ['electra', 'encoder', 'layer_3', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_3', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_3', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/LayerNorm/gamma ['electra', 'encoder', 'layer_3', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_3', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_3', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/dense/bias ['electra', 'encoder', 'layer_3', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/dense/bias/adam_m ['electra', 'encoder', 'layer_3', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/dense/bias/adam_v ['electra', 'encoder', 'layer_3', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/dense/kernel ['electra', 'encoder', 'layer_3', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_3', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_3/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_3', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/dense/bias ['electra', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/dense/kernel ['electra', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/key/bias ['electra', 'encoder', 'layer_4', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_4', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_4', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/key/kernel ['electra', 'encoder', 'layer_4', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_4', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_4', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/query/bias ['electra', 'encoder', 'layer_4', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_4', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_4', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/query/kernel ['electra', 'encoder', 'layer_4', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_4', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_4', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/value/bias ['electra', 'encoder', 'layer_4', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_4', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_4', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/value/kernel ['electra', 'encoder', 'layer_4', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_4', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_4', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/intermediate/dense/bias ['electra', 'encoder', 'layer_4', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_4', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_4', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/intermediate/dense/kernel ['electra', 'encoder', 'layer_4', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_4', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_4', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/LayerNorm/beta ['electra', 'encoder', 'layer_4', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_4', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_4', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/LayerNorm/gamma ['electra', 'encoder', 'layer_4', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_4', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_4', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/dense/bias ['electra', 'encoder', 'layer_4', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/dense/bias/adam_m ['electra', 'encoder', 'layer_4', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/dense/bias/adam_v ['electra', 'encoder', 'layer_4', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/dense/kernel ['electra', 'encoder', 'layer_4', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_4', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_4/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_4', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/dense/bias ['electra', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/dense/kernel ['electra', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/key/bias ['electra', 'encoder', 'layer_5', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_5', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_5', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/key/kernel ['electra', 'encoder', 'layer_5', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_5', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_5', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/query/bias ['electra', 'encoder', 'layer_5', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_5', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_5', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/query/kernel ['electra', 'encoder', 'layer_5', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_5', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_5', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/value/bias ['electra', 'encoder', 'layer_5', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_5', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_5', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/value/kernel ['electra', 'encoder', 'layer_5', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_5', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_5', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/intermediate/dense/bias ['electra', 'encoder', 'layer_5', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_5', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_5', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/intermediate/dense/kernel ['electra', 'encoder', 'layer_5', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_5', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_5', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/LayerNorm/beta ['electra', 'encoder', 'layer_5', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_5', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_5', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/LayerNorm/gamma ['electra', 'encoder', 'layer_5', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_5', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_5', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/dense/bias ['electra', 'encoder', 'layer_5', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/dense/bias/adam_m ['electra', 'encoder', 'layer_5', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/dense/bias/adam_v ['electra', 'encoder', 'layer_5', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/dense/kernel ['electra', 'encoder', 'layer_5', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_5', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_5/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_5', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/dense/bias ['electra', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/dense/kernel ['electra', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/key/bias ['electra', 'encoder', 'layer_6', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_6', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_6', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/key/kernel ['electra', 'encoder', 'layer_6', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_6', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_6', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/query/bias ['electra', 'encoder', 'layer_6', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_6', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_6', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/query/kernel ['electra', 'encoder', 'layer_6', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_6', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_6', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/value/bias ['electra', 'encoder', 'layer_6', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_6', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_6', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/value/kernel ['electra', 'encoder', 'layer_6', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_6', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_6', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/intermediate/dense/bias ['electra', 'encoder', 'layer_6', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_6', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_6', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/intermediate/dense/kernel ['electra', 'encoder', 'layer_6', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_6', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_6', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/LayerNorm/beta ['electra', 'encoder', 'layer_6', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_6', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_6', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/LayerNorm/gamma ['electra', 'encoder', 'layer_6', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_6', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_6', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/dense/bias ['electra', 'encoder', 'layer_6', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/dense/bias/adam_m ['electra', 'encoder', 'layer_6', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/dense/bias/adam_v ['electra', 'encoder', 'layer_6', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/dense/kernel ['electra', 'encoder', 'layer_6', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_6', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_6/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_6', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/dense/bias ['electra', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/dense/kernel ['electra', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/key/bias ['electra', 'encoder', 'layer_7', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_7', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_7', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/key/kernel ['electra', 'encoder', 'layer_7', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_7', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_7', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/query/bias ['electra', 'encoder', 'layer_7', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_7', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_7', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/query/kernel ['electra', 'encoder', 'layer_7', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_7', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_7', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/value/bias ['electra', 'encoder', 'layer_7', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_7', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_7', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/value/kernel ['electra', 'encoder', 'layer_7', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_7', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_7', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/intermediate/dense/bias ['electra', 'encoder', 'layer_7', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_7', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_7', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/intermediate/dense/kernel ['electra', 'encoder', 'layer_7', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_7', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_7', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/LayerNorm/beta ['electra', 'encoder', 'layer_7', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_7', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_7', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/LayerNorm/gamma ['electra', 'encoder', 'layer_7', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_7', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_7', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/dense/bias ['electra', 'encoder', 'layer_7', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/dense/bias/adam_m ['electra', 'encoder', 'layer_7', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/dense/bias/adam_v ['electra', 'encoder', 'layer_7', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/dense/kernel ['electra', 'encoder', 'layer_7', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_7', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_7/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_7', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/dense/bias ['electra', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/dense/kernel ['electra', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/key/bias ['electra', 'encoder', 'layer_8', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_8', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_8', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/key/kernel ['electra', 'encoder', 'layer_8', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_8', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_8', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/query/bias ['electra', 'encoder', 'layer_8', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_8', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_8', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/query/kernel ['electra', 'encoder', 'layer_8', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_8', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_8', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/value/bias ['electra', 'encoder', 'layer_8', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_8', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_8', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/value/kernel ['electra', 'encoder', 'layer_8', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_8', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_8', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/intermediate/dense/bias ['electra', 'encoder', 'layer_8', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_8', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_8', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/intermediate/dense/kernel ['electra', 'encoder', 'layer_8', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_8', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_8', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/LayerNorm/beta ['electra', 'encoder', 'layer_8', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_8', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_8', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/LayerNorm/gamma ['electra', 'encoder', 'layer_8', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_8', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_8', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/dense/bias ['electra', 'encoder', 'layer_8', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/dense/bias/adam_m ['electra', 'encoder', 'layer_8', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/dense/bias/adam_v ['electra', 'encoder', 'layer_8', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/dense/kernel ['electra', 'encoder', 'layer_8', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_8', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_8/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_8', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/LayerNorm/beta ['electra', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/LayerNorm/gamma ['electra', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/dense/bias ['electra', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/dense/bias/adam_m ['electra', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/dense/bias/adam_v ['electra', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/dense/kernel ['electra', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/key/bias ['electra', 'encoder', 'layer_9', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/key/bias/adam_m ['electra', 'encoder', 'layer_9', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/key/bias/adam_v ['electra', 'encoder', 'layer_9', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/key/kernel ['electra', 'encoder', 'layer_9', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/key/kernel/adam_m ['electra', 'encoder', 'layer_9', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/key/kernel/adam_v ['electra', 'encoder', 'layer_9', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/query/bias ['electra', 'encoder', 'layer_9', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/query/bias/adam_m ['electra', 'encoder', 'layer_9', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/query/bias/adam_v ['electra', 'encoder', 'layer_9', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/query/kernel ['electra', 'encoder', 'layer_9', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/query/kernel/adam_m ['electra', 'encoder', 'layer_9', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/query/kernel/adam_v ['electra', 'encoder', 'layer_9', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/value/bias ['electra', 'encoder', 'layer_9', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/value/bias/adam_m ['electra', 'encoder', 'layer_9', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/value/bias/adam_v ['electra', 'encoder', 'layer_9', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/value/kernel ['electra', 'encoder', 'layer_9', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/value/kernel/adam_m ['electra', 'encoder', 'layer_9', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/attention/self/value/kernel/adam_v ['electra', 'encoder', 'layer_9', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/intermediate/dense/bias ['electra', 'encoder', 'layer_9', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/intermediate/dense/bias/adam_m ['electra', 'encoder', 'layer_9', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/intermediate/dense/bias/adam_v ['electra', 'encoder', 'layer_9', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/intermediate/dense/kernel ['electra', 'encoder', 'layer_9', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/intermediate/dense/kernel/adam_m ['electra', 'encoder', 'layer_9', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/intermediate/dense/kernel/adam_v ['electra', 'encoder', 'layer_9', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/LayerNorm/beta ['electra', 'encoder', 'layer_9', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/LayerNorm/beta/adam_m ['electra', 'encoder', 'layer_9', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/LayerNorm/beta/adam_v ['electra', 'encoder', 'layer_9', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/LayerNorm/gamma ['electra', 'encoder', 'layer_9', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/LayerNorm/gamma/adam_m ['electra', 'encoder', 'layer_9', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/LayerNorm/gamma/adam_v ['electra', 'encoder', 'layer_9', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/dense/bias ['electra', 'encoder', 'layer_9', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/dense/bias/adam_m ['electra', 'encoder', 'layer_9', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/dense/bias/adam_v ['electra', 'encoder', 'layer_9', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/dense/kernel ['electra', 'encoder', 'layer_9', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/dense/kernel/adam_m ['electra', 'encoder', 'layer_9', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'electra'
Skipping electra/encoder/layer_9/output/dense/kernel/adam_v ['electra', 'encoder', 'layer_9', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'electra'
Skipping generator/embeddings_project/bias ['generator', 'embeddings_project', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/embeddings_project/bias/adam_m ['generator', 'embeddings_project', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/embeddings_project/bias/adam_v ['generator', 'embeddings_project', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/embeddings_project/kernel ['generator', 'embeddings_project', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/embeddings_project/kernel/adam_m ['generator', 'embeddings_project', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/embeddings_project/kernel/adam_v ['generator', 'embeddings_project', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_0', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/dense/bias ['generator', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/dense/kernel ['generator', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_0', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/key/bias ['generator', 'encoder', 'layer_0', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_0', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_0', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/key/kernel ['generator', 'encoder', 'layer_0', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_0', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_0', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/query/bias ['generator', 'encoder', 'layer_0', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_0', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_0', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/query/kernel ['generator', 'encoder', 'layer_0', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_0', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_0', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/value/bias ['generator', 'encoder', 'layer_0', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_0', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_0', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/value/kernel ['generator', 'encoder', 'layer_0', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_0', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_0', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/intermediate/dense/bias ['generator', 'encoder', 'layer_0', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_0', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_0', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/intermediate/dense/kernel ['generator', 'encoder', 'layer_0', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_0', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_0', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/LayerNorm/beta ['generator', 'encoder', 'layer_0', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_0', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_0', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/LayerNorm/gamma ['generator', 'encoder', 'layer_0', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_0', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_0', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/dense/bias ['generator', 'encoder', 'layer_0', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/dense/bias/adam_m ['generator', 'encoder', 'layer_0', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/dense/bias/adam_v ['generator', 'encoder', 'layer_0', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/dense/kernel ['generator', 'encoder', 'layer_0', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_0', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_0/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_0', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_1', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/dense/bias ['generator', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/dense/kernel ['generator', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_1', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/key/bias ['generator', 'encoder', 'layer_1', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_1', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_1', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/key/kernel ['generator', 'encoder', 'layer_1', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_1', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_1', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/query/bias ['generator', 'encoder', 'layer_1', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_1', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_1', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/query/kernel ['generator', 'encoder', 'layer_1', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_1', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_1', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/value/bias ['generator', 'encoder', 'layer_1', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_1', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_1', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/value/kernel ['generator', 'encoder', 'layer_1', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_1', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_1', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/intermediate/dense/bias ['generator', 'encoder', 'layer_1', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_1', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_1', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/intermediate/dense/kernel ['generator', 'encoder', 'layer_1', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_1', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_1', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/LayerNorm/beta ['generator', 'encoder', 'layer_1', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_1', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_1', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/LayerNorm/gamma ['generator', 'encoder', 'layer_1', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_1', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_1', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/dense/bias ['generator', 'encoder', 'layer_1', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/dense/bias/adam_m ['generator', 'encoder', 'layer_1', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/dense/bias/adam_v ['generator', 'encoder', 'layer_1', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/dense/kernel ['generator', 'encoder', 'layer_1', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_1', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_1/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_1', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_10', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/dense/bias ['generator', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/dense/kernel ['generator', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_10', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/key/bias ['generator', 'encoder', 'layer_10', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_10', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_10', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/key/kernel ['generator', 'encoder', 'layer_10', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_10', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_10', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/query/bias ['generator', 'encoder', 'layer_10', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_10', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_10', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/query/kernel ['generator', 'encoder', 'layer_10', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_10', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_10', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/value/bias ['generator', 'encoder', 'layer_10', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_10', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_10', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/value/kernel ['generator', 'encoder', 'layer_10', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_10', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_10', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/intermediate/dense/bias ['generator', 'encoder', 'layer_10', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_10', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_10', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/intermediate/dense/kernel ['generator', 'encoder', 'layer_10', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_10', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_10', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/LayerNorm/beta ['generator', 'encoder', 'layer_10', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_10', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_10', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/LayerNorm/gamma ['generator', 'encoder', 'layer_10', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_10', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_10', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/dense/bias ['generator', 'encoder', 'layer_10', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/dense/bias/adam_m ['generator', 'encoder', 'layer_10', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/dense/bias/adam_v ['generator', 'encoder', 'layer_10', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/dense/kernel ['generator', 'encoder', 'layer_10', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_10', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_10/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_10', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_11', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/dense/bias ['generator', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/dense/kernel ['generator', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_11', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/key/bias ['generator', 'encoder', 'layer_11', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_11', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_11', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/key/kernel ['generator', 'encoder', 'layer_11', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_11', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_11', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/query/bias ['generator', 'encoder', 'layer_11', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_11', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_11', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/query/kernel ['generator', 'encoder', 'layer_11', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_11', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_11', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/value/bias ['generator', 'encoder', 'layer_11', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_11', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_11', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/value/kernel ['generator', 'encoder', 'layer_11', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_11', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_11', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/intermediate/dense/bias ['generator', 'encoder', 'layer_11', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_11', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_11', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/intermediate/dense/kernel ['generator', 'encoder', 'layer_11', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_11', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_11', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/LayerNorm/beta ['generator', 'encoder', 'layer_11', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_11', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_11', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/LayerNorm/gamma ['generator', 'encoder', 'layer_11', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_11', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_11', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/dense/bias ['generator', 'encoder', 'layer_11', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/dense/bias/adam_m ['generator', 'encoder', 'layer_11', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/dense/bias/adam_v ['generator', 'encoder', 'layer_11', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/dense/kernel ['generator', 'encoder', 'layer_11', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_11', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_11/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_11', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_2', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/dense/bias ['generator', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/dense/kernel ['generator', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_2', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/key/bias ['generator', 'encoder', 'layer_2', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_2', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_2', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/key/kernel ['generator', 'encoder', 'layer_2', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_2', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_2', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/query/bias ['generator', 'encoder', 'layer_2', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_2', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_2', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/query/kernel ['generator', 'encoder', 'layer_2', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_2', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_2', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/value/bias ['generator', 'encoder', 'layer_2', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_2', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_2', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/value/kernel ['generator', 'encoder', 'layer_2', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_2', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_2', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/intermediate/dense/bias ['generator', 'encoder', 'layer_2', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_2', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_2', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/intermediate/dense/kernel ['generator', 'encoder', 'layer_2', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_2', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_2', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/LayerNorm/beta ['generator', 'encoder', 'layer_2', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_2', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_2', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/LayerNorm/gamma ['generator', 'encoder', 'layer_2', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_2', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_2', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/dense/bias ['generator', 'encoder', 'layer_2', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/dense/bias/adam_m ['generator', 'encoder', 'layer_2', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/dense/bias/adam_v ['generator', 'encoder', 'layer_2', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/dense/kernel ['generator', 'encoder', 'layer_2', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_2', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_2/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_2', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_3', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/dense/bias ['generator', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/dense/kernel ['generator', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_3', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/key/bias ['generator', 'encoder', 'layer_3', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_3', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_3', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/key/kernel ['generator', 'encoder', 'layer_3', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_3', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_3', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/query/bias ['generator', 'encoder', 'layer_3', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_3', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_3', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/query/kernel ['generator', 'encoder', 'layer_3', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_3', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_3', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/value/bias ['generator', 'encoder', 'layer_3', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_3', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_3', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/value/kernel ['generator', 'encoder', 'layer_3', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_3', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_3', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/intermediate/dense/bias ['generator', 'encoder', 'layer_3', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_3', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_3', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/intermediate/dense/kernel ['generator', 'encoder', 'layer_3', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_3', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_3', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/LayerNorm/beta ['generator', 'encoder', 'layer_3', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_3', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_3', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/LayerNorm/gamma ['generator', 'encoder', 'layer_3', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_3', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_3', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/dense/bias ['generator', 'encoder', 'layer_3', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/dense/bias/adam_m ['generator', 'encoder', 'layer_3', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/dense/bias/adam_v ['generator', 'encoder', 'layer_3', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/dense/kernel ['generator', 'encoder', 'layer_3', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_3', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_3/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_3', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_4', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/dense/bias ['generator', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/dense/kernel ['generator', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_4', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/key/bias ['generator', 'encoder', 'layer_4', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_4', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_4', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/key/kernel ['generator', 'encoder', 'layer_4', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_4', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_4', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/query/bias ['generator', 'encoder', 'layer_4', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_4', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_4', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/query/kernel ['generator', 'encoder', 'layer_4', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_4', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_4', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/value/bias ['generator', 'encoder', 'layer_4', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_4', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_4', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/value/kernel ['generator', 'encoder', 'layer_4', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_4', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_4', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/intermediate/dense/bias ['generator', 'encoder', 'layer_4', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_4', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_4', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/intermediate/dense/kernel ['generator', 'encoder', 'layer_4', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_4', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_4', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/LayerNorm/beta ['generator', 'encoder', 'layer_4', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_4', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_4', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/LayerNorm/gamma ['generator', 'encoder', 'layer_4', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_4', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_4', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/dense/bias ['generator', 'encoder', 'layer_4', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/dense/bias/adam_m ['generator', 'encoder', 'layer_4', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/dense/bias/adam_v ['generator', 'encoder', 'layer_4', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/dense/kernel ['generator', 'encoder', 'layer_4', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_4', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_4/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_4', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_5', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/dense/bias ['generator', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/dense/kernel ['generator', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_5', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/key/bias ['generator', 'encoder', 'layer_5', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_5', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_5', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/key/kernel ['generator', 'encoder', 'layer_5', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_5', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_5', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/query/bias ['generator', 'encoder', 'layer_5', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_5', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_5', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/query/kernel ['generator', 'encoder', 'layer_5', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_5', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_5', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/value/bias ['generator', 'encoder', 'layer_5', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_5', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_5', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/value/kernel ['generator', 'encoder', 'layer_5', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_5', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_5', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/intermediate/dense/bias ['generator', 'encoder', 'layer_5', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_5', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_5', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/intermediate/dense/kernel ['generator', 'encoder', 'layer_5', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_5', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_5', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/LayerNorm/beta ['generator', 'encoder', 'layer_5', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_5', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_5', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/LayerNorm/gamma ['generator', 'encoder', 'layer_5', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_5', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_5', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/dense/bias ['generator', 'encoder', 'layer_5', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/dense/bias/adam_m ['generator', 'encoder', 'layer_5', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/dense/bias/adam_v ['generator', 'encoder', 'layer_5', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/dense/kernel ['generator', 'encoder', 'layer_5', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_5', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_5/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_5', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_6', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/dense/bias ['generator', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/dense/kernel ['generator', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_6', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/key/bias ['generator', 'encoder', 'layer_6', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_6', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_6', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/key/kernel ['generator', 'encoder', 'layer_6', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_6', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_6', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/query/bias ['generator', 'encoder', 'layer_6', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_6', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_6', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/query/kernel ['generator', 'encoder', 'layer_6', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_6', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_6', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/value/bias ['generator', 'encoder', 'layer_6', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_6', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_6', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/value/kernel ['generator', 'encoder', 'layer_6', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_6', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_6', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/intermediate/dense/bias ['generator', 'encoder', 'layer_6', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_6', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_6', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/intermediate/dense/kernel ['generator', 'encoder', 'layer_6', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_6', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_6', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/LayerNorm/beta ['generator', 'encoder', 'layer_6', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_6', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_6', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/LayerNorm/gamma ['generator', 'encoder', 'layer_6', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_6', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_6', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/dense/bias ['generator', 'encoder', 'layer_6', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/dense/bias/adam_m ['generator', 'encoder', 'layer_6', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/dense/bias/adam_v ['generator', 'encoder', 'layer_6', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/dense/kernel ['generator', 'encoder', 'layer_6', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_6', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_6/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_6', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_7', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/dense/bias ['generator', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/dense/kernel ['generator', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_7', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/key/bias ['generator', 'encoder', 'layer_7', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_7', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_7', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/key/kernel ['generator', 'encoder', 'layer_7', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_7', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_7', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/query/bias ['generator', 'encoder', 'layer_7', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_7', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_7', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/query/kernel ['generator', 'encoder', 'layer_7', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_7', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_7', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/value/bias ['generator', 'encoder', 'layer_7', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_7', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_7', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/value/kernel ['generator', 'encoder', 'layer_7', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_7', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_7', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/intermediate/dense/bias ['generator', 'encoder', 'layer_7', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_7', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_7', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/intermediate/dense/kernel ['generator', 'encoder', 'layer_7', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_7', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_7', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/LayerNorm/beta ['generator', 'encoder', 'layer_7', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_7', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_7', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/LayerNorm/gamma ['generator', 'encoder', 'layer_7', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_7', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_7', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/dense/bias ['generator', 'encoder', 'layer_7', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/dense/bias/adam_m ['generator', 'encoder', 'layer_7', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/dense/bias/adam_v ['generator', 'encoder', 'layer_7', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/dense/kernel ['generator', 'encoder', 'layer_7', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_7', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_7/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_7', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_8', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/dense/bias ['generator', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/dense/kernel ['generator', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_8', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/key/bias ['generator', 'encoder', 'layer_8', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_8', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_8', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/key/kernel ['generator', 'encoder', 'layer_8', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_8', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_8', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/query/bias ['generator', 'encoder', 'layer_8', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_8', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_8', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/query/kernel ['generator', 'encoder', 'layer_8', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_8', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_8', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/value/bias ['generator', 'encoder', 'layer_8', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_8', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_8', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/value/kernel ['generator', 'encoder', 'layer_8', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_8', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_8', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/intermediate/dense/bias ['generator', 'encoder', 'layer_8', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_8', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_8', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/intermediate/dense/kernel ['generator', 'encoder', 'layer_8', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_8', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_8', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/LayerNorm/beta ['generator', 'encoder', 'layer_8', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_8', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_8', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/LayerNorm/gamma ['generator', 'encoder', 'layer_8', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_8', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_8', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/dense/bias ['generator', 'encoder', 'layer_8', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/dense/bias/adam_m ['generator', 'encoder', 'layer_8', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/dense/bias/adam_v ['generator', 'encoder', 'layer_8', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/dense/kernel ['generator', 'encoder', 'layer_8', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_8', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_8/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_8', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/LayerNorm/beta ['generator', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/LayerNorm/gamma ['generator', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_9', 'attention', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/dense/bias ['generator', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/dense/bias/adam_m ['generator', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/dense/bias/adam_v ['generator', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/dense/kernel ['generator', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_9', 'attention', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/key/bias ['generator', 'encoder', 'layer_9', 'attention', 'self', 'key', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/key/bias/adam_m ['generator', 'encoder', 'layer_9', 'attention', 'self', 'key', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/key/bias/adam_v ['generator', 'encoder', 'layer_9', 'attention', 'self', 'key', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/key/kernel ['generator', 'encoder', 'layer_9', 'attention', 'self', 'key', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/key/kernel/adam_m ['generator', 'encoder', 'layer_9', 'attention', 'self', 'key', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/key/kernel/adam_v ['generator', 'encoder', 'layer_9', 'attention', 'self', 'key', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/query/bias ['generator', 'encoder', 'layer_9', 'attention', 'self', 'query', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/query/bias/adam_m ['generator', 'encoder', 'layer_9', 'attention', 'self', 'query', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/query/bias/adam_v ['generator', 'encoder', 'layer_9', 'attention', 'self', 'query', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/query/kernel ['generator', 'encoder', 'layer_9', 'attention', 'self', 'query', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/query/kernel/adam_m ['generator', 'encoder', 'layer_9', 'attention', 'self', 'query', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/query/kernel/adam_v ['generator', 'encoder', 'layer_9', 'attention', 'self', 'query', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/value/bias ['generator', 'encoder', 'layer_9', 'attention', 'self', 'value', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/value/bias/adam_m ['generator', 'encoder', 'layer_9', 'attention', 'self', 'value', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/value/bias/adam_v ['generator', 'encoder', 'layer_9', 'attention', 'self', 'value', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/value/kernel ['generator', 'encoder', 'layer_9', 'attention', 'self', 'value', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/value/kernel/adam_m ['generator', 'encoder', 'layer_9', 'attention', 'self', 'value', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/attention/self/value/kernel/adam_v ['generator', 'encoder', 'layer_9', 'attention', 'self', 'value', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/intermediate/dense/bias ['generator', 'encoder', 'layer_9', 'intermediate', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/intermediate/dense/bias/adam_m ['generator', 'encoder', 'layer_9', 'intermediate', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/intermediate/dense/bias/adam_v ['generator', 'encoder', 'layer_9', 'intermediate', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/intermediate/dense/kernel ['generator', 'encoder', 'layer_9', 'intermediate', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/intermediate/dense/kernel/adam_m ['generator', 'encoder', 'layer_9', 'intermediate', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/intermediate/dense/kernel/adam_v ['generator', 'encoder', 'layer_9', 'intermediate', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/LayerNorm/beta ['generator', 'encoder', 'layer_9', 'output', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/LayerNorm/beta/adam_m ['generator', 'encoder', 'layer_9', 'output', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/LayerNorm/beta/adam_v ['generator', 'encoder', 'layer_9', 'output', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/LayerNorm/gamma ['generator', 'encoder', 'layer_9', 'output', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/LayerNorm/gamma/adam_m ['generator', 'encoder', 'layer_9', 'output', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/LayerNorm/gamma/adam_v ['generator', 'encoder', 'layer_9', 'output', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/dense/bias ['generator', 'encoder', 'layer_9', 'output', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/dense/bias/adam_m ['generator', 'encoder', 'layer_9', 'output', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/dense/bias/adam_v ['generator', 'encoder', 'layer_9', 'output', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/dense/kernel ['generator', 'encoder', 'layer_9', 'output', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/dense/kernel/adam_m ['generator', 'encoder', 'layer_9', 'output', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator'
Skipping generator/encoder/layer_9/output/dense/kernel/adam_v ['generator', 'encoder', 'layer_9', 'output', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator'
Skipping generator_predictions/LayerNorm/beta ['generator_predictions', 'LayerNorm', 'beta'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/LayerNorm/beta/adam_m ['generator_predictions', 'LayerNorm', 'beta', 'adam_m'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/LayerNorm/beta/adam_v ['generator_predictions', 'LayerNorm', 'beta', 'adam_v'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/LayerNorm/gamma ['generator_predictions', 'LayerNorm', 'gamma'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/LayerNorm/gamma/adam_m ['generator_predictions', 'LayerNorm', 'gamma', 'adam_m'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/LayerNorm/gamma/adam_v ['generator_predictions', 'LayerNorm', 'gamma', 'adam_v'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/dense/bias ['generator_predictions', 'dense', 'bias'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/dense/bias/adam_m ['generator_predictions', 'dense', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/dense/bias/adam_v ['generator_predictions', 'dense', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/dense/kernel ['generator_predictions', 'dense', 'kernel'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/dense/kernel/adam_m ['generator_predictions', 'dense', 'kernel', 'adam_m'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/dense/kernel/adam_v ['generator_predictions', 'dense', 'kernel', 'adam_v'] 'ElectraModel' object has no attribute 'generator_predictions'
Skipping generator_predictions/output_bias ['generator_lm_head', 'bias'] 'ElectraModel' object has no attribute 'generator_lm_head'
Skipping generator_predictions/output_bias/adam_m ['generator_lm_head', 'bias', 'adam_m'] 'ElectraModel' object has no attribute 'generator_lm_head'
Skipping generator_predictions/output_bias/adam_v ['generator_lm_head', 'bias', 'adam_v'] 'ElectraModel' object has no attribute 'generator_lm_head'

So, my question is, is it the expected behaviour of the Electra model loader or I am doing something wrong? Thanks!

wontfix

Most helpful comment

Hi! I don't really understand how you obtained what you did, what script did you use, what arguments did you put in? The procedure to convert an ELECTRA checkpoint from the official implementation to our implementation is to do the following (feel free to skip the first steps if you already have your checkpoint):

# Get a checkpoint
wget https://storage.googleapis.com/electra-data/electra_small.zip 

# Unzip it
unzip electra_small.zip  

# Get an appropriate configuration file for your model (see below)
vim electra_small/config.json

# Run the script
python $TRANSFORMERS/src/transformers/convert_electra_original_tf_checkpoint_to_pytorch.py \                                                                                                                                                         
    --tf_checkpoint_path=./electra_small/electra_small \
    --config_file=./electra_small/config.json \
    --pytorch_dump_path=pytorch_model.bin \
    --discriminator_or_generator=discriminator

From this you should get the following output:

Initialize PyTorch weight ['discriminator_predictions', 'dense', 'bias'] discriminator_predictions/dense/bias
Initialize PyTorch weight ['discriminator_predictions', 'dense', 'kernel'] discriminator_predictions/dense/kernel
Initialize PyTorch weight ['discriminator_predictions', 'dense_prediction', 'bias'] discriminator_predictions/dense_1/bias
Initialize PyTorch weight ['discriminator_predictions', 'dense_prediction', 'kernel'] discriminator_predictions/dense_1/kernel
Initialize PyTorch weight ['electra', 'embeddings', 'LayerNorm', 'beta'] electra/embeddings/LayerNorm/beta
Initialize PyTorch weight ['electra', 'embeddings', 'LayerNorm', 'gamma'] electra/embeddings/LayerNorm/gamma
[...]
Skipping generator_predictions/dense/bias ['generator_predictions', 'dense', 'bias'] 'ElectraForPreTraining' object has no attribute 'generator_predictions'
Skipping generator_predictions/dense/kernel ['generator_predictions', 'dense', 'kernel'] 'ElectraForPreTraining' object has no attribute 'generator_predictions'
Skipping generator_predictions/output_bias ['generator_lm_head', 'bias'] 'ElectraForPreTraining' object has no attribute 'generator_lm_head'
INFO:transformers.modeling_electra:Skipping generator_predictions/temperature
INFO:transformers.modeling_electra:Skipping global_step
Save PyTorch model to pytorch_model.bin

Which tells you that it ignored the generator layers, but saved the discriminator layers :).

The tricky part here is to craft a configuration file specific to the model. I want to obtain the small discriminator from this checkpoint, so the configuration file is the following:

{
  "attention_probs_dropout_prob": 0.1,
  "hidden_size": 256,
  "intermediate_size": 1024,
  "num_attention_heads": 4,
  "num_hidden_layers": 12,
  "embedding_size": 128,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "type_vocab_size": 2,
  "vocab_size": 30522
}

You can either write it yourself or instantiate it from a transformers.ElectraConfig and save it as a JSON file.

All 7 comments

Hi! I don't really understand how you obtained what you did, what script did you use, what arguments did you put in? The procedure to convert an ELECTRA checkpoint from the official implementation to our implementation is to do the following (feel free to skip the first steps if you already have your checkpoint):

# Get a checkpoint
wget https://storage.googleapis.com/electra-data/electra_small.zip 

# Unzip it
unzip electra_small.zip  

# Get an appropriate configuration file for your model (see below)
vim electra_small/config.json

# Run the script
python $TRANSFORMERS/src/transformers/convert_electra_original_tf_checkpoint_to_pytorch.py \                                                                                                                                                         
    --tf_checkpoint_path=./electra_small/electra_small \
    --config_file=./electra_small/config.json \
    --pytorch_dump_path=pytorch_model.bin \
    --discriminator_or_generator=discriminator

From this you should get the following output:

Initialize PyTorch weight ['discriminator_predictions', 'dense', 'bias'] discriminator_predictions/dense/bias
Initialize PyTorch weight ['discriminator_predictions', 'dense', 'kernel'] discriminator_predictions/dense/kernel
Initialize PyTorch weight ['discriminator_predictions', 'dense_prediction', 'bias'] discriminator_predictions/dense_1/bias
Initialize PyTorch weight ['discriminator_predictions', 'dense_prediction', 'kernel'] discriminator_predictions/dense_1/kernel
Initialize PyTorch weight ['electra', 'embeddings', 'LayerNorm', 'beta'] electra/embeddings/LayerNorm/beta
Initialize PyTorch weight ['electra', 'embeddings', 'LayerNorm', 'gamma'] electra/embeddings/LayerNorm/gamma
[...]
Skipping generator_predictions/dense/bias ['generator_predictions', 'dense', 'bias'] 'ElectraForPreTraining' object has no attribute 'generator_predictions'
Skipping generator_predictions/dense/kernel ['generator_predictions', 'dense', 'kernel'] 'ElectraForPreTraining' object has no attribute 'generator_predictions'
Skipping generator_predictions/output_bias ['generator_lm_head', 'bias'] 'ElectraForPreTraining' object has no attribute 'generator_lm_head'
INFO:transformers.modeling_electra:Skipping generator_predictions/temperature
INFO:transformers.modeling_electra:Skipping global_step
Save PyTorch model to pytorch_model.bin

Which tells you that it ignored the generator layers, but saved the discriminator layers :).

The tricky part here is to craft a configuration file specific to the model. I want to obtain the small discriminator from this checkpoint, so the configuration file is the following:

{
  "attention_probs_dropout_prob": 0.1,
  "hidden_size": 256,
  "intermediate_size": 1024,
  "num_attention_heads": 4,
  "num_hidden_layers": 12,
  "embedding_size": 128,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "type_vocab_size": 2,
  "vocab_size": 30522
}

You can either write it yourself or instantiate it from a transformers.ElectraConfig and save it as a JSON file.

@LysandreJik I used your script to convert the trained model from the origin repo (training on my own data) and it worked. I wonder whether an equal technique to convert this trained model to the Electra tf2 model that implemented in HuggingFace?

@nguyenvulebinh glad the script worked! The script only outputs a PyTorch model but it's very simple to convert that model to TF2. Once you have the converted model, you can then load it in TensorFlow by specifying the from_pt option:

from transformers import TFElectraForPreTraining

model = TFElectraForPreTraining.from_pretrained("directory", from_pt=True)

You can then save that model in .h5 format so that it gets natively loaded by TensorFlow in the future:

model.save_pretrained("directory-tf")

# Can now load directly from TensorFlow without the `from_pt` option:
model = TFElectraForPreTraining.from_pretrained("directory-tf")

@LysandreJik It's really cool! Thank you! I did it 😍

@LysandreJik

Hi,

I have a question on pre-training Electra using the PyTorch base model.

If I want to continue pretraining the Electra model (HuggingFace implementation) on a domain-specific corpus, which model should I use to initialize - the generator or discriminator?

Thanks!

When using the ELECTRA method what you're really interested in is the discriminator.

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

Was this page helpful?
0 / 5 - 0 ratings