I am recieving the following warning, is this something normal, that should be happening or I am doing something wrong?
The version of the transformers module and other dependencies are the same as in requirements.txt.
I just want to know if I should be worried about this warning.
Some weights of the model checkpoint at bert-large-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.decoder.weight', 'cls.seq_relationship.bias']
This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
I am recieving the following warning, is this something normal, that should be happening or I am doing something wrong?
The version of the transformers module and other dependencies are the same as in requirements.txt.
I just want to know if I should be worried about this warning.
Some weights of the model checkpoint at bert-large-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.decoder.weight', 'cls.seq_relationship.bias']
This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).