https://huggingface.co/bert-base-uncased model pre-trained on dataset https://huggingface.co/datasets/and111/bert_pretrain_phase2 until loss reached 1.96.
https://huggingface.co/bert-base-uncased model pre-trained on dataset https://huggingface.co/datasets/and111/bert_pretrain_phase2 until loss reached 1.96.