Training BERT Language Model From Scratch On TPUs
In this video I show how you can train your own language model e.g. BERT or any other configuration from scratch on Google's TPUs. Kaggle recently incorporated v3-8 TPUs in their Kernels/Notebooks and I will be using those. The Kernel is available here: https://www.kaggle.com/abhishek/training-language-models-on-tpus-from-scratch Follow me on: Twitter: https://twitter.com/abhi1thakur LinkedIn: https://www.linkedin.com/in/abhi1thakur/ Kaggle: https://kaggle.com/abhishek