BERT on Steroids: Fine-tuning BERT for a dataset using PyTorch and Google Cloud TPUs

Save to stack
Abhishek Thakur Open on YouTube ↗
Google Company Fine-Tuning Technique AI Coding Vertical Developers Audience Analyse Business Data Use Case BERT Technique TPU Tool
From the creator

In this special episode, I show how to train #BERT on a dataset with 30 target variables. You will need Google Cloud #TPU and an instance for the code. Its very important that they are in the same zone. I am using #pytorch ! Dataset used: https://www.kaggle.com/c/google-quest-challenge Inference Kernel: https://www.kaggle.com/abhishek/bert-inference-of-tpu-model/ Follow me on: Twitter: twitter.com/abhi1thakur LinkedIn: https://www.linkedin.com/in/abhi1thakur/

Stop watching · start building
Matched to Google

Makers residency 4th edition

Your idea can be anything. At our last workshops, people built plant-based nutrition businesses, a way to measure planetary resilience, crochet headwear and a way to connect lonely people living in the same building. An asset manager went on to raise an additional £25M on their fund within nine months. The fourth workshop is a full day at KOKO with Nick Sarafa, learning to build with Claude Code. Bring the thing you keep meaning to start. We’ll bring the pizza.

◆ Fri 13 Nov 2026 ◆ KOKO, London
Get tickets See every event
Makers residency 4th edition
Live event
Makers residency 4th edition
Fri 13 Nov 2026
Find a job · 6 live roles

Jobs in AI.
Apply now.

Apply once › get screened › meet the company

See all roles

More like this

Running one yourself?

List your AI event,
wherever it is.

A meetup, a workshop, a hackathon, a conference. Any city, or online. Tell us about it and it lands in front of people already learning this stuff.

List your AI event