TextGrad: Automatic "Differentiation" via TextMert Yuksekgonul et al.
Batch Optimization
In batch optimization, we use the tg.sum function described above. In particular, gradients propagating from multiple instances are concatenated together, thus the optimizer sees all of the feedback to a variable coming from multiple sources.
The syntax is as simple as the following:
1 losses [loss_fn(answer, model(question)) for question, answer in batch] 2 total_loss tg.sum(losses) 3 total_loss.backward()
Code Snippet 4: An example use for batch optimization for question answering.