Abhinav Bohra
Abhinav Bohra
I see a similar issue while training the text predictor 0.4 on an instance with multiple GPUs on SageMaker Studio.
Hi @ayushbits @ganramkr, Please share whether you could replicate results from the paper on other datasets such as Twitter and CDR?
+1 for this feature. There is a paper on mixed negative sampling(MNS) for Two-Tower neural network. The paper recommends using an index for negative sampling along with in-batch sampling. Link:...