Akshay Sharma

I have tried(1e-4, 1e-5, 1e-6) with adam but my loss didn't decrease.

hi @Sayyam-Jain @SealQ @arshv27 Any update?

@momo1986 have you figured out how to activate 3d estimation switch?

Hi Team(@patrickorlando) is there any update regarding implementation of non-in batch negative example(like in this [paper](https://research.google/pubs/mixed-negative-sampling-for-learning-two-tower-neural-networks-in-recommendations/))? Can you share the way to implement this?

Hi Team, just adding the cmd which I used: `python train_eval_movielens.py --data_path /content/sample_data --root_dir /content/tmp --agent epsGreedy --per_arm False`