Closed daegonYu closed 2 months ago
Hi @daegonYu,
We did not run ablations on the choice of loss scale. We followed existing literature on this - Echo embeddings hyperparameters for sentence similarity and SimCSE for unsupervised contrastive learning.
oh! I misunderstood. thank you for telling me!
hello!
The loss scale is set to 20 for sentence similarity learning in SimCSE and 50 (default) for supervised contrastive training. Are there any benefits resulting from this loss scale change?